Establishing an instrumented training environment for simulation-based training of health care providers: An initial proof of concept
Scott M Pappada1, Thomas John Papadimos2, Jonathan A Lipps2, John J Feeney3, Kevin T Durkee3, Scott M Galster4, Scott R Winfield5, Sheryl A Pfeil6, Sujatha P Bhandary2, Karina Castellon-Larios2, Nicoleta Stoicea2, Susan D Moffatt-Bruce7
1 Department of Anesthesiology, The Ohio State University Wexner Medical Center, Columbus; Aptima, Inc., Dayton, OH, USA
2 Department of Anesthesiology, The Ohio State University Wexner Medical Center, Columbus, USA
3 Aptima, Inc., Dayton, OH, USA
4 United States Air Force Research Laboratory, Dayton, OH, USA
5 Clinical Skills Education and Assessment Center, The Ohio State University College of Medicine, Columbus, OH, USA
6 Clinical Skills Education and Assessment Center, The Ohio State University College of Medicine; Department of Medicine, Clinical Skills Education and Assessment Center, The Ohio State University College of Medicine, The Ohio State University Wexner Medical Center, Columbus, OH, USA
7 Department of Surgery, Division of Thoracic Surgery, The Ohio State University Wexner Medical Center, Columbus, USA
Thomas John Papadimos
Department of Anesthesiology, The Ohio State University Wexner Medical Center, 410 West 10th Avenue, Columbus, OH 43210
Source of Support: None, Conflict of Interest: None
Objective: Several decades of armed conflict at a time of incredible advances in medicine have led to an acknowledgment of the importance of cognitive workload and environmental stress in both war and the health care sector. Recent advances in portable neurophysiological monitoring technologies allow for the continuous real-time measurement and acquisition of key neurophysiological signals that can be leveraged to provide high-resolution temporal data indicative of rapid changes in functional state, (i.e., cognitive workload, stress, and fatigue). Here, we present recent coordinated proof of concept pilot project between private industry, the health sciences, and the USA government where a paper-based self-reporting of workload National Aeronautics and Space Administration Task Load Index Scale (NASA TLX) was successfully converted to a real-time objective measure through an automated cognitive load assessment for medical staff training and evaluation (ACLAMATE).
Methods: These real-time objective measures were derived exclusively through the processing and modeling of neurophysiological data. This endeavor involved health care education and training with real-time feedback during high fidelity simulations through the use of this artificial modeling and measurement approach supported by Aptima Corporation's FuSE2, SPOTLITE, and PM Engine technologies.
Results: Self-reported NASA TLX workload indicators were converted to measurable outputs through the development of a machine learning-based modeling approach. Workload measurements generated by this modeling approach were represented as a NASA TLX anchored scale of 0–100 and were displayed on a computer screen numerically and visually as individual outputs and as a consolidated team output.
Conclusions: Cognitive workloads for individuals and teams can be modeled through use of feed forward back-propagating neural networks thereby allowing healthcare systems to measure performance, stress, and cognitive workload in order to enhance patient safety, staff education, and overall quality of patient care.
The following core competencies are addressed in this article: Medical Knowledge, Interpersonal Skills, Patient Care, and Professionalism.