An intelligent framework to measure the effects of COVID-19 on the mental health of medical staff

• Published in: PloS one Vol. 18; no. 6; p. e0286155
• Main Authors: Irfan, Muhammad, Shaf, Ahmad, Ali, Tariq, Zafar, Maryam, Rahman, Saifur, I Hendi, Meiaad Ali, M Baeshen, Shatha Abduh, Maghfouri, Maryam Mohammed Mastoor, Alahmari, Hailah Saeed Mohammed, Shahhar, Ftimah Ahmed Ibrahim, Shahhar, Nujud Ahmed Ibrahim, Halawi, Amnah Sultan, Mahnashi, Fatima Hussen, Alqhtani, Samar M, Ali M, Bahran Taghreed
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 08-06-2023; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Anxiety; Anxiety - epidemiology; Anxiety - psychology; Biology and Life Sciences; Care and treatment; Computer and Information Sciences; Coronaviruses; COVID-19; COVID-19 - epidemiology; COVID-19 - psychology; Data mining; Datasets; Decision trees; Depression, Mental; Emergency medical care; Epidemics; Health care; Health Personnel - psychology; Humans; Learning algorithms; Machine learning; Medical personnel; Medical research; Medical Staff; Medicine and Health Sciences; Medicine, Experimental; Mental depression; Mental Health; Nurses; Pandemics; People and Places; Pest outbreaks; Physical Sciences; Polls & surveys; Post traumatic stress disorder; Professionals; Psychological aspects; Psychological effects; Research and Analysis Methods; Respiratory diseases; SARS-CoV-2; Sleep disorders; Social Sciences; Surveys; Tertiary; Well being; Saudi Arabia; Italy; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0286155

The mental and physical well-being of healthcare workers is being affected by global COVID-19. The pandemic has impacted the mental health of medical staff in numerous ways. However, most studies have examined sleep disorders, depression, anxiety, and post-traumatic problems in healthcare workers during and after the outbreak. The study's objective is to evaluate COVID-19's psychological effects on healthcare professionals of Saudi Arabia. Healthcare professionals from tertiary teaching hospitals were invited to participate in the survey. Almost 610 people participated in the survey, of whom 74.3% were female, and 25.7% were male. The survey included the ratio of Saudi and non-Saudi participants. The study has utilized multiple machine learning algorithms and techniques such as Decision Tree (DT), Random Forest (RF), K Nearest Neighbor (KNN), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The machine learning models offer 99% accuracy for the credentials added to the dataset. The dataset covers several aspects of medical workers, such as profession, working area, years of experience, nationalities, and sleeping patterns. The study concluded that most of the participants who belonged to the medical department faced varying degrees of anxiety and depression. The results reveal considerable rates of anxiety and depression in Saudi frontline workers.