This work aims to transform the derivation of clinically-actionable pain measures from patient-generated, mobile-health data.
In particular, we are designing, implementing and evaluating:
Mobile devices and wearables offer up continuous data from patients, but these data streams must be summarized, synthesized, and combined to create clinically meaningful measures of a patient's disease status. We are researching analytical techniques that create robust behavioral biomarkers from noisy, continuous, mobile data streams. As a starting point we defined a preliminary Mobility Index which represents multiple activity streams in a legible calendar-based output.
We have several clinical research groups, and over 50 research participants, using our current platform to conduct small scale feasibility studies.
While passively collected data is a critical form of objective and low-user-burden measurement, self-report is still essential to understand the patient's experience of pain. New forms of multi-modal self report aim to leverage the capabilities of visually rich interfaces to minimize self-report burden while maintaining or improving the validity of the self-reported data.
We are developing methods for utilizing sensed user experience to collect richer, less obtrusive, and more accurate self-report data. We are also creating more intuitive methods for reporting pain intensity and interference.
We have developed an open source, end to end complete system for capturing, managing, processing and visualizing patient data called Ohmage-omh. We are using this system to engage clinicians across several specialities in a participatory design process that targets clinically useful and usable summarization of behavioral biomarker data in the context of patient care.
For example, based on initial clinician interviews, we defined a preliminary Mobility Index which represents multiple activity streams in a legible calendar-based output. In the next phase of our work these data will be integrated with self report.
Ohmage-omh is a modular, open-source, open-architecture mobile health platform that is intended for rapid prototyping and piloting of mobile health applications. The system consists of downloadable applications for both Android and iOS and a secure Open mHealth compliant data store. (See Open Source on Github)
We make the software available for researchers to host their own instance of the system and described the process for contacting us to run their projects on our instance. (See Instructions for installation)