JMIR Publications

ABSTRACT

Background:

The Institute for Surgical Research (formerly known as the Telemedicine and Advanced Technology Research Center [TATRC]) conducted a formal analysis of three prototype sensor suites; all were designed to passively document care delivery in tactical combat casualty care (TCCC) environments. In the future, mature sensor suite systems will generate beneficial healthcare information in austere environments without distracting from care delivery.

Objective:

Conducting a systematic performance analysis of early-stage sensor suite prototype configurations determines the potential approaches for continued development and refinement to maximize the performance of the technologies.

Methods:

The sensor suite evaluation methodology prioritized functionality, usability and performance. Specifically, the assessment consisted of three phases: (1) tabletop evaluations, (2) simulated use testing and (3) a sensor suite rodeo simulation event. The second and third phases included human subject participants leveraging the technology sets in hyper-realistic TCCC simulation environments. The entirely of the sensor suite system configurations and their individual commercial off the shelf (COTS) components were included in the comparative assessment.

Results:

There were no statistically significant differences observed in the initial tabletop evaluations. Key differences emerged during the second and third phases of the evaluation. From a quantitative perspective, the usability scores of the first (M-WAVE) and third sensor suites (PoTAg) were significantly higher than the second (ACME) prototype configuration. From a qualitative perspective, there were reliability concerns about latency display issues with a specific vital sign monitor (VSM) and the electromyography (EMG) armband technology was preferred approach when contrasted with inertial measurement unit (IMU) components. From a data quality perspective, output rates were consistent in all environmental conditions for first sensor suite, but variable for the second and third configurations. There were issues aggregating large data files (greater than 1 GB) into a common computing device on the first sensor suite configuration.

Conclusions:

This systematic sensor suite evaluation is critical to determine the direction of medical advanced technology capabilities on the future battlefield. The comparative assessment outcomes reveal opportunities to blend the strengths into a next generation implementation. However, the evaluation was constrained by several factors. An unmet capability is effective tracking of the use of consumable medical supplies at the point of care (POC). The phase 2 and 3 qualitative analyses was limited by incomplete participant survey responses. Because artificial intelligence (AI) based algorithms for the sensor suites were still under development at the time of this assessment, data quality phase did not assess the sensor suite capacities to process algorithms. Finally, the ability of the sensor suites to manage multiple casualties/patients was not a requirement of these early-stage prototypes. Follow-on evaluations for these critical elements will be required in the future.