This CAREER project is developing a wireless sensor network infrastructure for medical care applications. Sensor networks have the potential for enormous impact on many aspects of medical care. In a hospital or clinic, outfitting every patient with wireless vital sign sensors will allow doctors and nurses to continuously monitor the status of their patients. In an emergency scenario, the same technology enables medics to care for large numbers of casualties. This project involves the development of a robust, scalable software platform for medical sensor networks, called CodeBlue, which provides protocols for device discovery, publish/subscribe multihop routing, and a query interface allowing caregivers to request data from groups of patients.

CodeBlue is focused on addressing the challenges of robustness and scalability of large networks of wireless medical sensors. With limited radio bandwidth, highly variable data rates, and a broad range of reliability requirements for medical sensors, it is necessary to develop techniques that can tune the bandwidth and data quality delivered by the network. This project is developing a suite of small, wireless, wearable medical sensors; adaptive, cross-layer approaches to quality-of-service and congestion management; and techniques for analyzing and fusing data across multiple patient sensors.

The research undertaken through this project will have significant impact on the development of future medical sensing technologies. In collaboration with several hospitals and medical research groups, this project is evaluating the CodeBlue system in real clinical settings, including large-scale disaster response, monitoring stroke patient rehabilitation, and understanding the effects of medication on Parkinson's Disease.

Project Report

This project investigated novel technologies for the use of wireless sensor technology in medical care settings, including emergency care, disaster response, and rehabilitation medicine. The use of tiny, wearable, wireless sensors has the potential to revolutionize many aspects of medical care by providing caregivers with real-time data on patient vital signs, location, activity patterns, and more. In a disaster response scenario, first responders could outfit each victim with a tiny wireless tracking tag to monitor their vital signs in real time, making it possible to keep track of many victims at the scene, during transportation, and during treatment at a medical facility. In a rehabilitation medicine application, wireless sensors could monitor the movement and activity patterns of individuals being treated for Parkinson's Disease, stroke, or epilepsy, making it possible to develop new treatments and study the long-term effects of medications. During the course of this project, we developed a new software stack for low-power wireless medical sensors. This software stack, called CodeBlue, included new communication mechanisms to allow wireless sensors to rapidly and reliably relay information on the patient status to a command post or a smartphone. We also developed software to enable long-term, high-resolution measurements of movement patterns from multiple sensors on the patient's body (for example, on the arms, legs, and torso). This software carefully manages wireless communication of the sensors to ensure that high quality data can be collected over long periods of time with tiny batteries. We deployed these sensors and our software stack as part of a pilot study at the Spaulding Rehabilitation Hospital in Boston, MA, which has been used to collect data on multiple patients taking part in a study of Parkinson's Disease treatments.

Agency
National Science Foundation (NSF)
Institute
Division of Computer and Network Systems (CNS)
Application #
0546338
Program Officer
Min Song
Project Start
Project End
Budget Start
2006-02-15
Budget End
2011-07-31
Support Year
Fiscal Year
2005
Total Cost
$450,000
Indirect Cost
Name
Harvard University
Department
Type
DUNS #
City
Cambridge
State
MA
Country
United States
Zip Code
02138