Machine Learning-Enabled Analysis for Obsessive-Compulsive Disorder Drug Development
DOI:
https://doi.org/10.62643/Keywords:
Obsessive-Compulsive Disorder, Medication Research, Ensemble Learning, Voting Classifier, Random Forest, Support Vector Machine, Gradient Boosting, Severity Prediction, Mental Health AnalyticsAbstract
Obsessive-Compulsive Disorder (OCD) is a complex mental health condition that requires
accurate assessment and effective medication strategies to improve patient outcomes. Traditional
methods of diagnosis and treatment planning often lack consistency and personalization, leading
to suboptimal care. This study aims to develop a machine learning-based approach to support
OCD medication research by predicting the severity levels of the disorder using clinical and
demographic data. The existing system utilizes the Random Forest algorithm for classification
due to its robustness and ability to handle high-dimensional data. The proposed system enhances
prediction performance by employing a Voting Classifier that combines Random Forest, Support
Vector Machine (SVM), and Gradient Boosting algorithms using a soft voting mechanism. The
dataset is preprocessed through encoding, feature selection, and normalization to improve model
efficiency. Experimental results demonstrate that the proposed ensemble model achieves higher
accuracy compared to the standalone Random Forest model, which achieves low accuracy. The
improved performance highlights the effectiveness of combining multiple models to capture
complex patterns in OCD-related data. This approach not only enhances prediction accuracy but
also supports clinicians in making informed decisions regarding treatment and medication
planning, ultimately contributing to more personalized and effective mental healthcare solutions
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













