Predicting the Risk of Developing Mental Health Disorders from Injuries with Machine Learning Algorithms

Abstract

Injuries-particularly long-term or permanent ones can significantly impact an individual's overall well-being, affecting both physical and mental health. While the physical consequences are often well-documented, the psychological and emotional effects remain less explored. Individuals who experience trauma may be at increased risk of developing mental health disorders such as anxiety, depression, or post-traumatic stress disorder (PTSD), often requiring ongoing psychological care. However, identifying which types of injuries pose the greatest risk for mental health complications remains a complex challenge. This research employs machine learning and artificial intelligence techniques to analyze the correlation between various injury types and the likelihood of developing mental health conditions. It also examines how socioeconomic factors—such as gender, education, and employment status—interact with these injuries to influence psychological outcomes. Results show that traumatic injuries like severed limbs and missing body parts are strongly associated with a higher risk of emotional and psychological disorders. Furthermore, factors such as being female, having a lower education level, or engaging in physically demanding jobs were also linked to increased vulnerability. The logistic regression model emerged as the most accurate predictive tool, achieving a performance of 69.55%, suggesting that machine learning can be a viable method for assessing mental health risk following injury. These findings highlight the importance of not only addressing the physical aftermath of trauma but also integrating mental health evaluations into post-injury care.

Ähnliche Arbeiten