The Veterans Health Administration (VHA) has undergone. equality: Electronic Quality Assessment From Narrative Clinical Reports

Size: px
Start display at page:

Download "The Veterans Health Administration (VHA) has undergone. equality: Electronic Quality Assessment From Narrative Clinical Reports"

Transcription

1 ORIGINAL equality ASSESSMENT ARTICLE FROM NARRATIVE CLINICAL REPORTS equality: Electronic Quality Assessment From Narrative Clinical Reports STEVEN H. BROWN, MS, MD; THEODORE SPEROFF, PHD; ELLIOT M. FIELSTEIN, PHD; BRENT A. BAUER, MD; DIETLIND L. WAHNER-ROEDLER, MD; ROBERT GREEVY, PHD; AND PETER L. ELKIN, MD OBJECTIVE: To evaluate an electronic quality (equality) assessment tool for dictated disability examination records. METHODS: We applied automated concept-based indexing techniques to automated quality screening of Department of Veterans Affairs spine disability examinations that had previously undergone gold standard quality review by human experts using established quality indicators. We developed automated quality screening rules and refined them iteratively on a training set of disability examination reports. We applied the resulting rules to a novel test set of spine disability examination reports. The initial data set was composed of all electronically available examination reports (N=125,576) finalized by the Veterans Health Administration between July and September RESULTS: Sensitivity was 91% for the training set and 87% for the test set (P=.02). Specificity was 74% for the training set and 71% for the test set (P=.44). Human performance ranged from 4% to 6% higher (P<.001) than the equality tool in sensitivity and 13% to 16% higher in specificity (P<.001). In addition, the equality tool was equivalent or higher in sensitivity for 5 of 9 individual quality indicators. CONCLUSION: The results demonstrate that a properly authored computer-based expert systems approach can perform quality measurement as well as human reviewers for many quality indicators. Although automation will likely always rely on expert guidance to be accurate and meaningful, equality is an important new method to assist clinicians in their efforts to practice safe and effective medicine. Mayo Clin Proc. 2006;81(11): a single medical record needs to be reviewed in the care of an individual patient, sentences and paragraphs of prose are resources not obstacles. However, when hundreds or thousands of medical records must be reviewed in search of specific facts (eg, for research, population-based care, or quality improvement), manual data abstraction from volumes of free text becomes a time-consuming chore. The costs of manual data abstraction include reviewer time, record logistics (eg, availability, handling, and storage), data identification errors, data transcription errors, data representation errors, sample size reductions, and study design impacts. Electronic health record systems that store free text begin to address the logistical problems but otherwise do little to make data available in a computer-usable form. Three basic methods exist to automatically extract computer-usable information from free text. String matching (keyword searching) is a simple, often effective, approach to detect various medical terms. 6-9 For example, simple keyword searches have used trigger words, such as complication, mental status, or rash, to identify adverse events with moderate success. 10 However, string matching does not identify synonyms or closely related terms. For example, myocardial infarction and heart attack are syn- CI = confidence interval; equality = electronic quality; MCVS = Mayo Clinic Vocabulary Server; NLP = natural language processor; VA = Department of Veterans Affairs; VHA = Veterans Health Administration The Veterans Health Administration (VHA) has undergone a wide-ranging data-driven transformation since the mid-1990s based on rationalization of resource allocation, explicit measurement and accountability for quality and value, and development of an information infrastructure supporting the needs of patients, clinicians, and administrators. 1 Today, the VHA is recognized in lay press such as the Wall Street Journal and the Washington Post for leadership in clinical informatics and performance improvement. 2,3 Despite these notable successes, most clinical documentation in the VHA electronic health record system 4,5 is stored as free text rather than as structured codified data. This preponderance of unstructured information appears to be the norm in most US practice settings. Free text, the result of dictation and transcription, is a rich source of information for medical professionals. For example, when From the Department of Veterans Affairs Compensation and Pension Examination Program, Nashville, Tenn (S.H.B., T.S., E.M.F.); Department of Biomedical Informatics, Vanderbilt University, Nashville, Tenn (S.H.B., E.M.F.); Postdoctoral Fellowship Program in Applied Medical Informatics (S.H.B., T.S., E.M.F.), Tennessee Valley Geriatric Research Education Clinical Center (GRECC) (T.S.), and Health Services Research (TREP) Center for Patient Healthcare Behavior (S.H.B., T.S., R.G.), Veterans Affairs Tennessee Valley Healthcare System, Nashville; Tennessee Valley Veterans Affairs Clinical Research Training Center of Excellence, Nashville, Tenn (T.S.); Veterans Affairs National Quality Scholars Fellowship Program, Nashville, Tenn (T.S.); Division of General Internal Medicine, Department of Medicine (T.S.), Department of Preventive Medicine (T.S.), Department of Biostatistics (T.S., R.G.), and Department of Psychiatry (E.M.F.), Vanderbilt University School of Medicine, Nashville, Tenn; and Division of General Internal Medicine, Mayo Clinic College of Medicine, Rochester, Minn (B.A.B., D.L.W.-R., P.L.E.). The Veterans Affairs Tennessee Valley Healthcare System Center for Patient Healthcare Behavior and US Department of Veterans Affairs Compensation and Pension Examination Program sponsored this study. This work has been supported in part by a grant from the National Library of Medicine (LM A103) and a grant from the Centers for Disease Control and Prevention (PH000022). Dr Elkin, who designed and implemented the software used in this study, is an employee of the Mayo Clinic. Drs Bauer and Wahner-Roedler are employees of the Mayo Clinic. Address reprint requests and correspondence to Steven H. Brown, MD, 2100 West End Ave, Suite 840, Nashville, TN ( steven.brown@med.va.gov) Mayo Foundation for Medical Education and Research 1472 Mayo Clin Proc. November 2006;81(11):

2 onyms for the same underlying concept, but simple string searching would not identify both terms in a single search. Identifying and indexing underlying concepts are much more complex processes. 11,12 Natural language processors (NLPs) are computer programs capable of scanning text documents and applying syntactic and semantic rules to extract information. Natural language processor programs attempt to perform both reading and comprehension. Natural language processor systems require a text parser, which segments a text into words and parts of speech, and domain knowledge rules, which link and combine extracted words and parts of speech to infer higher-level concepts. Natural language processor techniques have been applied to areas such as imaging reports, discharge summaries, 24 general medical texts, clinic-specific notes, pathology reports, 31 adverse event detection, 32 drug and gene data, 33 medical curriculum, 34 and provider order entry. 35 Natural language processing holds great promise but has proved difficult to implement broadly in practice. 36,37 Concept-based indexing uses large-scale, organized collections of health concepts known as ontologies to identify and cluster similar findings within free text. One such ontology, SNOMED CT, consists of a set of uniquely identified concepts, synonyms, hierarchical relations, and other facts that define and interrelate terms. In SNOMED CT, the concept of myocardial infarction is identified by the code and has the synonyms heart attack, infarction of heart, and cardiac infarction. Search engines such as the National Library of Medicine s PubMed satisfy information requests via concept-based indexing. 41 Others have used concept-based indexing on radiology reports, discharge summaries, 45 health-related Web sites, 46 clinical diagnoses, 6,47 and medical narratives. 22 Our work applies concept-based indexing to quality assessment of VHA spine disability examination reports. The studied reports are usually dictated and transcribed with similar structure and content to other types of medical documentation, such as outpatient visits, admission notes, progress notes, consultation notes, and discharge summaries. To help examiners conduct thorough examinations, the Veterans Benefits Administration has translated legalistic disability-rating criteria into 57 examination protocols that examiners are expected to use when performing disability examinations. Despite having detailed protocols to follow, examiners overlook critical elements with alarming regularity. To address this problem, the Department of Veterans Affairs (VA) initiated a national quality improvement program in 2001 based on quality measurement using standardized, validated quality indicators and expert review. 48 The VA produces monthly quality reports to guide improvement initiatives. Quality indicators are applied to a random national sample of examination reports that have been completed and submitted as evidence for disability claim evaluation. Two subject matter experts independently review each examination report to determine whether it meets the quality indicators. If there is any disagreement, a third independent reviewer serves as a tiebreaker. This article aims to evaluate an electronic quality (equality) assessment tool for dictated disability examination records. We describe the application of automated concept-based indexing techniques to assess spine disability examination reports algorithmically for the presence or absence of established quality indicators. We compare the output of the resulting quality-screening program to a gold standard established by expert human review. METHODS DATA SETS We focused our efforts on spine disability examinations for several reasons. The spine examination is one of the most commonly requested disability examinations in the VHA. As such, spine examination quality is routinely monitored and contributes to an overall performance assessment of the VHA Veterans Integrated Service Network directors. Spine examinations also share quality indicators with other disability examination types; thus, we anticipated that computer executable quality rules developed for spine examinations might be usable for other examination types. We extracted 490 spine examination reports and expert review results that were performed as part of a baseline measurement of regional examination quality. The initial data set was composed of all electronically available examination reports (N=125,576) finalized by the VHA between July and September 2001 and stored in the VistA system at a VA medical center. The data set was deidentified. 49 One hundred eighteen examination reports contained insufficient text for analysis (eg, reports that consisted only of see other examination report ) and were excluded from the study. We divided the remaining 372 cases into a training set (20%) to aid rule formulation and refinement and a test set (80%) for rule evaluation. The final training set consisted of 73 examination reports, and the final test set consisted of 299 reports. ROLE OF THE FUNDING SOURCE AND HUMAN SUBJECTS PROTECTION The VA Tennessee Valley Healthcare System Center for Patient Healthcare Behavior and the VA Compensation and Pension Examination Program sponsored this study. The principle investigators and coinvestigators had full access to the data and were responsible for the study protocol, statistical analysis plan, progress of the study, analysis, Mayo Clin Proc. November 2006;81(11):

3 TABLE 1. Example of an Automated Rule* Boolean Boolean Line Mnemonic Criteria Criteria type operator operand line 1 Musculoskeletal CT concept explosion or 0 finding 2 Pain CT concept explosion or 1 3 Asthenia CT concept or 2 4 Muscle rigidity CT concept explosion or 3 5 Instability of joint CT concept explosion or 4 6 Erythema CT concept explosion or 5 7 Inflammation CT concept explosion or 6 8 Ache Ache String or 7 9 Aching Aching String or 8 10 General problem CT concept explosion or 9 and/or complaint 11 Numbness CT concept explosion or 10 *Automated rule created for the quality criterion, Does the report note veteran s subjective complaints? In this example, the rule consists of 11 elements linked by or statements. Column 2 provides a readable shortcut for the concept number or string displayed in column 3. Criteria have 3 types: a single SNOMED CT concept, an explosion of a SNOMED CT concept, or a simple string. reporting of the study, and the decision to publish. The VHA Veterans Integrated Service Network 9 had the opportunity to comment on the manuscript before submission. The institutional review board of Vanderbilt University and the VA Tennessee Valley Healthcare System Research and Development Committee for Human Subjects Protection approved this study. FORMULATION OF COMPUTER-USABLE RULES We used the health assessment language to reformulate all 9 human-readable spine examination quality indicators into a format suitable for computer implementation (Table 1 and Table 2). First, we manually identified the concepts contained in each criterion and mapped them into SNOMED CT using a terminology browser. We mapped TABLE 2. Composition of Automated Quality Screening Rules* No. of SNOMED CT exploded concepts No. of SNOMED CT nonexploded concepts Total terms Total terms No. of No. of Spine disability examination Lines Parent Total including Total including free-text net search quality indicator in rule concepts concepts synonyms concepts synonyms terms terms Does report note veteran s subjective complaints? , ,704 Does report describe effects of the condition on the veteran s usual occupation? Does report describe effects of the condition on the veteran s daily activities? Does report provide each range of motion separately and in degrees? Does report address additional limitation following repetitive use? Do the findings address additional limitation during flare-ups? Does report address objective evidence of painful motion, spasm, weakness, and/or tenderness? If neurological abnormalities are noted, is appropriate worksheet followed? , ,893 Do the objective findings include results of all conducted diagnostic and clinical tests? Total , ,230 *Total term counts also include synonyms for each concept. Additional lines were added to provide structure to the rules that do not contain SNOMED CT concepts, SNOMED CT exploded concepts, or free-text terms Mayo Clin Proc. November 2006;81(11):

4 FIGURE 1. Example of a spine disability examination report that has been indexed by the Mayo Clinic Vocabulary Server. Phrases and words in blue are indexed as positive findings. Phrases and words in red are indexed as negative findings. Words in yellow are structural elements that affect the interpretation of other phrases. concepts to either single SNOMED CT concepts or to explosions of SNOMED CT concepts. An exploded concept is linked to more specific subconcepts within the terminology. For example, the explosion of myocardial infarction includes anterior myocardial infarction, inferior myocardial infarction, lateral myocardial infarction, and several other subtypes of myocardial infarctions. We represented concepts that could not be mapped to SNOMED CT using simple strings. Second, we built complex rules by combining mapped concepts and unmapped strings with the Boolean operators and, or, and not. Finally, we specified which examination report section(s) (eg, history or physical) to which each rule was to be applied. Table 1 is the concept-based indexing algorithm for the spine examination quality indicator that measured whether the report notes subjective complaints. EVALUATION OF COMPUTER-USABLE RULES The health assessment language allows the specification of computer-usable rules that can be applied to each examination via 3 steps. In the first step, the Mayo Clinic Vocabulary Server (MCVS) separates examination results into examination report sections (eg, history or physical). In the second step, the MCVS indexes the document. Before indexing, words are normalized using a variation of the National Library of Medicine s public domain software program Norm 50 from the Unified Medical Language System s knowledge source server, and then sentences are broken into single word and multiword phrases. The MCVS indexes the phrases from each examination using SNOMED CT ; in so doing, it identifies separately phrases that indicate positive, negative, and uncertain assertions and constructs compositional expressions from combinations of simpler concepts (eg, left foot is represented as the body part foot with laterality left ). The MCVS has been extensively tested in Mayo s usability laboratory and has been published in the medical literature. 46,47,51-53 Public domain concept-based indexing tools, such as the National Library of Medicine s MetaMap, 54,55 could also have been used. Figure 1 is an example of a spine examination report that has been marked up by the computer to highlight indexed terms. In the third step, a rules evaluation engine sequentially applies the rules expressed in health assessment language against the indices created for each examination report. Figure 2 is an example of the same spine examination report that has been formatted by the system to highlight sentences that meet quality indicator 6 ( Do the findings address additional limitation during flare-ups? ). Seven cycles of rule improvement were conducted using the training set. In the first step of each cycle, the computer- Mayo Clin Proc. November 2006;81(11):

5 FIGURE 2. Example of a spine disability examination report that has been formatted to support quality measurement. The highlighted sentence contains indexed concepts that are linked by a rule to quality indicator 6 ( Do the findings address additional limitation during flare-ups? ). usable rules were applied to each disability examination included in the training set using concept-based indexing software. The results of the algorithmic approach were compared to the gold standard of human expert review. The true-positive rate, false-positive rate, true-negative rate, false-negative rate, sensitivity, and specificity were calculated for each quality rule. The second step of the rule improvement cycle was a manual failure analysis of the false-positive and false-negative results. Rule modification based on the failure analysis was the final step of the cycle. Mapped concepts or strings were either added to or deleted from existing rules in an attempt to improve performance. When improvement cycles ceased to be effective using the training set, we evaluated the resulting final rule set on the test set of spine examinations. STATISTICAL ANALYSES During development, the evolving rules were applied iteratively to the training set (n=73) of examination reports. The results of the algorithmic review were compared with the gold standard results generated by human expert review. Sensitivity, specificity, and percentage of agreement with the consensus gold standard were generated for each rule. After development, the final rules for each examination type were applied to the test set (n=299) of disability examinations. The same statistics were calculated for the test set as for the training set. Results are presented for each examination-specific quality criterion singly and then aggregated. Sensitivity and specificity for the training and test sets were compared using the Fisher exact test for independent samples. Algorithm sensitivity and specificity for the training set and test set items were compared with the corresponding performance of each individual human reviewer (denoted as human 1 and human 2) using an exact binomial version of the McNemar test for paired data to account for small cell sizes. To test total performance across all 9 items and properly account for nonindependent outcomes, permutation resampling tests, each with 10,000 runs, were conducted to generate a distribution-free P value. 56 Statistical analyses were conducted with the R software. 57 Correlation coefficients and 95% confidence intervals (CIs) based on the Fisher z transformation were calculated between the computer s percentage of agreement with the gold standard results and that of the human reviewers on the 9 quality indicators. RESULTS RULE FORMULATION The concepts used in the 9 spine examination specific quality indicators were mapped to 4 unexploded SNOMED CT concepts and 49 exploded SNOMED CT concepts 1476 Mayo Clin Proc. November 2006;81(11):

6 TABLE 3. Computer Performance on the Training Set (n=73) and Test Set (n=299)* Sensitivity Specificity Training Test Training Test Agreement (%) True- True- True- True- Quality positive Sensitivity positive Sensitivity P negative Specificity negative Specificity P indicator Training Test rate (No.) (%) rate (No.) (%) value rate (No.) (%) rate (No.) (%) value > > > > Total *Agreement (%) is the agreement between the computer-based scoring and the gold standard consensus of human reviewers. P values are from the Fisher exact test. (composed of the parent term and its child concepts). These 49 exploded concepts subsumed 9197 single concepts in the SNOMED CT terms and 53,144 synonyms as stored in the MCVS. There were 17 MCVS synonyms for the 4 unexploded concepts used in the rules. Sixty-nine free-text strings, representing concepts not found in SNOMED CT, were also used. The net number of search terms was 53,230. The mapped terms were then combined with Boolean operators to specify 124 computer-implementable rules. The number of Boolean operations required to express a single free-text quality criteria ranged from 3 to 39 (average, 13.8). An example of one of the human-readable quality criteria and its associated computer-implementable rules is given in Table 1. A breakdown describing the components of each individual spine examination rule is presented in Table 2. ALGORITHM PERFORMANCE Table 3 summarizes the performance of the computerized algorithm for sensitivity, specificity, and percentage of agreement with the consensus gold standard for the training and test sets. Sensitivity was 91% for the training set and 87% for the test set (P=.02). Specificity was 74% for the training set and 71% for the test set (P=.44). The small decline from training development to the test set indicates validation of the computer performance. Table 4 and Table 5 provide comparisons of the computerized algorithms with the human reviewers for the training set and the test set of spine disability examinations, respectively. On the test set, the human review sensitivity was 91% and 93%, which was 4% to 6% higher than the computer performance (P<.001). The computer sensitivity performance was the same as human review for 4 of the quality indicators, higher on 1 quality indicator, and lower on 4 quality indicators. On the test set, the human review specificity was 84% and 88%, which was higher than the computer performance of 71% (P<.001). The computer specificity performance was lower on 5 quality indicators for human review 1 and on 7 quality indicators for human review 2; the sensitivity for the computer performance was TABLE 4. Comparison of Human Reviewers and the Computer System Against the Gold Standard When Classifying the Training Set* Agreement (%) Sensitivity (%) Specificity (%) Quality Comput- Human Human Comput- Human P Human P Comput- Human P Human P indicator er 1 2 No. er 1 value 2 value No. er 1 value 2 value > > > > > > > > > > > > < > >.99 Total > *P values are from the exact binomial (McNemar) test for quality indicators and the permutation test for the total, accounting for nonindependent observations. Mayo Clin Proc. November 2006;81(11):

7 TABLE 5. Comparison of Human Reviewers and the Computer System Against the Gold Standard When Classifying the Test Set* Agreement (%) Sensitivity (%) Specificity (%) Quality Comput- Human Human Comput- Human P Human P Comput- Human P Human P indicator er 1 2 No. er 1 value 2 value No. er 1 value 2 value > > < < < > < < < < < > < < < < < < Total < < < <.001 *P values are from the exact binomial (McNemar) test for quality indicators and the permutation test for the total, accounting for nonindependent observations. the same or higher for 5 quality items for both human reviews. In an effort to understand whether humans and the computer performed well or poorly on the same items, we calculated the association between the computer s percent agreement with the consensus gold standard on the 9 quality indicators with the percent agreement of each of the human reviewers to the consensus gold standard. The correlation coefficient between the computer and human reviewer 1 was (95% CI, ). The same statistic for human reviewer 2 was (95% CI, ). DISCUSSION Our findings of an overall test set sensitivity of 87% and specificity of 71% demonstrate the feasibility of spine disability examination quality measurement using this automated equality approach. The sensitivity and specificity of the equality approach were in the range of many tests used routinely in medicine. For example, dobutamine echocardiography has a sensitivity of 92% and a specificity of 75%. 58 The point of this article is not to promote a specific software platform but to enlighten our colleagues about this new modality for improving quality of care and potential cost savings related to quality review. The comparison of computer reviews to the 2 human expert reviews shows similar or better performance by the computerized approach for 10 of 18 comparisons of sensitivity on the test set. Human performance was superior to computer performance with regard to specificity on 12 of 18 items. The performance of the computer was highest on the quality indicators that the human reviewers also performed well and lowest on the items in which the human reviewers also had difficulties as evidenced by the extent of correlation between computer and human performance. Overall, human performance was better than computer performance in sensitivity (4%-6%) and specificity (13%- 16%). Although humans and the equality computer were more concordant in sensitivity, in some cases specificity was substantially better for humans than the computer. Sensitivity results were statistically significant, but the clinical difference does not appear meaningful, especially because, in part, the human reviewers would be expected to have a performance advantage because their scores were incorporated into the consensus score that determined the gold standard. Thus, the judgment of each human reviewer was correlated with the gold standard, whereas the computer reviews are independent of the gold standard. Future studies should use an independent third human sample to eliminate the bias favoring the human reviewer. We encountered a number of different types of errors during the development and refinement of the rules. We have previously found that missing synonymy within SNOMED CT accounts for 94.9% of indexing failures. 53 When terms and synonyms are present, the MCVS indexer has been shown to have a sensitivity of 99.7% and specificity of 97.9%. During early stages of rule development, both sensitivity and specificity tend to improve. In later stages, increased sensitivity comes at the cost of decreased specificity and vice versa. Our results are comparable to the results of other investigators who have used concept-based indexing and NLP methods. However, the tasks to which indexing methods have been applied vary considerably, as does the performance of those techniques via the usual measures of sensitivity and specificity. We believe that the comparison of computer results to human experts is a potentially fieldleveling metric. For example, Fiszman et al 16 examined extracting pneumonia-related concepts from 292 chest x- ray reports using NLP techniques. They found that the performance of the NLP system was similar to that of physicians and superior to that of laypersons and keyword searches. Hripcsak et al 19 developed NLP techniques to evaluate chest x-ray films for the presence of 6 conditions Mayo Clin Proc. November 2006;81(11):

8 The NLP had a sensitivity of 81% and a specificity of 98%. These values were similar to those obtained by physicians in the study. The task of screening examination reports for quality criteria presents different challenges than trying to provide clinical decision support. Certain criteria demand only that an issue be addressed; the precise result itself may not be relevant for quality review. For example, to successfully evaluate the quality criterion, Does report note veteran s subjective complaints? it is not necessary to know if the examiner documented presence or absence of particular subjective complaints; it is sufficient that symptoms are mentioned in either context. It can be particularly challenging to algorithmically determine when concepts are expressed as negations (eg, no fracture present) or uncertainties (eg, possible fracture) Furthermore, the current study examined only one type of disability examination. Other examination types might be less amenable to automated quality screening. This study takes a step beyond the identification of concepts present in free text. Our system permits the construction of complex rules from targeted concepts and strings. These rules allow the computer system, as a component of an overall quality measurement program, to begin to answer more abstract questions about examination reports, such as, Was this report of high quality? Although spine examinations accounted for approximately 8% of total disability examinations performed between October and December 2004, they still affect a large number of veterans. During the same quarter, the VHA performed 195,772 examinations at more than 130 sites across the United States. If this approach can be generalized, it could affect a much larger group relatively quickly because the top 10 most commonly performed examinations account for two thirds of all examinations performed (>500,000 examinations per year). A computer-based tool that can read text, abstract and identify concepts, and assign scoring with high sensitivity could have a significant quantitative and qualitative impact on screening tasks, such as case finding for quality assurance and decision support for human reviewers abstracting quality indicators. Computerbased screening is tireless and could be applied to large numbers of examinations. This strategy is efficient and may help realize significant cost savings. Computer-based screening may also allow human reviewers to focus their efforts on difficult rather than routine assessments. The examinations provide crucial evidence for the claims process. Examination-related questions are a common cause of benefits determination appeals and judicial remand. We believe that all examinations should be reviewed for quality before being returned to the requesting administrative office. A workable automated or even semiautomated quality screening approach might help realize this goal by reducing human review costs and increasing review consistency. In the near future, we plan to develop and evaluate rules that cover additional examination types. Our efforts will be directed toward the most frequently performed VA disability examinations. If these plans can be successfully implemented for disability examination screening, we would have cause to hope that other protocol-based examination reports may also be efficiently reviewed. Other areas that might possibly benefit from this approach include screening for other more common quality measures, such as the Health Employer Data and Information Set measures and the Joint Commission on Accreditation of Healthcare Organization s ORYX criteria We are also evaluating methods to integrate automated review into our standard work processes. Integrating the tools into our routine national quality screening process is a first step. Implementations being evaluated include helping human experts perform reviews more quickly, by finding relevant statements in free-text disability examination reports and highlighting the relevant text within the examination reports (Figure 2), and a stand-alone automated review function to complement existing human expert reviewers. Finally, we are exploring access to just-in-time quality review for practitioners in the field to speed the evidencegathering process and provide real-time or near-time feedback. A scalable quality screening server accessed via standardized messages sent over the VA internal network is one potential technical approach. Future research should focus on determining if real-time feedback to clinicians from such a system can effectively improve patient outcomes by preventing medical error and encouraging the best practice of medicine in other settings. CONCLUSION A properly authored computer-based expert systems approach can perform quality measurement as well as human reviewers for many quality indicators. We believe that quality assurance and quality improvement, whether automated or manual, must be guided by subject matter experts and follow valid and reproducible processes. Automation will likely always rely on expert guidance to be accurate and meaningful. equality is an important new method to assist clinicians in their efforts to practice safe and effective medicine. We dedicate this article to the memory of Dr Vladimir Slamecka, pioneering medical informatician and founding director of the Georgia Tech School of Information and Computer Science. We acknowledge the contributions of Glenda Taylor, Edna MacDonald, and the quality review staff supporting the Compensation and Pension Examination Program. Mayo Clin Proc. November 2006;81(11):

9 REFERENCES 1. Perlin JB, Kolodner RM, Roswell RH. The Veterans Health Administration: quality, value, accountability, and information as transforming strategies for patient-centered care. Am J Manag Care. 2004;10(11, pt 2): Boodman S. No end to errors. Washington Post. December 3, 2002:HE01 3. Rundle R. In the drive to mine medical data, VHA is the unlikely leader. Wall Street Journal. December 10, 2001:1. 4. Kolodner RM. Computerizing Large Integrated Health Networks: The VA Success. New York, NY: Springer-Verlag; Brown SH, Lincoln MJ, Groen PJ, Kolodner RM. VistA: U.S. Department of Veterans Affairs national-scale HIS. Int J Med Inform. 2003;69: Chute CG, Yang Y. An evaluation of concept based latent semantic indexing for clinical information retrieval. Proc Annu Symp Comput Appl Med Care. 1992: Hersh WR, Hickam DH. A comparison of two methods for indexing and retrieval from a full-text medical database. Med Decis Making. 1993;13: Hersh WR, Hickam DH, Leone TJ. Words, concepts, or both: optimal indexing units for automated information retrieval. Proc Annu Symp Comput Appl Med Care. 1992: Goldman JA, Chu WW, Parker DS, Goldman RM. Term domain distribution analysis: a data mining tool for text databases. Methods Inf Med. 1999;38: Murff HJ, Forster AJ, Peterson JF, Fiskio JM, Heiman HL, Bates DW. Electronically screening discharge summaries for adverse medical events. J Am Med Inform Assoc July-Aug;10: Epub 2003 Mar Baud RH, Lovis C, Ruch P, Rassinoux AM. Conceptual search in electronic patient record. Medinfo. 2001;10(pt 1): Hersh WR, Greenes RA. SAPHIRE an information retrieval system featuring concept matching, automatic indexing, probabilistic retrieval, and hierarchical relationships. Comput Biomed Res. 1990;23: Aronsky D, Fiszman M, Chapman WW, Haug PJ. Combining decision support methodologies to diagnose pneumonia. Proc AMIA Symp. 2001: Chapman WW, Fizman M, Chapman BE, Haug PJ. A comparison of classification algorithms to automatically identify chest X-ray reports that support pneumonia. J Biomed Inform. 2001;34: Elkins JS, Friedman C, Boden-Albala B, Sacco RL, Hripcsak G. Coding neuroradiology reports for the Northern Manhattan Stroke Study: a comparison of natural language processing and manual review. Comput Biomed Res. 2000;33: Fiszman M, Chapman WW, Aronsky D, Evans RS, Haug PJ. Automatic detection of acute bacterial pneumonia from chest X-ray reports. J Am Med Inform Assoc. 2000;7: Friedman C, Knirsch C, Shagina L, Hripcsak G. Automating a severity score guideline for community-acquired pneumonia employing medical language processing of discharge summaries. Proc AMIA Symp. 1999: Hripcsak G, Austin JH, Alderson PO, Friedman C. Use of natural language processing to translate clinical information from a database of 889,921 chest radiographic reports. Radiology. 2002;224: Hripcsak G, Friedman C, Alderson PO, DuMouchel W, Johnson SB, Clayton PD. Unlocking clinical data from narrative reports: a study of natural language processing. Ann Intern Med. 1995;122: Hripcsak G, Knirsch CA, Jain NL, Pablos-Mendez A. Automated tuberculosis detection. J Am Med Inform Assoc. 1997;4: Mamlin BW, Heinze DT, McDonald CJ. Automated extraction and normalization of findings from cancer-related free-text radiology reports. AMIA Annu Symp Proc. 2003: Nadkarni P, Chen R, Brandt C. UMLS concept indexing for production databases: a feasibility study. J Am Med Inform Assoc. 2001;8: Trick WE, Chapman WW, Wisniewski MF, Peterson BJ, Solomon SL, Weinstein RA. Electronic interpretation of chest radiograph reports to detect central venous catheters. Infect Control Hosp Epidemiol. 2003;24: Sager N, Lyman M, Tick LJ, Nhan NT, Bucknall CE. Natural language processing of asthma discharge summaries for the monitoring of patient care. Proc Annu Symp Comput Appl Med Care. 1993: Friedman C. A broad-coverage natural language processing system. Proc AMIA Symp. 2000: Ruch P, Baud R, Geissbuhler A, Rassinoux AM. Comparing general and medical texts for information retrieval based on natural language processing: an inquiry into lexical disambiguation. Medinfo. 2001;10(pt 1): Sager N, Lyman M, Nhan NT, Tick LJ. Medical language processing: applications to patient data representation and automatic encoding. Methods Inf Med. 1995;34: Barrows RC Jr, Busuioc M, Friedman C. Limited parsing of notational text visit notes: ad-hoc vs. NLP approaches. Proc AMIA Symp. 2000: Hyun S, Bakken S, Friedman C, Johnson SB. Natural language processing challenges in HIV/AIDS clinic notes. AMIA Annu Symp Proc. 2003: Sager N, Bross ID, Story G, Bastedo P, Marsh E, Shedd D. Automatic encoding of clinical narrative. Comput Biol Med. 1982;12: Xu H, Friedman C. Facilitating research in pathology using natural language processing. AMIA Annu Symp Proc. 2003: Bates DW, Evans RS, Murff H, Stetson PD, Pizziferri L, Hripcsak G. Detecting adverse events using information technology. J Am Med Inform Assoc. 2003;10: Rindflesch TC, Tanabe L, Weinstein JN, Hunter L. EDGAR: extraction of drugs, genes and relations from the biomedical literature. Pac Symp Biocomput. 2000: Wehbe FH, Armstrong BK, Peachey MR, Denny JC, Spickard A III. Formative evaluation to guide early deployment of an online content management tool for medical curriculum. AMIA Annu Symp Proc. 2003: Lovis C, Chapko MK, Martin DP, et al. Evaluation of a command-line parser-based order entry pathway for the Department of Veterans Affairs electronic patient record. J Am Med Inform Assoc. 2001;8: Friedman C, Hripcsak G. Natural language processing and its future in medicine. Acad Med. 1999;74: Rassinoux AM, Wagner JC, Lovis C, Baud RH, Rector A, Scherrer JR. Analysis of medical texts based on a sound medical model. Proc Annu Symp Comput Appl Med Care. 1995: National Library of Medicine. SNOMED Clinical Terms To Be Added To UMLS Metathesaurus. Available at: /umls /Snomed/snomed_announcement.html. Accessed October 3, Spackman KA, Campbell KE, Cote RA. SNOMED RT: a reference terminology for health care. Proc AMIA Annu Fall Symp. 1997: Stearns MQ, Price C, Spackman KA, Wang AY. SNOMED clinical terms: overview of the development process and project status. Proc AMIA Symp. 2001: Nelson SJ, Johnston D, Humphreys BL. Relationships in medical subject headings. In: Bean CA, Green R, eds. Relationships in the Organization of Knowledge. New York, NY: Kluwer Academic Publishers; 2001: Hersh W, Mailhot M, Arnott-Smith C, Lowe H. Selective automated indexing of findings and diagnoses in radiology reports. J Biomed Inform. 2001;34: Huang Y, Lowe HJ, Hersh WR. A pilot study of contextual UMLS indexing to improve the precision of concept-based representation in XMLstructured clinical radiology reports. J Am Med Inform Assoc Nov-Dec; 10: Epub 2003 Aug Taira RK, Johnson DB, Bhushan V, et al. A concept-based retrieval system for thoracic radiology. J Digit Imaging. 1996;9: Happe A, Pouliquen B, Burgun A, Cuggia M, Le Beux P. Automatic concept extraction from spoken medical reports. Int J Med Inform. 2003;70: Elkin PL, Ruggieri A, Bergstrom L, et al. A randomized controlled trial of concept based indexing of Web page content. Proc AMIA Symp. 2000: Elkin PL, Ruggieri AP, Brown SH, et al. A randomized controlled trial of the accuracy of clinical record retrieval using SNOMED-RT as compared with ICD9-CM. Proc AMIA Symp. 2001: Weeks WB, Mills PD, Waldron J, Brown SH, Speroff T, Coulson LR. A model for improving the quality and timeliness of compensation and pension examinations in VA facilities. J Healthc Manag. 2003;48: Fielstein EM, Brown SH, Speroff T. Algorithmic de-identification of VA medical exam text for HIPAA privacy compliance: preliminary findings. MedInfo. 2004: Browne AC, Divita G, Aronson AR, McCray AT. UMLS language and vocabulary tools. AMIA Annu Symp Proc. 2003: Mayo Clin Proc. November 2006;81(11):

10 51. Brown SH, Bauer BA, Wahner-Roedler DL, Elkin PL. Coverage of oncology drug indication concepts and compositional semantics by SNOMED- CT. AMIA Annu Symp Proc. 2003: Elkin PL, Brown SH. Automated enhancement of description logicdefined terminologies to facilitate mapping to ICD9-CM. J Biomed Inform. 2002;35: Elkin PL, Brown SH, Husser CS, et al. Evaluation of the content coverage of SNOMED CT: ability of SNOMED clinical terms to represent clinical problem lists. Mayo Clin Proc. 2006;81: Aronson AR. Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. Proc AMIA Symp. 2001: Pratt W, Yetisgen-Yildiz M. A study of biomedical concept identification: MetaMap vs. people. AMIA Annu Symp Proc. 2003: Good PI. Permutation, Parametric and Bootstrap Tests of Hypotheses. 3rd ed. New York, NY: Springer; R Foundation for Statistical Computing. The R Project for Statistical Computing. Available at: Accessed October 3, Marzullo P, Parodi O, Sambuceti G, et al. Myocardial viability: nuclear medicine versus stress echocardiography. Echocardiography. 1995;12: Chapman WW, Bridewell W, Hanbury P, Cooper GF, Buchanan BG. A simple algorithm for identifying negated findings and diseases in discharge summaries. J Biomed Inform. 2001;34: Krauthammer M, Hripcsak G. A knowledge model for the interpretation and visualization of NLP-parsed discharged summaries. Proc AMIA Symp. 2001: Mutalik PG, Deshpande A, Nadkarni PM. Use of general-purpose negation detection to augment concept indexing of medical documents: a quantitative study using the UMLS. J Am Med Inform Assoc. 2001;8: Elkin PL, Brown SH, Bauer BA, et al. A controlled trial of automated classification of negation from clinical notes. BMC Med Inform Decis Mak [serial online]. 2005;5:13. Available at: Accessed October 3, HEDIS 2.0: a precursor to national report cards for health plans. Bus Health. 1993;11: NCQA releases HEDIS 2.0 standards: quality monitoring group prepares to test report card measures. QRC Advis. 1994;10: Berry K. Legislative forum: HEDIS 2.0: a standardized method to evaluate health plans. J Healthc Qual. 1993;15: Campbell S. Outcomes-based accreditation evolves slowly with JCAHO s Oryx initiative. Health Care Strateg Manage. 1997;15: DeMott K. JCAHO introduces ORYX for outcomes-based accreditation. Qual Lett Healthc Lead. 1997;9: Popovich M. The Joint Commission s ORYX initiative. Caring. 1998; 17: Mayo Clin Proc. November 2006;81(11):

Analyzing the Semantics of Patient Data to Rank Records of Literature Retrieval

Analyzing the Semantics of Patient Data to Rank Records of Literature Retrieval Proceedings of the Workshop on Natural Language Processing in the Biomedical Domain, Philadelphia, July 2002, pp. 69-76. Association for Computational Linguistics. Analyzing the Semantics of Patient Data

More information

EDUCATION/TRAINING (Begin with baccalaureate or other initial professional education, such as nursing, and include postdoctoral training.

EDUCATION/TRAINING (Begin with baccalaureate or other initial professional education, such as nursing, and include postdoctoral training. NAME Henry Lowe, M.D. BIOGRAPHICAL SKETCH Provide the following information for the key personnel and other significant contributors in the order listed on Form Page 2. Follow this format for each person.

More information

Extracting Diagnoses from Discharge Summaries

Extracting Diagnoses from Discharge Summaries Extracting Diagnoses from Discharge Summaries William Long, PhD CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA Abstract We have developed a program for extracting the diagnoses and procedures

More information

Evaluation of SNOMED Coverage of Veterans Health Administration Terms

Evaluation of SNOMED Coverage of Veterans Health Administration Terms MEDINFO 2004 M. Fieschi et al. (Eds) Amsterdam: IOS Press 2004 IMIA. All rights reserved Evaluation of SNOMED Coverage of Veterans Health Administration Terms Janet FE Penz a, Steven H Brown b, John S

More information

Evaluating E&M Coding Accuracy of GoCode as Compared to Internal Medicine Physicians and Auditors

Evaluating E&M Coding Accuracy of GoCode as Compared to Internal Medicine Physicians and Auditors Evaluating E&M Coding Accuracy of GoCode as Compared to Internal Medicine Physicians and Auditors Evaluating E&M Coding Accuracy of GoCode as Compared to Internal Medicine Physicians and Auditors by Rhonda

More information

Using Regular Expressions to Abstract Blood Pressure and Treatment Intensification Information from the Text of Physician Notes

Using Regular Expressions to Abstract Blood Pressure and Treatment Intensification Information from the Text of Physician Notes Journal of the American Medical Informatics Association Volume 13 Number 6 Nov / Dec 2006 691 Case Report Using Regular Expressions to Abstract Blood Pressure and Treatment Intensification Information

More information

Automatic Identification of Pneumonia Related Concepts on Chest x-ray Reports

Automatic Identification of Pneumonia Related Concepts on Chest x-ray Reports Automatic Identification of Pneumonia Related Concepts on Chest x-ray Reports Marcelo Fiszman MD, Wendy W. Chapman, Scott R. Evans Ph.D., Peter J. Haug MD Department of Medical Informatics, LDS Hospital,

More information

Query Refinement: Negation Detection and Proximity Learning Georgetown at TREC 2014 Clinical Decision Support Track

Query Refinement: Negation Detection and Proximity Learning Georgetown at TREC 2014 Clinical Decision Support Track Query Refinement: Negation Detection and Proximity Learning Georgetown at TREC 2014 Clinical Decision Support Track Christopher Wing and Hui Yang Department of Computer Science, Georgetown University,

More information

Comparing ICD9-Encoded Diagnoses and NLP-Processed Discharge Summaries for Clinical Trials Pre-Screening: A Case Study

Comparing ICD9-Encoded Diagnoses and NLP-Processed Discharge Summaries for Clinical Trials Pre-Screening: A Case Study Comparing ICD9-Encoded Diagnoses and NLP-Processed Discharge Summaries for Clinical Trials Pre-Screening: A Case Study Li Li, MS, Herbert S. Chase, MD, Chintan O. Patel, MS Carol Friedman, PhD, Chunhua

More information

A Study of Abbreviations in Clinical Notes Hua Xu MS, MA 1, Peter D. Stetson, MD, MA 1, 2, Carol Friedman Ph.D. 1

A Study of Abbreviations in Clinical Notes Hua Xu MS, MA 1, Peter D. Stetson, MD, MA 1, 2, Carol Friedman Ph.D. 1 A Study of Abbreviations in Clinical Notes Hua Xu MS, MA 1, Peter D. Stetson, MD, MA 1, 2, Carol Friedman Ph.D. 1 1 Department of Biomedical Informatics, Columbia University, New York, NY, USA 2 Department

More information

Lessons Extracting Diseases from Discharge Summaries

Lessons Extracting Diseases from Discharge Summaries Lessons Extracting Diseases from Discharge Summaries William Long, PhD CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA Abstract We developed a program to extract diseases and procedures

More information

Retrieving disorders and findings: Results using SNOMED CT and NegEx adapted for Swedish

Retrieving disorders and findings: Results using SNOMED CT and NegEx adapted for Swedish Retrieving disorders and findings: Results using SNOMED CT and NegEx adapted for Swedish Maria Skeppstedt 1,HerculesDalianis 1,andGunnarHNilsson 2 1 Department of Computer and Systems Sciences (DSV)/Stockholm

More information

Not all NLP is Created Equal:

Not all NLP is Created Equal: Not all NLP is Created Equal: CAC Technology Underpinnings that Drive Accuracy, Experience and Overall Revenue Performance Page 1 Performance Perspectives Health care financial leaders and health information

More information

A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text

A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text Anthony Nguyen 1, Michael Lawley 1, David Hansen 1, Shoni Colquist 2 1 The Australian e-health Research Centre, CSIRO ICT

More information

Semantic Alignment between ICD-11 and SNOMED-CT. By Marcie Wright RHIA, CHDA, CCS

Semantic Alignment between ICD-11 and SNOMED-CT. By Marcie Wright RHIA, CHDA, CCS Semantic Alignment between ICD-11 and SNOMED-CT By Marcie Wright RHIA, CHDA, CCS World Health Organization (WHO) owns and publishes the International Classification of Diseases (ICD) WHO was entrusted

More information

International Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program (non US/Canada) Curriculum

International Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program (non US/Canada) Curriculum International Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program (non US/Canada) Curriculum Effective: July 2015 INTERNATIONAL POSTPROFESSIONAL DOCTORAL OF PHYSICAL

More information

Automatic Identification & Classification of Surgical Margin Status from Pathology Reports Following Prostate Cancer Surgery

Automatic Identification & Classification of Surgical Margin Status from Pathology Reports Following Prostate Cancer Surgery Automatic Identification & Classification of Surgical Margin Status from Pathology Reports Following Prostate Cancer Surgery Leonard W. D Avolio MS a,b, Mark S. Litwin MD c, Selwyn O. Rogers Jr. MD, MPH

More information

A Descriptive Delta for Identifying Changes in SNOMED CT

A Descriptive Delta for Identifying Changes in SNOMED CT A Descriptive Delta for Identifying Changes in SNOMED CT Christopher Ochs, Yehoshua Perl, Gai Elhanan Department of Computer Science New Jersey Institute of Technology Newark, NJ, USA {cro3, perl, elhanan}@njit.edu

More information

Identifying Deviations from Usual Medical Care using a Statistical Approach

Identifying Deviations from Usual Medical Care using a Statistical Approach Identifying Deviations from Usual Medical Care using a Statistical Approach Shyam Visweswaran, MD, PhD 1, James Mezger, MD, MS 2, Gilles Clermont, MD, MSc 3, Milos Hauskrecht, PhD 4, Gregory F. Cooper,

More information

Toward a Unified Representation of Findings in Clinical Radiology

Toward a Unified Representation of Findings in Clinical Radiology Toward a Unified Representation of Findings in Clinical Radiology Valérie Bertaud a, Jérémy Lasbleiz ab, Fleur Mougin a, Franck Marin a, Anita Burgun a, Régis Duvauferrier ab a EA 3888, LIM, Faculty of

More information

Pilot Study: Clinical Trial Task Ontology Development. A prototype ontology of common participant-oriented clinical research tasks and

Pilot Study: Clinical Trial Task Ontology Development. A prototype ontology of common participant-oriented clinical research tasks and Pilot Study: Clinical Trial Task Ontology Development Introduction A prototype ontology of common participant-oriented clinical research tasks and events was developed using a multi-step process as summarized

More information

Keeping Abreast of Breast Imagers: Radiology Pathology Correlation for the Rest of Us

Keeping Abreast of Breast Imagers: Radiology Pathology Correlation for the Rest of Us SIIM 2016 Scientific Session Quality and Safety Part 1 Thursday, June 30 8:00 am 9:30 am Keeping Abreast of Breast Imagers: Radiology Pathology Correlation for the Rest of Us Linda C. Kelahan, MD, Medstar

More information

An Ontology for Healthcare Quality Indicators: Challenges for Semantic Interoperability

An Ontology for Healthcare Quality Indicators: Challenges for Semantic Interoperability 414 Digital Healthcare Empowering Europeans R. Cornet et al. (Eds.) 2015 European Federation for Medical Informatics (EFMI). This article is published online with Open Access by IOS Press and distributed

More information

A Study on a Comparison of Diagnostic Domain between SNOMED CT and Korea Standard Terminology of Medicine. Mijung Kim 1* Abstract

A Study on a Comparison of Diagnostic Domain between SNOMED CT and Korea Standard Terminology of Medicine. Mijung Kim 1* Abstract , pp.49-60 http://dx.doi.org/10.14257/ijdta.2016.9.11.05 A Study on a Comparison of Diagnostic Domain between SNOMED CT and Korea Standard Terminology of Medicine Mijung Kim 1* 1 Dept. Of Health Administration,

More information

Pneumonia identification using statistical feature selection

Pneumonia identification using statistical feature selection Pneumonia identification using statistical feature selection Research and applications Cosmin Adrian Bejan, 1 Fei Xia, 1,2 Lucy Vanderwende, 1,3 Mark M Wurfel, 4 Meliha Yetisgen-Yildiz 1,2 < An additional

More information

Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program. Curriculum

Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program. Curriculum Postprofessional Doctoral of Physical Therapy (DPT) in Musculoskeletal Management Program Curriculum Effective: January 2014 POSTPROFESSIONAL DOCTORAL OF PHYSICAL THERAPY (DPT) IN MUSCULOSKELETAL MANAGEMENT

More information

On-time clinical phenotype prediction based on narrative reports

On-time clinical phenotype prediction based on narrative reports On-time clinical phenotype prediction based on narrative reports Cosmin A. Bejan, PhD 1, Lucy Vanderwende, PhD 2,1, Heather L. Evans, MD, MS 3, Mark M. Wurfel, MD, PhD 4, Meliha Yetisgen-Yildiz, PhD 1,5

More information

Matching GP terms to the ICD-10-AM index

Matching GP terms to the ICD-10-AM index 1 of 9 3/07/2008 11:39 AM HIMJ: Reviewed articles HIMJ HOME Matching GP terms to the ICD-10-AM index Peter R Scott CONTENTS GUIDELINES MISSION CONTACT US HIMAA Locked Bag 2045 North Ryde, NSW Australia

More information

Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials

Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials Riccardo Miotto and Chunhua Weng Department of Biomedical Informatics Columbia University,

More information

Methods for Scaling Medical Device Analyses to Large Observational Data. Michael E. Matheny, MD, MS, MPH

Methods for Scaling Medical Device Analyses to Large Observational Data. Michael E. Matheny, MD, MS, MPH Methods for Scaling Medical Device Analyses to Large Observational Data Michael E. Matheny, MD, MS, MPH Outline Introduction to Clinical Data Research Networks Capacity to conduct comparative effectiveness

More information

Geriatric Certification. Curriculum

Geriatric Certification. Curriculum Geriatric Certification Curriculum EIM Certification in Geriatrics - 16 credits EBP 6100 - Evidence-based Practice I (15 hours/1 credit) ONLINE SELF-PACED, SELF-STUDY This course is designed to improve

More information

Building a Diseases Symptoms Ontology for Medical Diagnosis: An Integrative Approach

Building a Diseases Symptoms Ontology for Medical Diagnosis: An Integrative Approach Building a Diseases Symptoms Ontology for Medical Diagnosis: An Integrative Approach Osama Mohammed, Rachid Benlamri and Simon Fong* Department of Software Engineering, Lakehead University, Ontario, Canada

More information

How to Advance Beyond Regular Data with Text Analytics

How to Advance Beyond Regular Data with Text Analytics Session #34 How to Advance Beyond Regular Data with Text Analytics Mike Dow Director, Product Development, Health Catalyst Carolyn Wong Simpkins, MD, PhD Chief Medical Informatics Officer, Health Catalyst

More information

BMC Medical Informatics and Decision Making 2006, 6:30

BMC Medical Informatics and Decision Making 2006, 6:30 BMC Medical Informatics and Decision Making This Provisional PDF corresponds to the article as it appeared upon acceptance. Copyedited and fully formatted PDF and full text (HTML) versions will be made

More information

The UMLS-CORE project: a study of the problem list terminologies used in large healthcare institutions

The UMLS-CORE project: a study of the problem list terminologies used in large healthcare institutions The UMLS-CORE project: a study of the problem list terminologies used in large healthcare institutions Kin Wah Fung, Clement McDonald, Suresh Srinivasan Research paper National Library of Medicine, Bethesda,

More information

Evaluation of Clinical Text Segmentation to Facilitate Cohort Retrieval

Evaluation of Clinical Text Segmentation to Facilitate Cohort Retrieval Evaluation of Clinical Text Segmentation to Facilitate Cohort Retrieval Enhanced Cohort Identification and Retrieval S105 Tracy Edinger, ND, MS Oregon Health & Science University Twitter: #AMIA2017 Co-Authors

More information

SAGE. Nick Beard Vice President, IDX Systems Corp.

SAGE. Nick Beard Vice President, IDX Systems Corp. SAGE Nick Beard Vice President, IDX Systems Corp. Sharable Active Guideline Environment An R&D consortium to develop the technology infrastructure to enable computable clinical guidelines, that will be

More information

Detecting Patient Complexity from Free Text Notes Using a Hybrid AI Approach

Detecting Patient Complexity from Free Text Notes Using a Hybrid AI Approach Detecting Patient Complexity from Free Text Notes Using a Hybrid AI Approach Malcolm Pradhan, CMO MBBS, PhD, FACHI Daniel Padilla, ML Engineer BEng,, PhD Alcidion Corporation Overview Alcidion s Natural

More information

How preferred are preferred terms?

How preferred are preferred terms? How preferred are preferred terms? Gintare Grigonyte 1, Simon Clematide 2, Fabio Rinaldi 2 1 Computational Linguistics Group, Department of Linguistics, Stockholm University Universitetsvagen 10 C SE-106

More information

Chapter 12 Conclusions and Outlook

Chapter 12 Conclusions and Outlook Chapter 12 Conclusions and Outlook In this book research in clinical text mining from the early days in 1970 up to now (2017) has been compiled. This book provided information on paper based patient record

More information

Interface Terminologies: Facilitating Direct Entry of Clinical Data into Electronic Health Record Systems

Interface Terminologies: Facilitating Direct Entry of Clinical Data into Electronic Health Record Systems Journal of the American Medical Informatics Association Volume 13 Number 3 May / Jun 2006 277 Review Paper j Interface Terminologies: Facilitating Direct Entry of Clinical Data into Electronic Health Record

More information

Dynamic Spinal Visualization and Vertebral Motion Analysis

Dynamic Spinal Visualization and Vertebral Motion Analysis Dynamic Spinal Visualization and Vertebral Motion Analysis Policy Number: 6.01.46 Last Review: 2/2019 Origination: 2/2006 Next Review: 2/2020 Policy Blue Cross and Blue Shield of Kansas City (Blue KC)

More information

The Human Behaviour-Change Project

The Human Behaviour-Change Project The Human Behaviour-Change Project Participating organisations A Collaborative Award funded by the www.humanbehaviourchange.org @HBCProject This evening Opening remarks from the chair Mary de Silva, The

More information

Documentation of Nonroutine Communications of Critical or Significant Radiology Results: A Multiyear Experience at a Tertiary Hospital

Documentation of Nonroutine Communications of Critical or Significant Radiology Results: A Multiyear Experience at a Tertiary Hospital Documentation of Nonroutine Communications of Critical or Significant Radiology Results: A Multiyear Experience at a Tertiary Hospital Paras Lakhani, MD a, Curtis P. Langlotz, MD, PhD a Purpose: The aim

More information

Visualizing Health Care for Rural Veterans with GIS

Visualizing Health Care for Rural Veterans with GIS Visualizing Health Care for Rural Veterans with GIS Justin Ahern, GIS Analyst U.S. Department of Veterans Affairs, Office of Rural Health, GeoSpatial Outcomes Division Other authors: Cowper Ripley DC,

More information

Rina Patel, Brent Greenberg, Steven Montner, Alexandra Funaki, Christopher Straus, Steven Zangan, and Heber MacMahon

Rina Patel, Brent Greenberg, Steven Montner, Alexandra Funaki, Christopher Straus, Steven Zangan, and Heber MacMahon Rina Patel, Brent Greenberg, Steven Montner, Alexandra Funaki, Christopher Straus, Steven Zangan, and Heber MacMahon Versions of voice recognition software have been used to generate radiology reports

More information

Enhancing Retrieval of Best Evidence for Health Care from Bibliographic Databases: Calibration of the Hand Search of the Literature

Enhancing Retrieval of Best Evidence for Health Care from Bibliographic Databases: Calibration of the Hand Search of the Literature Enhancing Retrieval of Best Evidence for Health Care from Bibliographic Databases: Calibration of the Hand Search of the Literature Nancy L. Wilczynski a, K. Ann McKibbon a, R. Brian Haynes a a Health

More information

Automatically extracting, ranking and visually summarizing the treatments for a disease

Automatically extracting, ranking and visually summarizing the treatments for a disease Automatically extracting, ranking and visually summarizing the treatments for a disease Prakash Reddy Putta, B.Tech 1,2, John J. Dzak III, BS 1, Siddhartha R. Jonnalagadda, PhD 1 1 Division of Health and

More information

Medical Policy. MP Dynamic Spinal Visualization and Vertebral Motion Analysis

Medical Policy. MP Dynamic Spinal Visualization and Vertebral Motion Analysis Medical Policy BCBSA Ref. Policy: 6.01.46 Last Review: 09/19/2018 Effective Date: 12/15/2018 Section: Radiology Related Policies 6.01.48 Positional Magnetic Resonance Imaging 9.01.502 Experimental / Investigational

More information

Kaiser Permanente Convergent Medical Terminology (CMT)

Kaiser Permanente Convergent Medical Terminology (CMT) Kaiser Permanente Convergent Medical Terminology (CMT) Using Oxford RDFox and SNOMED for Quality Measures Peter Hendler, MD Alan Abilla, RN, MS About Kaiser Permanente Largest health maintenance organization

More information

General Symptom Extraction from VA Electronic Medical Notes

General Symptom Extraction from VA Electronic Medical Notes General Symptom Extraction from VA Electronic Medical Notes Guy Divita a,b, Gang Luo, PhD c, Le-Thuy T. Tran, PhD a,b, T. Elizabeth Workman, PhD a,b, Adi V. Gundlapalli, MD, PhD a,b, Matthew H. Samore,

More information

Innovative Risk and Quality Solutions for Value-Based Care. Company Overview

Innovative Risk and Quality Solutions for Value-Based Care. Company Overview Innovative Risk and Quality Solutions for Value-Based Care Company Overview Meet Talix Talix provides risk and quality solutions to help providers, payers and accountable care organizations address the

More information

Progress Report. Date: 12/18/ :15 PM Medical Record #: DOB: 10/17/1940 Account #: Patient Information

Progress Report. Date: 12/18/ :15 PM Medical Record #: DOB: 10/17/1940 Account #: Patient Information Visits From SOC: Address: City, State, Zip: Occupation: Gender: Contact Person: 2 Primary Diagnosis: Other Diagnosis: 4614 Winstead Way Franklin, Tennessee 37065 Patient Information Healthcare - Medical

More information

Orthopaedic Physical Therapy Residency Program. Curriculum

Orthopaedic Physical Therapy Residency Program. Curriculum Orthopaedic Physical Therapy Residency Program Curriculum Effective: January 2017 ORTHOPAEDIC PHYSICAL THERAPY RESIDENCY PROGRAM Program Director: Dr. Brett Beuning The EIM Orthopaedic Residency is committed

More information

Validation of Clinical Outcomes in Electronic Data Sources

Validation of Clinical Outcomes in Electronic Data Sources Validation of Clinical Outcomes in Electronic Data Sources Vincent Lo Re, MD, MSCE Assistant Professor of Medicine and Epidemiology Center for Clinical Epidemiology and Biostatistics Center for Pharmacoepidemiology

More information

SNOMED CT and Orphanet working together

SNOMED CT and Orphanet working together SNOMED CT and Orphanet working together Ian Green Business Services Executive, IHTSDO Dr. Romina Armando INSERM Session outline What is Orphanet? Rare disorders Orphanet nomenclature Mappings to other

More information

Automatic generation of MedDRA terms groupings using an ontology

Automatic generation of MedDRA terms groupings using an ontology Automatic generation of MedDRA terms groupings using an ontology Gunnar DECLERCK a,1, Cédric BOUSQUET a,b and Marie-Christine JAULENT a a INSERM, UMRS 872 EQ20, Université Paris Descartes, France. b Department

More information

Postprofessional Occupational Therapy Doctorate. Core Curriculum. EFFECTIVE: July Revised Jan 2018

Postprofessional Occupational Therapy Doctorate. Core Curriculum. EFFECTIVE: July Revised Jan 2018 Postprofessional Occupational Therapy Doctorate Core Curriculum EFFECTIVE: July 2016 Revised Jan 2018 Postprofessional Occupational Therapy Doctorate Program Program Director: Dr. Marian Gillard, PhD,

More information

Integrating Personalized Health Information from MedlinePlus in a Patient Portal

Integrating Personalized Health Information from MedlinePlus in a Patient Portal Integrating Personalized Health Information from MedlinePlus in a Patient Portal Damian BORBOLLA a,1, Guilherme DEL FIOL b, Vanina TALIERCIO a, Carlos OTERO a, Fernando CAMPOS a,c, Marcela MARTINEZ a,

More information

Scope of Practice for the Diagnostic Ultrasound Professional

Scope of Practice for the Diagnostic Ultrasound Professional Scope of Practice for the Diagnostic Ultrasound Professional Copyright 1993-2000 Society of Diagnostic Medical Sonographers, Dallas, Texas USA: All Rights Reserved Worldwide. Organizations which endorse

More information

PROPOSED WORK PROGRAMME FOR THE CLEARING-HOUSE MECHANISM IN SUPPORT OF THE STRATEGIC PLAN FOR BIODIVERSITY Note by the Executive Secretary

PROPOSED WORK PROGRAMME FOR THE CLEARING-HOUSE MECHANISM IN SUPPORT OF THE STRATEGIC PLAN FOR BIODIVERSITY Note by the Executive Secretary CBD Distr. GENERAL UNEP/CBD/COP/11/31 30 July 2012 ORIGINAL: ENGLISH CONFERENCE OF THE PARTIES TO THE CONVENTION ON BIOLOGICAL DIVERSITY Eleventh meeting Hyderabad, India, 8 19 October 2012 Item 3.2 of

More information

Atigeo at TREC 2012 Medical Records Track: ICD-9 Code Description Injection to Enhance Electronic Medical Record Search Accuracy

Atigeo at TREC 2012 Medical Records Track: ICD-9 Code Description Injection to Enhance Electronic Medical Record Search Accuracy Atigeo at TREC 2012 Medical Records Track: ICD-9 Code Description Injection to Enhance Electronic Medical Record Search Accuracy Bryan Tinsley, Alex Thomas, Joseph F. McCarthy, Mike Lazarus Atigeo, LLC

More information

Big Data Phenomics in the VA. Outline

Big Data Phenomics in the VA. Outline Big Phenomics in the VA Mary Whooley MD Director, VA Measurement Science QUERI San Francisco VA Health Care System University of California, San Francisco Kelly Cho PhD MPH Phenomics Lead, Million Veteran

More information

Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework

Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework Stepwise Knowledge Acquisition in a Fuzzy Knowledge Representation Framework Thomas E. Rothenfluh 1, Karl Bögl 2, and Klaus-Peter Adlassnig 2 1 Department of Psychology University of Zurich, Zürichbergstraße

More information

Christina Martin Kazi Russell MED INF 406 INFERENCING Session 8 Group Project November 15, 2014

Christina Martin Kazi Russell MED INF 406 INFERENCING Session 8 Group Project November 15, 2014 INFERENCING (HW 8) 1 Christina Martin Kazi Russell MED INF 406 INFERENCING Session 8 Group Project November 15, 2014 Page 2 The Clinical Decision Support System designed to utilize the Training Set data

More information

A Method for Analyzing Commonalities in Clinical Trial Target Populations

A Method for Analyzing Commonalities in Clinical Trial Target Populations A Method for Analyzing Commonalities in Clinical Trial Target Populations Zhe (Henry) He 1, Simona Carini 2, Tianyong Hao 1, Ida Sim 2, and Chunhua Weng 1 1 Department of Biomedical Informatics, Columbia

More information

Product Brochure (734)

Product Brochure  (734) Product Brochure www.fcesoftware.com (734) 904-1895 Our primary focus is to assist physicians and therapists in the objective evaluation of functional abilities by developing, providing and supporting

More information

Use of Online Resources While Using a Clinical Information System

Use of Online Resources While Using a Clinical Information System Use of Online Resources While Using a Clinical Information System James J. Cimino, MD; Jianhua Li, MD; Mark Graham, PhD, Leanne M. Currie, RN, MS; Mureen Allen, MB BS, Suzanne Bakken, RN, DNSc, Vimla L.

More information

HHS Public Access Author manuscript Stud Health Technol Inform. Author manuscript; available in PMC 2015 July 08.

HHS Public Access Author manuscript Stud Health Technol Inform. Author manuscript; available in PMC 2015 July 08. Navigating Longitudinal Clinical Notes with an Automated Method for Detecting New Information Rui Zhang a, Serguei Pakhomov a,b, Janet T. Lee c, and Genevieve B. Melton a,c a Institute for Health Informatics,

More information

Auditing SNOMED Relationships Using a Converse Abstraction Network

Auditing SNOMED Relationships Using a Converse Abstraction Network Auditing SNOMED Relationships Using a Converse Abstraction Network Duo Wei, MS 1, Michael Halper, PhD 2, Gai Elhanan, MD 1, Yan Chen, PhD 3, Yehoshua Perl, PhD 1, James Geller, PhD 1, Kent A. Spackman,

More information

Identifying anatomical concepts associated with ICD10 diseases

Identifying anatomical concepts associated with ICD10 diseases Proceedings of the 8th Conference on Terminology and Artificial Intelligence (TIA 2009). (electronic proceedings: http://www.irit.fr/tia09/start_here.htm) Identifying anatomical concepts associated with

More information

vertaplan the spine surgeon s software vertaplan System for successful reconstruction of the individual sagittal balance

vertaplan the spine surgeon s software vertaplan System for successful reconstruction of the individual sagittal balance the spine surgeon s software System for successful reconstruction of the individual sagittal balance What do you think of patient-specific reconstruction of the spine geometry? Optimum surgical outcome

More information

Text mining for lung cancer cases over large patient admission data. David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor

Text mining for lung cancer cases over large patient admission data. David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor Text mining for lung cancer cases over large patient admission data David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor Opportunities for Biomedical Informatics Increasing roll-out

More information

INSIGHTS AND BEST PRACTICES FOR EMS AGENCIES

INSIGHTS AND BEST PRACTICES FOR EMS AGENCIES 2018 ESO EMS INDEX: INSIGHTS AND BEST PRACTICES FOR EMS AGENCIES AUTHORS DR. BRENT MYERS, CHIEF MEDICAL OFFICER, ESO ALLEN JOHNSON, VICE PRESIDENT FOR HEALTH DATA EXCHANGE, ESO CONTEXT AND OVERVIEW FOR

More information

Geriatric Certification

Geriatric Certification Geriatric Certification Curriculum 2017 Geriatric Certification Program Program Director: Cody Thompson, PT, DPT, GCS, CSCS Program Description This program offers PTs and OTs the opportunity to develop

More information

Standards for reporting Plain Language Summaries (PLS) for Cochrane Diagnostic Test Accuracy Reviews (interim guidance adapted from Methodological

Standards for reporting Plain Language Summaries (PLS) for Cochrane Diagnostic Test Accuracy Reviews (interim guidance adapted from Methodological s for reporting Plain Language Summaries (PLS) for Cochrane Diagnostic Test Accuracy Reviews (interim guidance adapted from Methodological Expectations of Cochrane Intervention Reviews (MECIR) guidance

More information

Running Head: AUTOMATED SCORING OF CONSTRUCTED RESPONSE ITEMS. Contract grant sponsor: National Science Foundation; Contract grant number:

Running Head: AUTOMATED SCORING OF CONSTRUCTED RESPONSE ITEMS. Contract grant sponsor: National Science Foundation; Contract grant number: Running Head: AUTOMATED SCORING OF CONSTRUCTED RESPONSE ITEMS Rutstein, D. W., Niekrasz, J., & Snow, E. (2016, April). Automated scoring of constructed response items measuring computational thinking.

More information

Text Mining of Patient Demographics and Diagnoses from Psychiatric Assessments

Text Mining of Patient Demographics and Diagnoses from Psychiatric Assessments University of Wisconsin Milwaukee UWM Digital Commons Theses and Dissertations December 2014 Text Mining of Patient Demographics and Diagnoses from Psychiatric Assessments Eric James Klosterman University

More information

Criteria for evaluating transferability of health interventions: a systematic review and thematic synthesis

Criteria for evaluating transferability of health interventions: a systematic review and thematic synthesis Schloemer and Schröder-Bäck Implementation Science (2018) 13:88 https://doi.org/10.1186/s13012-018-0751-8 SYSTEMATIC REVIEW Open Access Criteria for evaluating transferability of health interventions:

More information

IBM Research Report. Automated Problem List Generation from Electronic Medical Records in IBM Watson

IBM Research Report. Automated Problem List Generation from Electronic Medical Records in IBM Watson RC25496 (WAT1409-068) September 24, 2014 Computer Science IBM Research Report Automated Problem List Generation from Electronic Medical Records in IBM Watson Murthy Devarakonda, Ching-Huei Tsou IBM Research

More information

38 Int'l Conf. Bioinformatics and Computational Biology BIOCOMP'16

38 Int'l Conf. Bioinformatics and Computational Biology BIOCOMP'16 38 Int'l Conf. Bioinformatics and Computational Biology BIOCOMP'16 PGAR: ASD Candidate Gene Prioritization System Using Expression Patterns Steven Cogill and Liangjiang Wang Department of Genetics and

More information

Building a framework for handling clinical abbreviations a long journey of understanding shortened words "

Building a framework for handling clinical abbreviations a long journey of understanding shortened words Building a framework for handling clinical abbreviations a long journey of understanding shortened words " Yonghui Wu 1 PhD, Joshua C. Denny 2 MD MS, S. Trent Rosenbloom 2 MD MPH, Randolph A. Miller 2

More information

10.2 Summary of the Votes and Considerations for Policy

10.2 Summary of the Votes and Considerations for Policy CEPAC Voting and Policy Implications Summary Supplemental Screening for Women with Dense Breast Tissue December 13, 2013 The last CEPAC meeting addressed the comparative clinical effectiveness and value

More information

National Quality Forum Environmental Scan: Regionalized Emergency Medical Care Services

National Quality Forum Environmental Scan: Regionalized Emergency Medical Care Services National Quality Forum Environmental Scan: Regionalized Emergency Medical Care Services EMS Performance Improvement Center Department of Emergency Medicine University of North Carolina at Chapel Hill Jefferson

More information

Innovator Case Studies: Oncology Networks

Innovator Case Studies: Oncology Networks Innovator Case Studies: Oncology Networks J. Ike Nicoll Chief Executive Officer Cancer Clinics of Excellence Alan Armer, Ph.D. Vice President, Research & Development Catholic Health Initiatives Cancer

More information

What Computer Tools to Use for Your Quality and Safety Program

What Computer Tools to Use for Your Quality and Safety Program What Computer Tools to Use for Your Quality and Safety Program Lincoln L. Berland, M.D., F.A.C.R. University of Alabama at Birmingham Disclosure Consultant to Nuance, Inc. Learning Objectives Understand

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Friedberg MW, Rosenthal MB, Werner RM, Volpp KG, Schneider EC. Effects of a medical home and shared savings intervention on quality and utilization of care. Published online

More information

Mayo Clinic Gynecologic Oncology Fellowship (Minnesota) Competency-based goals

Mayo Clinic Gynecologic Oncology Fellowship (Minnesota) Competency-based goals Mayo Clinic Gynecologic Oncology Fellowship (Minnesota) Competency-based goals 1. PATIENT CARE (includes surgical skills) To train gynecologic oncology fellows to competency in evaluation, treatment and

More information

Task Force Background Donald Patrick. Appreciation to Reviewers. ISPOR PRO GRP Task Force Reports

Task Force Background Donald Patrick. Appreciation to Reviewers. ISPOR PRO GRP Task Force Reports Content Validity: Establishing and Reporting the Evidence in Newly-Developed Patient-Reported Outcome (PRO) Instruments for Medical Product Evaluation - Good Research Practices Donald L. Patrick PhD, MSPH,

More information

Evaluating Measures of Redundancy in Clinical Texts

Evaluating Measures of Redundancy in Clinical Texts Evaluating Measures of Redundancy in Clinical Texts Rui Zhang, MS 1, Serguei Pakhomov, PhD 1, 2, Bridget T. McInnes, PhD 2, Genevieve B. Melton, MD, MA 1,3 1 Institute for Health Informatics; 2 College

More information

ELECTRONIC HEALTH RECORDS AND DIAGNOSTIC ERRORS: FROM CHALLENGES TO OPPORTUNITIES

ELECTRONIC HEALTH RECORDS AND DIAGNOSTIC ERRORS: FROM CHALLENGES TO OPPORTUNITIES ELECTRONIC HEALTH RECORDS AND DIAGNOSTIC ERRORS: FROM CHALLENGES TO OPPORTUNITIES HARDEEP SINGH, MD, MPH HOUSTON VA CENTER FOR INNOVATIONS IN QUALITY, EFFECTIVENESS & SAFETY MICHAEL E. DEBAKEY VA MEDICAL

More information

Nature and significance of the local problem

Nature and significance of the local problem Revised Standards for Quality Improvement Reporting Excellence (SQUIRE 2.0) September 15, 2015 Text Section and Item Section or Item Description Name The SQUIRE guidelines provide a framework for reporting

More information

WELSH INFORMATION STANDARDS BOARD

WELSH INFORMATION STANDARDS BOARD WELSH INFORMATION STANDARDS BOARD DSC Notice: DSCN 2018 / 06 Date of Issue: 8 th August 2018 Welsh Health Circular / Official Letter: (2015) 053 Subject: CT Maturity Matrix Sponsor: Chris Newbrook, Head

More information

The Potential of SNOMED CT to Improve Patient Care. Dec 2015

The Potential of SNOMED CT to Improve Patient Care. Dec 2015 The Potential of SNOMED CT to Improve Patient Care stephen.spencer@nhs.net stephen.spencer@nhs.net Dec 2015 What is SNOMED CT SNOMED CT: Is the most comprehensive, multilingual clinical healthcare terminology

More information

2019 COLLECTION TYPE: MIPS CLINICAL QUALITY MEASURES (CQMS) MEASURE TYPE: Patient Reported Outcome High Priority

2019 COLLECTION TYPE: MIPS CLINICAL QUALITY MEASURES (CQMS) MEASURE TYPE: Patient Reported Outcome High Priority Quality ID #223 (NQF 0428): Functional Status Change for Patients with General Orthopedic Impairments National Quality Strategy Domain: Communication and Care Coordination Meaningful Measure Area: Patient

More information

A Lexical-Ontological Resource forconsumerheathcare

A Lexical-Ontological Resource forconsumerheathcare A Lexical-Ontological Resource forconsumerheathcare Elena Cardillo FBK-IRST, Via Sommarive 18, 38123 Trento, Italy cardillo@fbk.eu Abstract. In Consumer Healthcare Informatics it is still difficult for

More information

A Comparison of Collaborative Filtering Methods for Medication Reconciliation

A Comparison of Collaborative Filtering Methods for Medication Reconciliation A Comparison of Collaborative Filtering Methods for Medication Reconciliation Huanian Zheng, Rema Padman, Daniel B. Neill The H. John Heinz III College, Carnegie Mellon University, Pittsburgh, PA, 15213,

More information

Shades of Certainty Working with Swedish Medical Records and the Stockholm EPR Corpus

Shades of Certainty Working with Swedish Medical Records and the Stockholm EPR Corpus Shades of Certainty Working with Swedish Medical Records and the Stockholm EPR Corpus Sumithra VELUPILLAI, Ph.D. Oslo, May 30 th 2012 Health Care Analytics and Modeling, Dept. of Computer and Systems Sciences

More information

Pulmonary nodules are commonly encountered in clinical

Pulmonary nodules are commonly encountered in clinical ORIGINAL ARTICLE Automated Identification of Patients With Pulmonary Nodules in an Integrated Health System Using Administrative Health Plan Data, Radiology Reports, and Natural Language Processing Kim

More information

Running head: CPPS REVIEW 1

Running head: CPPS REVIEW 1 Running head: CPPS REVIEW 1 Please use the following citation when referencing this work: McGill, R. J. (2013). Test review: Children s Psychological Processing Scale (CPPS). Journal of Psychoeducational

More information