Predictive Model for Anxiety Disorder

Anxiety disorders are among the most prevalent mental conditions globally, necessating advanced methodologies for early detention and intervention. This project explores the development of predictive models for anxiety disorders by integrating diverse data sources and advanced analytics techniques. By leveraging a bio-psychosocial. The study considers the interplay of biological, psychological and social factors contributing to anxiety. Utilizing machine learning algorithms, the project aims to identify key predictors and develop robust models that can accurately forecast the onset and progression of anxiety disorders. This study was carried out based on factors which are student academic performance, interpersonal relationship of the student, sleep pattern and financial stress that are likely causes of anxiety. Benson Idahosa University was used as a case study which comprises five (5) departments with one thousand (1000) population size and a total of two hundred final year student as sample size. The student comprises of male and female within the age of 16 to 30years. The study identified the mental health of the students through the administration of questionnaire. This research aims to enhance the early detection of anxiety disorders ultimately contributing to improved mental health outcomes. The findings underscore the potential of predictive modeling as a vital tool in mental health care, highlighting the importance of interdisciplinary approaches in addressing complex psychological conditions. Keywords: Anxiety, Disorder, Mental Health, Machine Learning, Algorithms, Predictive Model Journal Reference Format: Otaren Fredrick Enoma & Emmanuel Amarachi (2024): Predictive Model for Anxiety Disorder. Journal of Behavioural Informatics, Digital Humanities and Development Rese Vol. 10 No. 3. Pp 57-73. isteams.net dx.doi.org