T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka and Tamil Nadu

Size: px

Start display at page:

Download "T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka and Tamil Nadu"

Christal Dickerson
5 years ago
Views:

2009 ISDS 8 th Annual Conference, Miami T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka and Tamil

LIRNEAsia Colombo, Sri Lanka T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka Objective: To present an

Current disease reporting system in Sri Lanka 2. Concept of the Real-Time Biosurveillance Program 3.

1 2009 ISDS 8 th Annual Conference, Miami T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka and Tamil Nadu Maheshkumar Sabhnani 1, Artur Dubrawski 1 and Nuwan Waidyanatha 2 1 The Auton Lab Carnegie Mellon University i 2 LIRNEAsia Colombo, Sri Lanka T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka Objective: To present an on-going effort to establish a system for real-time disease surveillance in a developing country Agenda: 1. Current disease reporting system in Sri Lanka 2. Concept of the Real-Time Biosurveillance Program 3. TCWI: An interactive surveillance component of RTBP a. Short demo (video) b. Examples of evaluations performed so far 4. Conclusion Slide 2 of 14

2 The Need for Real-Time Biosurveillance Slide 3 of 14 Source: DARPA Real-time Monitoring of Emergency Department Patient Data during 2002 Winter Olympics We have built an early warning system for outbreaks of diseases (with U.Pitt.)... Slide 4 of 14 February 5, 2002

Astrophysics Interactive analytics Learning Locomotion United Nations CTBTO Fleet

Safety of agriculture Sri Lanka Disease Notification: Current System Black arrows

reporting It can take up to 10 days for Epidemiology Unit to receive data It only

No direct alerting capability; alerts distributed by phone throughout organizational

3 Astrophysics Interactive analytics Learning Locomotion United Nations CTBTO Fleet prognostics Bio-surveillance Food safety Nuclear threat Slide detection 5 of 14 Safety of agriculture Sri Lanka Disease Notification: Current System Black arrows represent the current manual paper/postal system for health data collection and reporting It can take up to 10 days for Epidemiology Unit to receive data It only records cases of a few reportable diseases and no syndrome or diagnosis information No direct alerting capability; alerts distributed by phone throughout organizational hierarchy (Epi Unit Regional Epis Medical Officers of Health Hospitals, Providers, etc ) Slide 6 of 14

SL Disease Notification: Opportunity for Improvement Red lines: RTBP mobile

developing countries, including Sri Lanka, have pretty good cell phone coverage

and advanced analytic capabilities It also aims at deepening and widening the

4 SL Disease Notification: Opportunity for Improvement Red lines: RTBP mobile phone communication system for heath data collection and reporting Many developing countries, including Sri Lanka, have pretty good cell phone coverage RTPB leverages that to mitigate reporting latencies RTBP adds automated alerting and advanced analytic capabilities It also aims at deepening and widening the scope of what is being reported Slide 7 of 14 RTBP: Actors, Processes, Data Flow Slide 8 of 14

Improved Detail and Resolution of Data Cur rrent distinct value count 17 9 case date location disease Min 2009-12-16 Bihalpola Dengue_fever Max 2009-07-10 Bingiriya Dysentery Bopitiya Encephalitis

Minuwangatte Munamaldeniya Narammala Sandalankawa Wariyapola RTBP: More dimensions More values per dimension Not just reportable diseases Daily resolution and collection cycles Finer spatial

Ammanamulla Abdominal pain Female 0-1 Abdominal Pain Coated tongue Max 2009-11-30 Bogahapitiya Abscesses Male 1-5 Anal itching Crepitation Bopitiya Accident Unknown 6-14 Backache Cyanosis Deegalla

Horathapola Allergy 30-34 Cold Difficulty in breathing Horombawa Anemia 35-39 Constipation Heart murmur Kadapathwehera Angina 40-45 Cough Increase of respiratory rate Kandanegedara Anxiety Above_45

5 Improved Detail and Resolution of Data Cur rrent distinct value count 17 9 case date location disease Min Bihalpola Dengue_fever Max Bingiriya Dysentery Bopitiya Encephalitis Dambadeniya Enteric_fever Dunakadeniya Food_poisoning Hettipola Human_rabies Horathapola Leptospirosis Kandanegedara Typhus_fever Kattimahana Viral_Hepatitis Katupotha Koshena Kuliyapitiya Minuwangatte Munamaldeniya Narammala Sandalankawa Wariyapola RTBP: More dimensions More values per dimension Not just reportable diseases Daily resolution and collection cycles Finer spatial resolution New distinct value count possible choices single single single single multiple multiple case date location disease gender age group sign symptom Min Ammanamulla Abdominal pain Female 0-1 Abdominal Pain Coated tongue Max Bogahapitiya Abscesses Male 1-5 Anal itching Crepitation Bopitiya Accident Unknown 6-14 Backache Cyanosis Deegalla Acne Body ache Dehydration Dunakadeniya Acute Diarrheal Disease Burning sensation in the stomach Delirium Havenegedara Acute Gastroenteritis Chest pain Deviation of the tongue Horathapola Allergy Cold Difficulty in breathing Horombawa Anemia Constipation Heart murmur Kadapathwehera Angina Cough Increase of respiratory rate Kandanegedara Anxiety Above_45 Deviation of the tongue Low Blood pressure Slide 9 of 14 T-Cube Web Interface in RTBP Efficient representation of data substantially speeds-up analyses and user interactions Implements statistical event detection techniques Enables data visualization along temporal and spatial dimensions at interactive speeds Automates alerts Slide 10 of 14

6 Video: Demo of the RTBP T-Cube Web Interface Slide 11 of 14 RTBP: TCWI Evaluations Performed So Far 17 Hospitals/Central Dispensaries 16 Sarvodaya Suwadana Centers Kurunegala District, North Western Province, Sri Lanka 24 Health Sub Centers; 4 Public Health Centers Thirupathur block, Sivaganga District, state of Tamil Nadu, India Data is being collected under the new schema only for a few months now Its amount & consistency do not warrant objective evaluations just yet Therefore, so far, evaluations rely on semi-synthetic data: Use actual historically reported counts per region and per reportable disease Other attributes in RTBP schema are then probabilistically synthesized We test the ability to detect known events, the usability in tracking of emerging events and in revealing systematic patterns of events. Slide 12 of 14

7 Example Evaluation: Leptospirosis: Deadly Pile-up during Q4_2008--Q1_ /30 4/17 8/1 Over 360 deaths Peak in Sept/08 originally noticed much later later RTBP would have picked up leading waves much earlier than Sept/08 10/30 4/17 8/1 Slide 13 of 14 Example Evaluation: Progression of Dengue Fever Outbreak (Spring 2009) 4/14 4/15 4/24 5/28 Spatial scan global score An elevated global score noted, centered in Kandy Situation in Kandy escalates, regions to the W and SW from it follow suit South begins to see increased counts South continues to escalate, ate, while the magnitudes in other regions subside Slide 14 of 14

reported health data while significantly

8 Example Evaluation: Dengue Fever: Seasonal and Spatial Patterns Note apparent Aug 30,2007 seasonality of Dengue fever It seems to be moving South and West May 1,2007 May 21,2008 April 15,2009 May 28,2009 Slide 15 of 14 Summary and Conclusion 1. RTBP deepens and widens coverage of reported health data while significantly reducing latency of reporting 2. T-Cube Web Interface (TCWI) supports RTBP by enabling: a. Automated comprehensive searches for events of interest through large collections of data b. Interactive data navigation and visualization c. Automated explanation of detected patterns 3. A fielded RTBP-like system can qualitatively yet affordably improve ability to detect and mitigate bio-medical threats in countries with limited resources and infrastructure 4. The pilot studies are ongoing in Sri Lanka and India, but we are on the outlook for additional challenges. Slide 16 of 14

9 Acknowledgements This work has been supported in part by the International Development Research Centre of Canada (105130), and by CDC (R01-PH000028) and NSF (IIS ). We have also received support from numerous collaborators not specifically named here! Partners in RTBP: LIRNEAsia Indian Institute of Technology Madras, India National Center for Biological Sciences, India Sarvodaya Shramadana Society, Sri Lanka Respere Lanka (Private) Limited, Sri Lanka University of Alberta, Canada Carnegie Mellon University Auton Lab, USA Slide 17 of 14 Backup Slides Slide 18 of 14

10 m-healthsurvey Midlet [IITM's-RTBI] (a) Main menu (b) Profile registration (c) Retrieve locations (d) Patient record screen I (e) Patient record screen II Slide 19 of 14 Messaging/Alerting CAP/EDXL Broker [Sahana] Single input multiple output engine; Able to channel through multiple technologies Manage publisher /subscribers and SOP Adopt PHIN Communication and Alerting Guidelines for EDXL/CAP Challenge of creating the EDXL/CAP template editor Relating the template editor with the SMS/ Messaging module Understanding direct and cascading alert from a regional jurisdictional prospective Designing the short and long text messages Addressing in multiple languages Slide 20 of 14

Interactive Analysis of Multidimensional Data. for Adverse Event Detection

University of Peradeniya, Sri Lanka, December 21 st 2009 Interactive Analysis of Multidimensional Data for Adverse Event Detection Artur Dubrawski Director, The Auton Lab School of Computer Science Carnegie