PUBLICATIONS

Monitoring, Extracting, and Decoding Indicators of Cognitive Workload (MEDIC)

Bracken, B.1, Palmon, N.1, Frederick, B.2, Cooke, N.3, Romero, V.1, Koelle, D.1, and Pfautz, J.1

Poster to be presented at Neuroscience 2015, Chicago, IL (October 2015)

Background: The success of emergency medical personnel in saving lives depends on their acting quickly and effectively, as individuals and as teams. Training must go beyond individual skills to include team member interactions, and how skills transfer to stressful environments. Currently, trainers must infer competence by observation alone—a challenging task. Automatically sensing indicators of cognitive workload can augment performance observations, offering insight into factors underlying that performance.

Method: We designed and demonstrated a system to augment training by Monitoring, Extracting, and Decoding Indicators of Cognitive workload (MEDIC). MEDIC combines a multimodal suite of unobtrusive, field-ready neurophysiological, physiological, and behavioral sensors; complex event processing to extract and fuse the best indicators of cognitive workload and team dynamics from the multiple, high-volume data streams originating from the sensor suite; and probabilistic modeling to interpret those indicators for easy understanding.

Results/Conclusions: We designed a head-mounted device to measure cognitive load, a body band device to measure physical activity, and a user interface (UI) for trainers to take notes and record time-tagged photos and videos as the scenario unfolds. During our pilot study, we successfully extracted and fused data from two individuals across both physically (simulated CPR) and cognitively (arithmetic and n-back cognitive task) demanding conditions. We concisely identified complex sequences of events in raw data using complex event processing. MEDIC is capable of processing both continuous (heart rate, oxygenated hemoglobin) and discrete (communication events, trainer observations on performance) variables. We explored five methods of data modeling, and determined that for our pilot data weighted averaging was most accurate for estimating individual state (stress and cognitive workload), but Causal Influence Models were most accurate for team state (team dynamics). Finally, we designed a separate UI that displays interpreted data after the simulation, including information about each state for each individual and for the team. Future work will include validation of each component of MEDIC using laboratory studies and testing in realistic training environments.

Charles River Analytics
McLean Hospital/Harvard Medical School
Arizona State University

This work was supported by the U.S. Army Medical Research and Material Command under Contract No. W81XWH-14-C-0018. The views, opinions and/or findings contained in this report are those of the author(s) and should not be construed as an official Department of the Army position, policy or decision unless so designated by other documentation.

For More Information

To learn more or request a copy of a paper (if available), contact Bethany Bracken.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)