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.
Prof. K. Vijayraghavan, Director of the National Center for Biological Sciences, in Bangalore is one of five recipients of this year’s Infosys Science Foundation prize, given to world-class researchers in social science in India. Along with our friends from the Indian Institute of Technology Madras’s – Rural Technology and Business Incubator, Prof. Vijayraghavan is one of the Investigators of the Real-Time Biosurveillance Program (RTBP) carried out in the state of Tamil Nadu in India and Sri Lanka.
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.
A m-HealthSurvey Certification Exercise was carried out as part of the m-Health Real-Time Biosurveillance Program (RTBP) to measure the usability and adoptability of the m-HealthSurvey mobile application. The exercise was conducted with health workers in Sivagangai District, Tamil Nadu, India and in Kurunegala District, Sri Lanka. The final results of the exercise will be published in the near future. m-HealthSurvey is a mobile application developed by indian Institute of technology Madras’s Rural Technology and Business Incubator (RTBI) for collecting near real-time patient disease, syndrome, and demographic data for rapid detection of disease outbreaks. It is a J2ME midlet that allows users to select categorical data as well as type information to generate patient clinical records to be submitted via GPRS to a central database.
m-Health Real-Time Biosurveillance Program (RTBP) interviewed Medical Officers in Kurunegal District in Sri Lanka and Sivagangai District in Tamil Nadu, India, during the months of September and October, 2009. These interactions revealed that outpatient health record entry in real-time by Medical Officers, using the mobile phone key pad is inefficient and the idea was rejected by them. The aim of the RTBP is to collect digitized patient disease, syndrome, and demographic information from the point of care to rapidly detect disease outbreaks. Village Health Nurses in Tamil Nadu examine at most 70 patients a week. Ninety percent of the Village Health Nurses opt to jot down the records on paper and later enter them leisurely after the day’s work is complete.
In developing countries such as Sri Lanka, when government has no resources to deliver the essential public good of early warnings, alternate methods must be advocated – that was the idea of the HazInfo research project, where civil society in villages were given training to respond appropriately to alerts received from the Hazard Information Hub located at the Sarvodaya Head Office in Moratuwa, Sri Lanka. The technology and organizational structure of the HazInfo last-mile hazard warning system proved to work as designed and drew valuable lessons for a full scale implementation. However, the major dilemma was in finding resources to sustain the system. The Hoteliers’ Association of Sri Lanka agreed to obtain services from Sarvodaya for a fee to train and certify the hotel staff in disaster response. This fee would go towards the OPEX of the HazInfo emergency response planning component and operationalize a 24/7/365 Hazard Information Hub for issuing alerts; but to kick start the endeavor a nominal CAPEX is required.
The main problem, identified by India and Sri Lanka health workers, with the Rural technology and Business Incubator (RTBI) developed m-HealthSurvey mobile application, was in the look up content. The application allows for the user to search for a disease name by typing a few characters of the name. Upon selection predefined symptoms and signs are auto-displayed, giving the user the option to edit those values, if needed. The Health Workers using the application to send patient case information, expressed the need for full list of all possible symptoms and signs, associated with each disease; then all they have to do is delete and not enter. Entering is cumbersome for those user; especially in Sri Lanka, who are not familiar with the spelling of symptom and signs.
The Real-Time Biosurveillance Program (RTBP) information communication system comprises an upstream health data submission by last-mile health workers, data processing by epidemiologist, and downstream alerting by health officials.There are four components to the RTBP software: mobile phone application, desktop web application, database, T-Cube analytic tools, and Common Alerting Protocol messaging. The individual components are to be developed by Rural Technology and Business Incubator, Respere (Private) Limited, and Auton Lab. Following are the four software requirement specification documents – 1) Sahana biosurveillance module (database and desktop web application) 2) Mobile J2ME application (data collection) 3) T-Cube web interface (analysis and event detection) 4) Sahana Common Alerting Protocol Messaging Module (publishing SMS/Email/Web alerts)
Village Health Nurses (VHN) are the last-mile health workers attending to the primary health care needs of the rural villagers in the state of Tamil Nadu; where the real-time biosruveillance program (RTBP) is being pilot tested in India. They work under harsh conditions. For instance transportation schedule is limited to a bus that leaves in the morning and returns in the afternoon. Baking and sweating in the hot sun in Sivaganga District of Tamil Nadu, they walk for several kilometers, carrying a heavy load of Registers, making house calls to give the much needed health care to the rural poor. During a recent workshop, in Tamil Nadu, a discussion around the accountability of submitting data revealed that the VHN sometimes cheat on the statistics they tediously record on large volumes of paper forms.
After showcasing our work at ICTD2009 (see poster), where our work: real-time biosurveillance program (RTBP) was highlighted along with Bill Gates in a Qatar media article, Prof. Artur Dubrawski (Director Auton Lab) and I returned to Sri Lanka to engage in work related to our pilot project: RTBP. Prof. Dubrawski’s visit included a workshop on T-Cube web interface in support ot the RTBP for the RTBP researchers at Sarvodaya head quarters in Moratuwa (see workshop program), a colloquium on Machine Learning in Support of Biomedical Security for the faculty and students at the University of Colombo School of Computing, and participating in the health worker m-HealthSurvey training program in Kuliyapitiya. The work under taken, April 21 – 25, is elaborated in the trip report.
Sixteen Sarovdaya Suwadana Center Volunteers working in the capacity of Research Assistants for the real-time biosurveillance program were trained in the use of the m-HealthSurvey mobile application. The training took place at the Sarvodaya Kuliyapitiya District Center, April 23 – 25, 2009. The three day program comprised lectures on disease surveillance and notification, use of mobile application for communicating patient data, and a field visit to understand the working environment. The Suwadana Center Volunteer training workshop report carries the full story.
“Leptospirosis is out and Dengue is in” – these are the words of the Sarvodaya Research Assistant – Pubudini weerakoon – working in Kurunegala District of Sri Lanka on the real-time biosurveillance program (RTBP). This report on Leptospirosis in Sri Lanka gives a full account of the past events. The aim of the RTBP is to gather patient case information through the m-Healthsurvey mobile application and subject that data to real time analysis for rapid detection of emerging health events. The automated analytic and detection is driven by the T-Cube software, developed by Carnegie Mellon Universities Auton Lab, based on data mining principles. We took the weekly epidemiological reports (WER) from the past two years and put T-Cube to the test.
Press Release 2009 from Brown Lloyd James. ICTD2009 highlights new developments in technology for developing countries “Dr. Artur Dubrawski, Director of the AutonLab at Carnegie Mellon University and Mr. Nuwan Waidyanatha, Senior Researcher and Project Director of LIRNEasia in Sri Lanka, are presenting their collaborative project using mobile telephony. The project uses the T-Cube Web Interface, a tool developed by Carnegie Mellon University to visualize and manipulate large scale multivariate time series datasets, to support real-time bio-surveillance.
Right from the concept stage Carnegie Mellon University’s Auton Lab has been engaging with LIRNEasia and other project partners in developing the “Evaluating a Real-Time Biosurveillance Program: Pilot Project (abbreviated as RTBP) proposal. In the month of July 2008, the International Development Research Center of Canada made available a grant to carry out the RTBP research project. The RTBP research aims to answer the question: “Can software programs that analyze health statistics and mobile phone applications that collect and report health information potentially be effective in the early detection, intervention, and prevention of disease outbreaks?” This project is a pilot aiming to study the technology, human, and policy predicaments in introducing the RTBP to Sri Lanka and India. Conventional aggregated reports on disease counts or the paper based notification systems in India and Sri Lanka have not proven to be effective in providing the much needed near real-time detection for containing disease before it takes the lives of a few patients.
The intention of this blog is to share the user requirements captured during the business analysis phase of the real time biosurveillance program. The state of Tamil Nadu and Sri Lankan business cases are documented in the report. Any changes can be discussed in this blog itself.