Machine Learning-Enhanced Evaluation of Neuroleptics Efficacy and Management in Schizoaffective Disorder

Abstract

Rocco de Filippis and Abdullah Al Foysal

Background: Neuroleptics or antipsychotic medications are widely used in the treatment of various psychiatric disorders. However, they have been associated with the secondary development of obsessive-compulsive symptoms (OCS) in some patients. This case report examines two patients who developed obsessive-compulsive aspects secondary to neuroleptic treatment, analysed using visual data representations and machine learning.

Objective: To evaluate the development of OCS in patients treated with neuroleptics and to analyse their clinical outcomes using Y-BOCS and CGI-S scores, complemented by machine learning predictions.

Methods: Two patients treated with neuroleptics were assessed for the emergence of OCS using the Yale-Brown Obsessive Compulsive Scale (Y-BOCS) and Clinical Global Impression-Severity (CGI-S). Data were collected before and after the onset of OCS, and visualizations were employed to illustrate symptom progression and treatment effectiveness. Machine learning techniques were applied to predict OCS outcomes.

Results: Both patients developed significant OCS after the initiation of neuroleptic treatment. Their Y-BOCS and CGI-S scores increased, indicating the emergence and severity of OCS. Following treatment adjustments, both patients showed marked improvement in their scores. Machine learning models provided additional insights into the factors influencing OCS development.

Conclusion: These findings highlight the potential for neuroleptics to induce secondary OCS in patients, necessitating careful monitoring and management of these symptoms. Visual data analysis and machine learning provide powerful tools to understand and communicate these clinical changes.

PDF