Predicting Suicidal Behavior Among Indian Adults Using Childhood Trauma, Mental Health Questionnaires and Machine Learning Cascade Ensembles - Research

Aug 3, 2026

Upload by Hazel

Among young adults, suicide remains a leading cause of death in India, motivating more accurate risk detection. Prior work suggests machine learning can forecast suicidal behavior from behavioral and mental-health signals, yet the Indian context has limited evaluation. This study develops multiple machine-learning models and cascade ensembles using childhood trauma, standardized mental health questionnaire measures, and related factors from 391 individuals. Cascade ensembles combining support vector machines, decision trees, and random forests achieved 95.04% accuracy. Findings support using these models to identify individuals with suicidal tendencies for targeted, efficient interventions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Suicide prevalence and risk factors in India

Role of machine learning in suicide prediction

Methods (implied)

Data source and questionnaire-based variables

Machine learning models and cascade ensembles

Results (implied)

Classification performance and accuracy

Discussion (implied)

Potential for targeted interventions

Predicting suicidal behavior among Indian adults using childhood trauma, mental health questionnaires and machine learning cascade ensembles Akash K Rao 1[0000-0003-4025-1042], Gunjan Y Trivedi2[0000-0003-4488-7945], Riri G Trivedi2[0000- 0001-5024-6103], Anshika Bajpai 1[0009-0007-4203-0581], Gajraj Singh Chauhan 1[0009-0000-7774-2887], Vishnu K Menon 1[0009-0007-9449-0934], Kathirvel Soundappan3[0000-0002-4839-0138], Hemalatha Ramani2[0009-0008-9513-8315], Neha Pandya2[0009-0005-5981-3764], Varun Dutt 1[0000-0002-2151-8314] 1 Applied Cognitive Science Laboratory, Indian Institute of Technology Mandi, Himachal Pradesh, India 2 Society for Energy and Emotions, Wellness Space LLP, Ahmedabad, India 3 Department of Community Medicine and School of Public Health, Post Graduate Institute of Medical Education and Research, Chandigarh, India [akashrao.iitmandi@gmail.com](akashrao.iitmandi@gmail.com) Abstract. Among young adults, suicide is India's leading cause of death, accounting for an alarming national suicide rate of around 16% . In recent years, machine learning algorithms have emerged to predict suicidal behavior using various behavioral traits. But to date, the efficacy of machine learning algorithms in predicting suicidal behavior in the Indian context has not been explored in literature. In this study, different machine learning algorithms and ensembles were developed to predict suicide behavior based on childhood trauma, different mental health parameters, and other behavioral factors. The dataset was acquired from 391 individuals from a wellness center in India. Information regarding their childhood trauma, psychological wellness, and other mental health issues was acquired through standardized questionnaires. Results revealed that cascade ensemble learning methods using support vector machine, decision trees, and random forest were able to classify suicidal behavior with an accuracy of 95.04% using data from childhood trauma and mental health questionnaires. The study highlights the potential of using these machine learning ensembles to identify individuals with suicidal tendencies so that targeted interventions could be provided efficiently. Keywords: Machine learning, childhood trauma, suicidal behavior, ensemble learning methods, Depression, Adverse childhood experiences. 1 Introduction Suicide is the most prevalent cause of death among the Indian population aged 15 to 49 [1] . India's proportion of worldwide suicide deaths rose among women from 25.3% in 1990 to 36.6% in 2016 and among men from 18.7% to 24.3%[1] . The research indicates that suicide is closely linked to mental health disorders (approximate- ly 90% of the individuals who commit suicide possess some mental health disorder, including psychiatric disorder, mood disorder, and substance use disorder, etc.) [3,7] . Suicide behavior (which includes suicidal thoughts and attempts) is defined as either having passive ideas about dying or an intention to kill oneself that is not accompanied by preparatory behavior. A recent systematic review found that mental disease increases the likelihood of suicide attempts tenfold [1] . To be effective at suicide prevention, it is vital to identify the risk factors. These risk factors include adverse childhood experiences (ACE), emotional abuse, a history of irrational decisions, inability to focus, and mental health issues [20-23] . Individuals who have undergone childhood trauma tend to have more mental and physical health issues, leading to a greater probability of suicide than individuals who have not undergone the trauma. Increased risk for suicide among those who experience child abuse or neglect has been reported in several meta‐analysis results and replicated in numerous studies comprising different types of samples [1] . As a result, an investigation into the association between ACE exposure throughout childhood and adult mental health is crucial, with a possible connection to suicidal behavio

FAQs

What data and measures are used to predict suicidal behavior in the study?

The study uses childhood trauma information and standardized mental health questionnaire parameters, along with other behavioral factors from 391 individuals.

Which modeling approach performed best for classifying suicidal behavior?

Cascade ensemble learning combining support vector machine, decision trees, and random forest achieved 95.04% accuracy.

How do the findings contribute to suicide prevention efforts?

The results suggest that machine learning ensembles can identify individuals with suicidal tendencies, enabling targeted interventions more efficiently.

Aug 3, 2026

Upload by Hazel