Saturday, July 12, 2008

Real-time biosurveillance research is off the ground

The long awaited real-time biosurveillance program pilot project officially began on 11-July-2008. LIRNEasia received a grant from the International Development Research Center to conduct the developmental research project over the next 2 years. I will be working in the capacity of the Project Director.

The first year will be spent on developing the ICT system for disease surveillance and notification. Data will be collected through a J2ME mobile phone application, which would be a direct adoption of the java rosa (a.k.a openROSA) suite of applications or a rendition of it. The analytics algorithms with GUI for detection of disease outbreaks will come from Auton Lab. Very well use Sahana Messaging or SMS Geo-Chats for a feedback/follow-up mechanism with a log for sending and keeping track of alerts.

Second year will be devoted to evaluating the ICT system in a real world setting where the government and community health care workers will use the system as part of their daily routines. A prominent question will be determining the incentives for health care workers in rural settings to participate in a e-Health based programs. We will look at the productivity increase, which will be weighted against a control group who is not exposed to the e-Health based disease surveillance and notification program. Justify issues related some prior studies that have shown effects of manipulation of data - under-reporting or over-reporting - depending on the circumstance. Evaluate the effectiveness of biosurveillance algorithms in detecting disease outbreaks and understanding whether mobile application based data streams can assist in the detection and notification process; as well as the different aspects between the different sides (data collectors, algorithm designers, algorithm implementers, health monitors, program evaluators, etc) in the overall picture.

Some of the initiatives in the same disease surveillance and notification space are the following projects -- Google Predict & Prevent, InSTEDD, Sahana, D-Tree, Dimagi, GATHER, among many others.

Wednesday, July 2, 2008

Healthcare Worker based mobile Sensor Systems

The aim of the real time biosurveillance program is to mobilize Healthcare Workers in the rural settings with mobile phones to record and submit patient counts for the purpose of consolidating national health data for surveillance of unusual patterns (headsup). Problem that this real-time biosurveillance program (RTBP) promises to solve is to strengthen existing disease surveillance and detection communication systems, reduce latencies in detecting and communicating disease information, and set a stand interoperable protocol for sharing disease information with national and international health-related organizations in the region.

My role in the RTBP is working in the capacity of a Researcher and Project Director. The grant has been approved by IDRC but the administrative work remains to be completed before funds can be transfered and work can begin

RTBP shares many similarities with the small study working in (somewhat) rural Tanzania focus on guiding health care workers through medical algorithms, with the primary goal of improving care and the secondary goal of collecting data. In particular, it is automated with the IMCI protocols for classifying and treating childhood illness. If you are interested, an online paper titled "e-IMCI: Improving Pediatric Health Care in Low-Income Countries" describes the project and lessons learned.

The design of RTBP using mobile phones is in par with this abstract from the IEEE Internet Computing article titled - The Rise of People-Centric Sensing - "Technological advances in sensing, computation, storage, and communications will turn the near-ubiquitous mobile phone into a global mobile sensing device. People-centric sensing will help drive this trend by enabling a different way to sense, learn, visualize, and share information about ourselves, friends, communities, the way we live, and the world we live in. It juxtaposes the traditional view of mesh sensor networks with one in which people, carrying mobile devices, enable opportunistic sensing coverage. In the MetroSense Project's vision of people-centric sensing, users are the key architectural system component, enabling a host of new application areas such as personal, public, and social sensing."