MD2K Software
Introduction
The MD2K software includes a smartphone platform called mCerebrum and a cloud counterpart called Cerebral Cortex.
mCerebrum is a configurable smartphone software platform for mobile and wearable sensors. It provides support for reliable data collection from mobile and wearable sensors, and real-time processing of these data for sensor-triggered just-in-time adaptive interventions.
Cerebral Cortex is the big data cloud companion of mCerebrum designed to support population-scale data analysis, visualization, model development, and intervention design for mobile sensor data. It provides the ability to do machine learning model development on population scale data sets and provides interoperable interfaces for aggregation of diverse data sources.
While MD2K is not a recruitment tool nor a server host, our software can be installed and used by anyone who wishes to advance research in mobile health using cutting edge techniques in high-frequency data collection, real-time intervention, and all the other unique capabilities MD2K can offer.
Software Overview
High-Rate Sensing
mCerebrum is a mobile phone software platform that can be used to collect both high-rate raw sensor data and associated labels in the field.
Multi-Sensor Field Studies
mCerebrum supports seamless sharing of streaming data from multiple sensors to enable computation of multi-sensor biomarkers (e.g., sress, smoking, eating), which can be remotely monitored through Cerebral Cortex.
Real-Time Data Quality Monitoring
mCerebrum supports real-time assessment of data quality to ensure data fidelity which is couple with Cerebral Cortex real-time montoring capabilities.
Marker Development and Validation
Cerebral Cortex supports population-scale data analysis and visualzation to enable marker development and validation.
To Monitor Health Wellness and Work Performance
mCerebrum aims to unleash a new wave of innovative research in the assessment and improvement of everyday job performance.
Real-Time Biomarker Computation
mCerebrum is architecturally scalable to support concurrent computation of a large number of biomarkers (each of which requires complex processing) without saturating the computational capacity or battery life of a mobile phone.
Sensor-Triggered Mobile Interventions
mCerebrum supports the sense-analyze-act paradigm to aid the development and evaluation of sensor-triggered interventions
Mobile Sensor Big-Data
mCerebrum allows for high-frequency raw sensor data collection (800+ Hz for 70+ million samples/day), processing, and storage (~2GB/day) and is coupled with Cerebral Cortex which scales to 1,000s of concurrent mCerebrum instances and 100s of terabytes of data.
High-Frequency Data in Real-Time
Wrist sensor gyroscrope
Mobile health data solutions are emerging and evolving every day. While most of these software platforms are primarily designed for low-frequency data collection, the MD2K platform is designed from the ground up as a high-frequency data stream processing toolchain that provides flexible data types and custom object storage. It can collect and analyze data from tens of wearable sensors via a wide array of wireless radios (ANT, Bluetooth, Bluetooth LE, etc.). It also provides native support for triggering notifications, self-report prompts, and interventions based on real-time values of digital biomarkers derived from sensor data.