TITLE:
AI-Driven Mental Disorder Prediction: A Machine Learning Approach for Early Detection
AUTHORS:
Rocco de Filippis, Abdullah Al Foysal
KEYWORDS:
Mental Disorder Prediction, Machine Learning in Healthcare, Artificial Intelligence in Psychiatry, Early Detection of Mental Illnesses, AI-Driven Diagnosis, Predictive Modelling for Mental Health
JOURNAL NAME:
Open Access Library Journal,
Vol.12 No.4,
April
21,
2025
ABSTRACT: Mental disorders, including depression, bipolar disorder, and mood disorders, affect millions of individuals worldwide, significantly impacting their quality of life. Early and accurate diagnosis is essential for effective intervention, reducing the burden on healthcare systems, and improving patient outcomes. However, traditional diagnostic methods rely heavily on subjective assessments, self-reported symptoms, and clinical observations, which may lead to delays and inconsistencies in diagnosis. The integration of artificial intelligence (AI) and machine learning (ML) in mental health care has emerged as a promising solution to enhance predictive accuracy and provide early diagnosis. This study explores the application of ML algorithms to predict mental disorders using behavioral and psychological features. The dataset comprises attributes such as sadness, sleep disorders, mood swings, anxiety levels, and suicidal thoughts. We employ supervised learning techniques, including Decision Trees, Random Forest, Support Vector Machines (SVM), and Neural Networks, to classify individuals into four categories: Bipolar Type-1, Bipolar Type-2, Depression, and Normal. The dataset is pre-processed through feature selection, normalization, and handling missing values to improve model performance. Our experimental results demonstrate that AI-driven predictive models achieve high accuracy in identifying mental health conditions, with certain models outperforming traditional diagnostic approaches. The findings suggest that AI can significantly contribute to mental health assessment, providing a non-invasive and scalable solution for early detection. By integrating such models into digital health platforms, AI can assist mental health professionals in making informed decisions and offering timely interventions. Future research should focus on expanding datasets, incorporating multimodal data, and refining models to enhance generalizability across diverse populations. AI-driven mental healthcare solutions hold immense potential to revolutionize psychiatric diagnosis and personalized treatment planning.