softwareFuture Research Agenda

MD2K's goal has been to demonstrate that the key to improving your health can be the cellphone in your hand or the smartwatch on your wrist. In pursuit of this goal, MD2K has developed the tools that make it possible to take complex, high-frequency mobile sensor data and turn it into something more meaningful than a heart rate or step count.

This has been done by harnessing the sensors commonly found in smartphones and fitness trackers, along with creating some new ones, to find indicators of health states that provide insight into conditions such as drug addiction, smoking, heart failure and obesity.

The mobile sensor data sources used by MD2K are:

• AutoSense: Electrocardiogram (ECG), respiration, accelerometers
• Microsoft Band: Accelerometers, gyroscopes
• MotionSense: Accelerometers, gyroscopes
• EasySense (contactless sensors): Heart motion, lung motion, lung fluid level
• Smartphone Sensors: Global Positioning System (GPS), accelerometers, self-report
• Smart toothbrush: Brushing motion, pressure, tooth location

Traditionally, mHealth researchers have tried to pull biomarker data directly from the sensors and use it in biomedical research. This method poses challenges, because raw sensor data often contains gaps and noise, and the number of samples collected per day is in the hundreds.

MD2K’s approach is to collect millions of samples per day, and process that data through its mCerebrum software suite to identify, develop and validate biomarkers that can be used in research.

A mobile software platform developed by MD2K is capable of collecting 55 million mobile sensor samples per day from high- and low-frequency sensors.

 

Publications

 

 

 

Copyright © 2017 MD2K. MD2K is supported by the National Institutes of Health Big Data to Knowledge Initiative (Grant #1U54EB020404)

Team: Cornell Tech, GA Tech, Harvard, U. Memphis, Northwestern, Ohio State, Open mHealth, UCLA, UCSD, UCSF, UMass, U. Michigan, Utah, WVU