Assessment of Circulatory Dysfunction by Automated Processing of Vital Signs Data
Abstract
Background: Casualty care is challenging because caregivers may be inexperienced, or distracted by environmental dangers or multiple casualties. Objective: To provide clinical data for development and validation of a system that executes, in real time, automated decision-assist tools that accurately identify key trauma patient conditions and guide relevant life-saving interventions. This system will be comprised of novel artificial intelligence algorithms that only rely on data measured by standard patient transport monitors. Specific Aims: We will validate a, fully functional prototype of the decision-assist system, which can be provided to an industry partner for full productization. Study Design: We will prospectively trial these algorithms by making use of our operational, IRB-approved plug-and-play system for clinical field-testing of algorithms, presently in use on board Boston Medflight helicopters and the MGH Emergency Dept. Relevance: Because the necessary medical instrumentation, i.e., a standard travel monitor, is so very familiar to caregivers, these decision-assistance capabilities could be broadly deployed with a relative minimum of additional training, hardware acquisition, and up-front buy-in by clinicians.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2019
- Accession Number
- AD1094993
Entities
People
- Andrew Reisner
Organizations
- Massachusetts General Hospital