Suicidal Ideation Prediction Using Machine Learning

• Author(s): A Ayush Gowda; Abhiram P S; Hemashree D B; Keerthana R; S J Shaheena Begum
• Paper ID: 1712067
• Page: 1095-1100
• Published Date: 14-11-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 5 November-2025

Abstract

Suicide is become a major cause of death worldwide. With each year that goes by, the suicide rate rises dramatically. It is crucial to remember that suicidal thoughts is a complicated problem that cannot be exclusively linked to one mental illness or circumstance. According to reports, sadness, anxiety, high levels of stress, unsatisfying relationships, sleep difficulties, and physical or mental impairments are the main factors that contribute to suicidal ideation. Therefore, when forecasting suicidal ideation, a comprehensive approach that takes into account a number of indicators is crucial. Using a large sample of review data, our proposed work employs machine learning approaches to predict suicidal ideation. We preprocessed and trained the data using a variety of machine learning techniques after gathering it using a tagged dataset. Models like Decision Trees (DT), Support Vector Machines (SVM), Random Forest (RF), and Logistic Regression (LR). According to the results, LR has the highest accuracy of all the computed models (76%), followed by SVM (75%), MLP (74%), RF (74%), and DT (74%). The clinical industry and, consequently, the welfare of our society depend on the suggested framework. Index Terms: depression, anxiety, machine learning, suicidal thoughts, and drowsiness

Citations

IRE Journals:
A Ayush Gowda, Abhiram P S, Hemashree D B, Keerthana R, S J Shaheena Begum "Suicidal Ideation Prediction Using Machine Learning" Iconic Research And Engineering Journals Volume 9 Issue 5 2025 Page 1095-1100 https://doi.org/10.64388/IREV9I5-1712067

IEEE:
A Ayush Gowda, Abhiram P S, Hemashree D B, Keerthana R, S J Shaheena Begum "Suicidal Ideation Prediction Using Machine Learning" Iconic Research And Engineering Journals, 9(5) https://doi.org/10.64388/IREV9I5-1712067