Title: Optimal Adaptive Scheduling of Clinical Assessments


Ecological Momentary Assessment (EMA) data provides a rich context for diagnosing and tracking the progression or remediation of disease during health care interventions. EMA enables frequent data collection between clinical appointments and in non-clinical settings. When implemented on mobile systems it provides a platform for real-time delivery of behavioral therapy and healthcare management. However existing EMA approaches are limited by the following:
1) They depend on pre-selected tests and conditions that are not optimized to the patient’s behavioral or functional level, or to changes in the patient’s behavior or function during treatment
2) The testing schedule is pre-determined and does not update in response to changes or patterns detected in the data
Technology Overview
Northeastern researchers have developed an adaptive method for disease diagnosis, tracking and assessment. The approach works by selecting optimal test schedules for detecting presence, progression, or remediation of disease, disease symptoms, and treatment side effects, as well as the scheduling of therapeutic interventions and the possible cessation of treatment. Clinical assessment data is collected from the patient, and machine learning approaches are used to detect unknown patterns in the data, modifying the testing schedule in real-time based on these analyses. This approach is designed to generate fast estimates of an unknown time-series function using a minimum number of observations in the form of clinical measurements. These adaptive methods operate on mobile testing equipment, with the precision of clinical and research-grade apparatus.
- Controls the timing of the assessment in order to collect data at times and under conditions that are most informative
- Increases test reliability through reduction in redundancy and prevention of frustration/fatigue of patient
- Optimizes the treatment schedule allowing for pharmaceutical companies to evaluate and track the efficacy of drugs for chronic medical conditions
- Provides significant reductions in the size and cost of clinical trials
- Clinical trial management
- Inviduailized/personalized medicine
- Remote patient monitoring
- License
- Partnering
- Research collaboration
Patent Information:
For Information, Contact:
Mark Saulich
Associate Director of Commercialization
Northeastern University
Peter Bex
John Ackermann
Tobias Elze