2021/10/25 by Mahnoosh Sadeghi, Sadeghi, Mahnoosh, Farzan Sasangohar +3
Medicine · Psychology · #FOS: Computer and information sciences #Heart Rate Variability and Autonomic Control #Human-Computer Interaction (cs.HC) #Posttraumatic Stress Disorder Research #Traumatic Brain Injury Research
paper · pdf · doi:10.48550/arxiv.2110.13211
openalex publication_date 2021/10/25 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Post Traumatic Stress Disorder is a psychiatric condition experienced by\nindividuals after exposure to a traumatic event. Prior work has shown promise\nin detecting PTSD using physiological data such as heart rate. Despite the\npromise shown by the machine learning based algorithms for PTSD, the validation\napproaches used in previous research largely rely on theoretical and\ncomputational validation methods rather than naturalistic evaluations that\naccount for users perceived precision and validity. Previous research has shown\nthat users perceptions of physiological changes may not always align well with\nautomated detection of such variables and such misalignment may lead to\ndistrust in automated detection which may affect adoption or sustainable usage\nof such technologies. Therefore, the goal of this article is to investigate the\nperceived precision of the PTSD hyperarousal detection tool (developed\npreviously) in a home study with a group of PTSD patients. Naturalistic\nevaluation of such data driven algorithms may provide foundational insight into\nthe efficacy of such tools for non intrusive and cost efficient remote\nmonitoring of PTSD symptoms and will pave the way for their future adoption and\nsustainable use. The results showed over sixty five percent of perceived\nprecision in naturalistic validation of the detection tool. Further, the\nresults indicated that longitudinal exposure to the detection tool might\ncalibrate users trust in automation.\n