Staff shortages and an increasingly aging population are straining the ability of emergency departments to provide olwghigh-quality care. Additionally, there is a growing concern about the ability of hospitals and EMS responders to provide effective care during disaster events. To automate the patient monitoring process and improve efficiency, quality of care, and the volume of patients treated, we have developed MEDiSN, a wireless sensor network for monitoring patients’ vital signs in hospitals and disaster events. MEDiSN has been deployed at the Emergency Department at the Johns Hopkins Hospital, at the University of Maryland's Trauma Center, and at the Washington Hospital Center. Recently, MEDiSN has been featured in the Discovery Channel Tech.

Overview of MEDiSN:

Given the U.S. demographic trends (aging population, increasing prevalence of chronic diseases), nursing staff shortages, and decreasing hospital capacities, it is no surprise that the U.S. healthcare system faces immense challenges on a daily basis. Moreover, there is growing concern about the hospitals’ ability to provide effective care during disasters when the surge of patients can be overwhelming. Multiple studies have shown that the use of inefficient tools in the patient care process is one of the root causes behind overcrowded and inefficient hospitals. Thereby, tools that automate the patient monitoring process will greatly improve the quality and effectiveness of health care both on a daily basis and during disasters. While these needs are widely accepted, a multitude of problems confront technology developers. First, a multi-stage infrastructure, including sensing devices, wired and wireless networks, and back-end servers, is necessary to generate medically relevant results. Second, healthcare providers have understandably little time and patience to work with untested technologies and engineering prototypes. Finally, healthcare facilities and research with human subjects present unique technical, administrative, and ethical challenges that few technologists have encountered.

In response to this challenge, we are developing miSense, an end-to-end platform for medical sensing applications. miSense includes all hardware and software components to design, develop, and deploy compelling sensing applications in the healthcare field. Specifically, we are developing the miTag (medical information Tag), an embedded wireless sensing device customized for healthcare applications. The miTag’s extensible design allows the easy integration of medical sensors (e.g., heart and respiration rate, blood pressure, ECG, etc.) and application-level software. The miTag has a small form factor, is battery-powered, and includes a wireless network interface allowing the persistent tracking of patients’ data throughout clinical facilities. Moreover, we are developing the miNet wireless network infrastructure that transports the miTags' measurements and allows administrators to remotely configure them. Finally, we are developing the miStore and miView servers that persistently store the collected measurements and deliver them to authenticated end-users.


An early prototype of miSense was deployed at the operating room and post anesthesia care unit of the Shock Trauma Center of the University of Maryland Medical Center and the emergency rooms of the Johns Hopkins Hospital and the Washington Hospital Center.

In collaboration with our partners at the Johns Hopkins Hospital, we selected the task of monitoring unattended Emergency Room patients as the first application for miSense. Specifically, patients waiting to be seen at the Emergency Room were given miTags that continually monitored their heart rate and blood oxygen levels. Medical staff remotely monitored the patients’ vital signs and were able to promptly respond to signs of deterioration. The results from the initial deployment at the Johns Hopkins hospital were very encouraging: the wireless network was successful in delivering the collected vital signs despite a challenging radio environment and patient mobility. Moreover, the average patient satisfaction level was 3.47 (on a 1-4 scale) and 91% of the patients indicated that they would be willing to use the device in the future.

Project Members:

Publications and Posters:

20112010, 2009, 2008






User Interface (miView) Code:

Media Coverage:

Code Contributions:

All of the code contributed to TinyOS from the MEDiSN project is part of the main TinyOS 2.x tree (link) .


This project is partially funded by the National Science Foundation under project #0855191.