Post-traumatic stress disorder (PTSD) prediction in Covid-19 survivors- A Clinical Questionnaire and Machine Learning Based Approach
Sheikh Afaan Farooq, A. M. Wani, Shehla Rafiq
Abstract
The Post-traumatic stress disorder (PTSD) can be denoted as a mental health issue which is caused due to the occurrence of a disturbing event, this event is either seen by a person or he has been involved in it. The Post-traumatic stress disorder (PTSD) is a psychological that disturbs the daily life of a person and halts his/her daily activities like job, work, study and much more. It also leads to other issues like depression, anxiety etc. The COVID-19 can be denoted as a transmissible disease that can harm the vital organs of a person and even cause death. However, the media hype of the disease being deadly has affected people psychologically more. Therefore, an onset of this disease in a person is a traumatic event and a person can get PTSD after he has beaten the disease. Thus, it is vital to detect the onset of PTSD early in a COVID-19 survivor to prevent any excessive health damage and allow for proper treatment of the patient. Machine learning methods have grown into a good alternative for analysis of health related data and also detection of health issues. In this research, we suggest a Machine learning based model to create a response-based classifier which utilizes a reduced questionnaire to detect the early onset of PTSD in a COVID-19 survivor. The questions are precisely based on the Diagnostic and Statistical Manual of Mental Disorders, fifth edition (DSM-5). In short, this research utilizes the answers given by a COVID-19 survivor to detect PTSD utilizing the decision tree (CART) classifier with an accuracy percentage of 97.4\%. The model is simple, computationally light and detects PTSD efficiently.