2020-05-06: PTSD Assessments in COVID-19 Health Care Workers

Figure 1:  Both military and medical personnel are at risk for psychological trauma [BBC.com]
Health care workers are working in unfamiliar territory in recent times. Hospitals in major cities are overwhelmed by the number of patients they are handling as a result of the coronavirus disease 2019 (COVID-19) pandemic. There are accounts of people dying in the hospital hallways before help can arrive due to an insufficient amount of space, equipment and staff to handle the influx of patients. Hospital morgues are overflowing. To make matters worse, doctors and nurses have to worry about exposure to COVID-19 and/or possibly exposing their families largely due to a lack of personnel protective equipment (PPE).

The current environment is putting health care works at greater risk of developing Post-Traumatic Stress Disorder (PTSD). As a matter of fact, hospital personnel have started to report symptoms consistent with those suffering with PTSD from sleep disturbances to constant worry and paranoia. There have even been reports of suicide among first responders and emergency room physicians. However, the increased risk is not limited to those in health care. Loss of wages, self-isolation, and illness as a result of the pandemic are expected to cause emotional trauma for millions.

PTSD is usually diagnosed through one of many survey-based assessment methods such as the Clinician-Administered PTSD Scale (CAPS) or PTSD Checklist-Military (PCL-M). Unfortunately, these methods depend on a patient's ability to reliably and consistently verbalize his or her symptoms and feelings. If a diagnosis cannot made, multiple therapy sessions could be required before a definitive diagnosis can be provided. The process can also be subject to doctor bias, especially when the results may lead to financial gain (e.g., disability payments).  These challenges are further detailed in one of our recent publications.

Bathsheba Farrow, and Sampath Jayarathna, "Technological Advancements in Post-Traumatic Stress Disorder Detection: A Survey", IEEE 20th International Conference on Information Reuse and Integration for Data Science , Los Angeles, CA, July 31-August 3, pp. 223-228, 2019.

With the identification of reliable biomarkers, automated classification of symptoms could accelerate the assessment process and provide reproducible, objective results in comparison to the widely relied upon survey-based PTSD assessment methods. Research in automated PTSD symptom assessment being conducted in the computer science department at Old Dominion University intends to do just that and could provide rapid results for not only health care workers, but also military personnel and other individuals exposed to trauma. In the past, our lab (Nirdslabhas already used machine learning and deep learning techniques on electroencephalogram (EEG) measurements to successfully detect autism spectrum disorder (ASD). These same techniques will be applied to EEG measurements from PTSD subjects to prove its utility for initial PTSD screening as well as measuring symptom severity following a treatment regimen.

Yasith Jayawardana, Mark Jaime, and Sampath Jayarathna, "Analysis of Temporal Relationships between ASD and Brain Activity through EEG and Machine Learning", IEEE 20th International Conference on Information Reuse and Integration for Data Science , Los Angeles, CA, July 31-August 3, pp. 151-158, 2019.

Future PTSD studies are being planned to prove the accuracy of our analytical models.  In collaboration with Professor Serina Neumann at Eastern Virginia Medical School (EVMS), EEG data sets captured with a hospital grade EEG system are being analyzed to build and refine models to support automated PTSD symptom assessments.  However, future EEG measurements will be made with more mobile, commercial EEG devices. We recently acquired the Cognionics Quick-30 EEG system with psychological sensory suite for our PTSD research.  
Figure 2:  CGX Quick-30 EEG headset 
The models under development and mobile EEG capabilities will eventually be incorporated into an end-to-end system that can be used in office settings, hospitals and even forward deployed.  To keep up with the latest updates on our PTSD research, be sure to follow us on Twitter.

-- Bathsheba Farrow (@sheissheba)