T-Cube Web Interface


Fidelity of digitized data in the Real-Time Biosurveillance Program (RTBP) was not promising; especially with the personnel in Sri Lanka with no medical knowledge but technically capable were producing up to 45% noisy data (second stacked graph). On the contrary the medically trained but less fluent in mobile phone usage Indian nurses were less prone to producing noisy data. The Indian health workers had an incentive because the erroneous data would produce false alarms, and they would need to respond to these false alarms or it would portray a bad image of the health situation in their area; while the Sri Lanka data digitizing personnel had no incentive besides picking up a paycheck for the data entry work they did. The data was submitted through the mHealthSurvey mobile software that works on less expensive Java-enabled hand-helds. The RTBP envisions that hospital data is submitted each day; thus, the real-time expectations.
Findings from the Real-Time Biosurveillance Program was presented in the poster session at the mHealth Summit 2010 (Fig 1). Our partners from Auton Lab were creative in affixing an iPad to the poster to show a video of the working solution. Thanks to the marketing abilities of our friends from Auton Lab, our work caught the special attention of delegates from the Bill & Melinda Gates Foundation, Rockefeller Foundation, UN Foundation and several other global development agencies. The Gates Foundation’s video crew made an exclusive appearance to capture our poster content and interviewed Prof. Arutur Dubrawski, which made all others presenting their work a bit jealous.
The IEEE-RIVF – Research, Innovation, and Vision for the Future –  International Conference on Computing and Communication Technology took place in Hanoi, Vietnam at the Vietnam National University, Nov 02-04, 2010. The plannery sessions were on applied operations research, software engineering, human machine interface & imaging technology, computational Intelligence, information & knowledge management, communication & networking, and modeling & computer simulations. I presented out paper titled: T-Cube Web Interface as a Tool for detecting disease outbreaks in real-time: a pilot in India and Sri Lanka. This paper discusses the results from the pilot in India and Sri Lanka, namely the Real-Time Biosurveillance Program (RTBP). While may discussed the science behind their solutions, we had surpassed that and were able to discuss the challenges in practically working the solutions in the real world.
The Real-Time Biosurveillance Program (RTBP) held a news conference in Colombo, Sri Lanka on September 14, 2010 at the Cinnamon Lake Side Hotel. This is list of the articles published in the News papers:
The Director of Carnegie Mellon University’s Auton Lab – Prof Artur Dubrawski – delivered a keynote speech at the Health Informatics Society of Sri Lanka organized eHealth Sri Lanka 2010 conference, 15-16 September, 2010. His talk titled – Detection of Informative Disjunctive Patterns in Support of Clinical Informatics (click to view slides) – has synergies with the Real-Time Biosurveillance Program (RTBP) we are piloting in India and Sri Lanka. RTBP specifically integrates a data mining and probability testing tool called the T-Cube Web Interface. In addition to the keynote, Chamindu Sampath, LIRNEasia Research Assistant, presented a paper titled the “T-Cube web tool for rapid detection of disease outbreaks in India and Sri Lanka” (click to view the slides) and a poster. Several interesting issues regarding data quality needed for event monitoring was discussed by the audience during the session: public health informatics.
The key take home from the workshop were: the Regional Epidemiologist – Dr. P. Hemachandra – stressing the need for Syndromic surveillance; especially, the ability to monitor escalating fever like disease and geographic clusters of increase in common symptoms. Dr. Lakshman Edirisinghe (Deputy Director Planning) emphasized the need for comprehensive patient clinical data for becoming a data driven organization that can optimize the resources opposed to speculative expert opinion.
I was in Lyon, France presenting our mHealth paper – Real-Time Biosurveillance pilot in India and Sri Lanka – at the IEEE-HealthCom conference, which took place 01-03, July 2010 (click to view the slides). I spent an extra day in France to travel down to Grenoble, accompanied by my friend and research partner – Artur Dubrawski – an ex-scholar from Grenoble,  in search of a Joseph Fourier’s statue for a photo opportunity. Why? Jean Baptist Joseph Fourier (21 Mar 1768 to 16 May 1830) was a French mathematician and physicist best known for the “Fourier series” – a way of writing a function as a sum of frequency components; i.e.
The “Evaluating a Real-Time Biosurveillance Program” (RTBP) research team meet in Chennai, July 6 – 7, 2010 to discuss the interim findings of the evaluation work (click to read workshop report) carried out in Tamil Nadu India. In addition to the workshop a news conference was organized to disseminate the pilot project findings. The links below are some of the news prints (click on the thumbnails to view news clippings) :: – Mobiles on Health Calls, The Hindu Business Line, September 13, 2010 – Pilot study in using mobile technology for disease reporting shows promise, Thehindu.com, July 07, 2010 – Pilot study on epidemiological early disease warning system, Chennaionline.com, July 07, 2010 – New tech to keep tab on diseases, timesofindia.
The Sivagangai District (Tamil Nadu, India) Deputy Director of Health Services (DDHS), Dr. Raghupathy, compared the Real-Time Biosurveillance Program (RTBP) to a comprehensive machine with multiple flavors that can give the required surveillance results with the touch of a button. Kurunegala RE (Region Epidemiologist, Sri Lanka), Dr. Hemachandra’s words were “RTBP will give a booster to surveillance in our region”. Evaluation planning workshops took place in Karraikudi, Tamil Nadu and Kurunegala, Sri Lanka.
The document describes the Standard Operating Procedures (SOPs) for data collection, data processing, data reporting, and database/system administration. Data collection involves Setting up of the Biosurveillance Module (BSM) initial information (i.e. implement database) through the web application and direct Database Administration (DBA) functions Installing, configuring, and maintaining the m-HealthSurvey mobile application Health worker expected practices in submitting data Documenting and reporting problems associated with the BSM and m-HealthSurvey Data processing involves Installing, configuring, and maintaining the T-Cube Web Interface (TCWI) analytical tool Installing, , configuring, and maintaining the detection algorithms Health Officials (epidemiologist) expected practices in analyzing the health data Defining priority levels for particular diseases Documenting events of interest Documenting and reporting problems associated with TCWI and detection algorithms Data reporting involves Installing, configuring, and maintaining the Sahana Alerting and Messaging Module (MAM) Initializing the MAM contact lists, jurisdictions, geographical areas, message templates Verification and Authorization procedures for issuing health alerts
Auton Lab is a technology partner developing the T-Cube software for the Real-Time Biosurveillance Program. Prof. Artur Dubrawski (Director of Carnegie Mellon Universities Auton Lab) presented the paper: T­Cube Web Interface for Real­-time Biosurveillance in Sri Lanka at the Eight Annual International Society for Disease Surveillance (ISDS) 2009 in Las Vegas, USA, Dec 03-04. The presentation shows some examples of events detected by the T-Cube analysis on synthetic data set produced using the Sri Lanka Ministry of Health and Nutrition’s Epidemiology Unit published Weekly Epidemiological Report as a basis.
The health departments and health workers involved in the Real-Time Biosruveillance Program (RTBP) pilot see the benefits in the m­-HealthSurvey for real­-time data collection, T­Cube Web Interface for near­-real­-time outbreak detection, and Sahana Alerting Module for real­-time health risk information dissemination. Preliminary lessons to date indicate the need for more robust mobile application for data collection with complete standardized content in disease­-syndrome for reduction of noise and increase of reliability in the datasets. More rigorous capacity building and frequent use is required for health officials to take advantage of the full potential of TCWI. Further exercises need to be carried out with the Sahana Alerting Module to understand its shortcomings. Given that the system has been in preliminary use for less than six months, it is anticipated that the usability issues will subside in time to come.
The   objective   of   this   document: Guidelines for Evaluating RTBP v0.4 is   to   outline   the   evaluation   methodology   for   assessing   the upstream   communication:   data   collection,   data   processing:   event   detection,   and   downstream communication: alerting/reporting stages (verticals in Figure 1) on the aspects of social, content, application, and technology of a Real­Time Biosurveillance Program (RTBP). The blue arrows across the verticals and the horizontals indicate the interoperability between elements.