Information is Different Now That You re a Doctor

Transcription

1 References Information is Different Now That You re a Doctor William Hersh, MD Professor and Chair Department of Medical Informatics & Clinical Epidemiology School of Medicine Oregon Health & Science University hersh@ohsu.edu Web: Blog: September 1, 2017 Ammenwerth, E and Spötl, HP (2009). The time needed for clinical documentation versus direct patient care. A work-sampling analysis of physicians' activities. Methods of Information in Medicine. 48: Anderson, C (2007). The End of Theory: The Data Deluge Makes the Scientific Method Obsolete. Wired, June 23, Angrisano, C, Farrell, D, et al. (2007). Accounting for the Cost of Health Care in the United States. Washington, DC, McKinsey & Company. Anonymous (2010). The State of Health Care Quality: Washington, DC, National Committee for Quality Assurance. Bastian, H, Glasziou, P, et al. (2010). Seventy-five trials and eleven systematic reviews a day: how will we ever keep up? PLoS Medicine. 7(9): e Brill, S (2013). Bitter Pill: Why Medical Bills Are Killing Us. Time, April 4, Classen, DC, Resar, R, et al. (2011). 'Global trigger tool' shows that adverse events in hospitals may be ten times greater than previously measured. Health Affairs. 30: Crown, WH (2015). Potential application of machine learning in health outcomes research and some statistical cautions. Value Health. 18: Davenport, TH (2006). Competing on Analytics. Harvard Business Review, Delbanco, T, Walker, J, et al. (2010). Open Notes: doctors and patients signing on. Annals of Internal Medicine. 153: DesRoches, CM, Painter, MW, et al. (2015). Health Information Technology in the United States Transition to a Post-HITECH World. Princeton, NJ, Robert Wood Johnson Foundation. Detmer, DE and Shortliffe, EH (2014). Clinical informatics: prospects for a new medical subspecialty. Journal of the American Medical Association. 311: Donoho, D (2015). 50 years of Data Science. Princeton NJ, Tukey Centennial Workshop. Esteva, A, Kuprel, B, et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature. 542:

2 Fox, S and Duggan, M (2013). Health Online Washington, DC, Pew Internet & American Life Project. Friedman, CP (2009). A 'fundamental theorem' of biomedical informatics. Journal of the American Medical Informatics Association. 16: Gulshan, V, Peng, L, et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Journal of the American Medical Association. 316: Hartman, M, Martin, AB, et al. (2015). National health spending in 2013: growth slows, remains in step with the overall economy. Health Affairs. 34: Henry, J, Pylypchuk, Y, et al. (2016). Adoption of Electronic Health Record Systems among U.S. Non- Federal Acute Care Hospitals: Washington, DC, Department of Health and Human Services. Hersh, W (2009). A stimulus to define informatics and health information technology. BMC Medical Informatics & Decision Making. 9: Hersh, W and Ehrenfeld, J (2017). Clinical Informatics. Health Systems Science. S. Skochelak, R. Hawkins, L. Lawson et al. New York, NY, Elsevier: Hersh, WR (2014). Healthcare Data Analytics. Health Informatics: Practical Guide for Healthcare and Information Technology Professionals, Sixth Edition. R. Hoyt and A. Yoshihashi. Pensacola, FL, Lulu.com: Hersh, WR, Gorman, PN, et al. (2014). Beyond information retrieval and EHR use: competencies in clinical informatics for medical education. Advances in Medical Education and Practice. 5: Hersh, WR, Weiner, MG, et al. (2013). Caveats for the use of operational electronic health record data in comparative effectiveness research. Medical Care. 51(Suppl 3): S30-S37. Hey, T, Tansley, S, et al., Eds. (2009). The Fourth Paradigm: Data-Intensive Scientific Discovery. Redmond, WA, Microsoft Research. Kim, CS, Lovejoy, W, et al. (2010). Hospitalist time usage and cyclicality: opportunities to improve efficiency. Journal of Hospital Medicine. 5: Kohn, LT, Corrigan, JM, et al., Eds. (2000). To Err Is Human: Building a Safer Health System. Washington, DC, National Academies Press. Kulikowski, CA, Shortliffe, EH, et al. (2012). AMIA Board white paper: definition of biomedical informatics and specification of core competencies for graduate education in the discipline. Journal of the American Medical Informatics Association. 19: Kuperman, GJ (2011). Health-information exchange: why are we doing it, and what are we doing? Journal of the American Medical Informatics Association. 18: Liu, Y, Gadepalli, K, et al. (2017). Detecting cancer metastases on gigapixel pathology images. arxiv.org: arxiv: McGlynn, EA, Asch, SM, et al. (2003). The quality of health care delivered to adults in the United States. New England Journal of Medicine. 348: Miller, HD, Yasnoff, WA, et al. (2009). Personal Health Records: The Essential Missing Element in 21st Century Healthcare. Chicago, IL, Healthcare Information and Management Systems Society. Safran, C, Bloomrosen, M, et al. (2007). Toward a national framework for the secondary use of health data: an American Medical Informatics Association white paper. Journal of the American Medical Informatics Association. 14: 1-9. Schoen, C, Osborn, R, et al. (2009). A survey of primary care physicians in eleven countries, 2009: perspectives on care, costs, and experiences. Health Affairs. 28: w Shortliffe, EH (2010). Biomedical informatics in the education of physicians. Journal of the American Medical Association. 304:

3 Sinsky, C, Colligan, L, et al. (2016). Allocation of physician time in ambulatory practice: a time and motion study in 4 specialties. Annals of Internal Medicine. 165: Sittig, DF, Wright, A, et al. (2008). Grand challenges in clinical decision support. Journal of Biomedical Informatics. 41: Skochelak, SE, Hawkins, RE, et al., Eds. (2017). Health Systems Science. New York, NY, Elsevier. Smith, M, Saunders, R, et al. (2012). Best Care at Lower Cost: The Path to Continuously Learning Health Care in America. Washington, DC, National Academies Press. Smith, PC, Araya-Guerra, R, et al. (2005). Missing clinical information during primary care visits. Journal of the American Medical Association. 293: Tai-Seale, M, Olson, CW, et al. (2017). Electronic health record logs indicate that physicians split time evenly between seeing patients and desktop medicine. Health Affairs. 36: Tipping, MD, Forth, VE, et al. (2010). Systematic review of time studies evaluating physicians in the hospital setting. Journal of Hospital Medicine. 5: Tipping, MD, Forth, VE, et al. (2010). Where did the day go?--a time-motion study of hospitalists. Journal of Hospital Medicine. 5: VanDenBos, J, Rustagi, K, et al. (2011). The $17.1 billion problem: the annual cost of measurable medical errors. Health Affairs. 30: Victores, AJ, Coggins, K, et al. (2015). Electronic health records and resident workflow: A timemotion study of otolaryngology residents. Laryngoscope. 125: Woods, SS, Schwartz, E, et al. (2013). Patient experiences with full electronic access to health records and clinical notes through the My HealtheVet Personal Health Record Pilot: qualitative study. Journal of Medical Internet Research. 15(3): e65. Yousefi, V (2011). How Canadian hospitalists spend their time - a work-sampling study within a hospital medicine program in Ontario. Journal of Clinical Outcomes Management. 18: Zikopoulos, P, Eaton, C, et al. (2011). Understanding Big Data: Analytics for Enterprise Class Hadoop and Streaming Data. New York, NY, McGraw-Hill.

4 Information is Different Now That You re a Doctor William Hersh, MD Professor and Chair Department of Medical Informatics & Clinical Epidemiology School of Medicine hersh@ohsu.edu Web: Blog: September 1, 2017 Disclosures/Conflict of Interest None William Hersh, MD Information is Different - 9/1/17 2 1

5 Session Objectives Describe the central role that data and information play in the practice of medicine Discuss how information becomes different when you are a medical professional, from the need to ascertain its quality to how it is accessed and disseminated by patients Explain the key issues for data science and data analytics in medicine Describe the discipline of clinical informatics and its role in medicine William Hersh, MD Information is Different - 9/1/17 3 From today s optional reading Shortliffe, 2010 William Hersh, MD Information is Different - 9/1/17 4 2

6 Most of you are digital natives but Your relationship with information changes as you become a healthcare professional You become responsible not only for knowing information, but also Using it to provide better care of patients Leveraging it to improve the healthcare system Protecting privacy and confidentiality of patients Acting professionally with information Computer literacy is a prerequisite, not an end William Hersh, MD Information is Different - 9/1/17 5 Question What percentage of time does the average physician spend directly interacting with patients? 1. Occasionally 2. Less than half 3. More than half 4. Doctors never do anything but take care of patients William Hersh, MD Information is Different - 9/1/17 6 3

7 Even before computers, more time spent with information than patients Time studies of physicians show physicians historically spend about 15-38% of their time in direct patient care 50-67% of their time in indirect patient care, divided between reviewing results, performing documentation, and engaging in communication More recent studies show 40-50% of time spent interacting with computers probably too much, how much is the right amount? Ammenwerth, 2009; Tipping, 2010; Kim, 2010; Tipping, 2010; Yousefi, 2011; Victores, 2014; Sinsky, 2016; Tai-Seale, 2017 William Hersh, MD Information is Different - 9/1/17 7 Why do physicians spend so much time with information? Growth of medical knowledge 75 new clinical trials and 11 systematic reviews published each day To say nothing of the basic science, especially genomics Medical knowledge no longer the exclusive purview of physicians; 80% of all Internet users have searched for personal health information Bastian, 2010; Fox, 2013 William Hersh, MD Information is Different - 9/1/17 8 4

8 Why so much time (cont.)? Rapid growth of electronic health record (EHR) adoption As result of meaningful use financial incentives of the Health Information for Technology and Clinical Health (HITECH) Act, there has been widespread adoption and use of the EHR, growing to 96% of hospitals 82% of physician offices Henry, 2016; DesRoches, 2015 Non-federal hospitals Office-based physicians William Hersh, MD Information is Different - 9/1/17 9 Many problems in healthcare have information-related solutions Quality not as good as it could be; slightly more than half of patients get care they should get Safety errors cause morbidity and mortality; many preventable Cost rising costs slowing, but US still spends more and gets less Inaccessible information missing information frequent in primary care McGlynn, 2003; Schoen, 2009; NCQA, 2010; Kohn, 2000; Classen, 2011; van den Bos, 2011; Smith 2012; Angrisano, 2007; Brill, 2013; Hartman, 2015; Smith, 2005 William Hersh, MD Information is Different - 9/1/

9 Question How many patients die each error due to medical errors? 1. None; doctors and the healthcare system are so well-trained that they never make errors 2. A small amount from mostly a few incompetent physicians 3. 48,000-96, Millions William Hersh, MD Information is Different - 9/1/17 11 EHR is more than charting Physicians must be able to Move from one vendor system to another Effectively use clinical decision support to remind us to things to do and warn us about things not to do Access information from other settings where patient received care through health information exchange Apply data analytics, especially in setting of population health management, to achieve quality, safety, and costeffectiveness Siittig, 2008; Kuperman, 2011; Hersh, 2014 William Hersh, MD Information is Different - 9/1/

10 Patients want more from us too Growing numbers of patients want to interact with healthcare the way they interact with airlines, retailers, banks, etc. Test results, prescription refills, scheduling, etc. Many healthcare systems offer access to personal health record (PHR) Growing number of systems offer access to notes and more (OpenNotes Project) Miller, 2009; Delbanco, 2010; Woods, 2013 William Hersh, MD Information is Different - 9/1/17 13 Those who pay for care want more accountability from us Purchasers (employers, government) and payors (insurers) want assurance that care provided is proper and cost-effective Clinical decision support aims to help physicians make best choices and avoid errors Growing use of quality measurement and improvement William Hersh, MD Information is Different - 9/1/

11 9/1/17 We also have responsibilities around information Patients expect us to keep their information private and secure Health Insurance Portability and Accountability Act (HIPAA) regulations guide our actions Treatment, payment, and operations (TPO) allowed Other uses require patient to consent Our public-facing persona must be professional, especially on social media William Hersh, MD Information is Different - 9/1/17 15 William Hersh, MD Information is Different - 9/1/17 16 Hersh, 2014; Skochelak, 2017; Hersh,

12 Question In 2015, how many Americans have suffered a breach of their clinical information? 1. None, clinical information is always highly secure 2. Just a few hundred, due to a few careless individuals million 4. The entire US population William Hersh, MD Information is Different - 9/1/17 17 Pause The OpenNotes Project allows patient access to their complete electronic record; should OHSU participate? 9

13 EHR also allows many re-uses of patient data Use data to improve care delivery Healthcare quality measurement and improvement Clinical and translational research Precision medicine Public health surveillance Safran, 2007 William Hersh, MD Information is Different - 9/1/17 19 Implementing the learning health system Unlike other industries (e.g., aviation), medicine does not learn as well from its mistakes Need to move away from culture of blame Many problems based on systems, not individuals Growing amount of clinical data in EHR and other systems allow us to learn and improve Can only be done with high-quality and usable information Smith, 2012 William Hersh, MD Information is Different - 9/1/

14 Importance of information goes beyond the EHR Professionalism proper use of social media and other public sources of information Telemedicine/telehealth providing care when separated by time and/or distance from patients Clinical and translational research advancing the knowledge base of medicine Precision medicine tailoring diagnosis and treatment more precisely, especially around the patient s genome William Hersh, MD Information is Different - 9/1/17 21 Built on a foundation of data Data analytics extensive use of data, statistical and quantitative analysis to drive decisions and actions Big Data the four Vs: volume, velocity, variety, and veracity Data science science of learning from data Leading to a new paradigm of science? Making the scientific method obsolete, i.e., no need for experimentation any more? Not really; many caveats for research use of clinical data Growing use of machine learning application of computer systems and algorithms that learn from data Ophthalmology retinal images Dermatology skin lesions Pathology breast cancer slides Davenport, 2007; Hersh, 2014; Zikopoulos, 2011; Donoho, 2015; Hey, 2009; Anderson, 2007; Hersh, 2013; Crown, 2015; Gulshan, 2016; Esteva, 2017; Liu, 2017 William Hersh, MD Information is Different - 9/1/

15 Clinical informatics Part of larger biomedical and health informatics, the field concerned with the optimal use of information, often aided by technology, to improve Individual health Healthcare Public health Biomedical research Hersh, 2009; Kulikowski, 2012 William Hersh, MD Information is Different - 9/1/17 23 Fundamental theorem of informatics Goal of informatics is Goal is not Friedman, 2009 William Hersh, MD Information is Different - 9/1/

16 Clinical informatics Competence required of all; career opportunities available for some Growing number of physicians work in roles such as Chief Medical Informatics Officer (CMIO) or others in academia or industry Clinical informatics is now a subspecialty of all medical specialties OHSU is a national leader in research and education Hersh, 2010; Detmer, 2014; Hersh, 2017 William Hersh, MD Information is Different - 9/1/17 25 What can you do? Informatics skills are essential to the practice of the 21 st century physician You should master informatics just as you master any other clinical skill For those interested as a career, plenty of opportunities in medical school and beyond Scholarly projects, electives, and more Physician-scientist track master s degree in informatics Clinical informatics subspecialty William Hersh, MD Information is Different - 9/1/

17 Questions? 14