Machine Learning Approaches to Workplace Mental Health - Predicting Treatment-Seeking Behavior Using the OSMI Dataset - paper

Aug 3, 2026

Workplace mental health increasingly underpins sustainable organizational performance, especially in technology settings where work intensity and psychological strain are common. This study applies machine learning to the Open Sourcing Mental Illness (OSMI) dataset, using 1,387 anonymized responses from the 2014 OSMI survey. After data cleaning and encoding, it identifies key predictors of treatment-seeking behavior, including family history of mental illness and work interference caused by psychological distress. Decision Tree and KNN are evaluated, with accuracy results of 73% and 100%. Findings support AI-enabled analytics for early intervention and guide future work on larger datasets and explainable AI for interpretability, fairness, and trust.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

I. Introduction

II. Methods

Dataset: OSMI

Preprocessing and Feature Encoding

Models: Decision Tree and KNN

III. Results

Prediction Accuracy

IV. Discussion and Future Work

Article Machine Learning Approaches to Workplace Mental Health: Predicting Treatment-Seeking Behavior Using the OSMI Dataset Nor Aishah Othman1, Mariana Rosdi2 1 Politeknik Sultan Haji Ahmad Shah, Electronic Engineering, Kuantan, Malaysia 2 Politeknik Sultan Salahuddin AbdulAziz Shah, Electronic Engineering, Shah Alam, Malaysia | SUBMISSION TRACK | A B S T R A C T | | --- | --- | Recieved: 12, 25, 2025 Final Revision: 01, 13, 2026 Available Online: 02, 02, 2026 KEYWORD Workplace Mental Health, Predictive Analytics, Machine Learning, K-Nearest Neighbour, Explainable AI CORRESPONDENCE E-mail: [noraishah.othman@polisas.edu.my](noraishah.othman@polisas.edu.my)[ ](noraishah.othman@polisas.edu.my)[mariana@psa.edu.my](mariana@psa.edu.my) Employee mental health is increasingly recognized as essential for sustainable organizational performance, particularly in technology sectors where work intensity and psychological strain are prevalent. This study leverages machine learning to identify predictors of treatment-seeking behavior using the Open Sourcing Mental Illness (OSMI) dataset, which includes 1,387 anonymized responses from the 2014 OSMI survey. The survey examines employees’ experiences and perceptions of mental health in the global tech industry. Through data cleaning and encoding, key factors influencing helpseeking behavior were identified, including family history of mental illness and work interference due to psychological distress. Two machine learning models, Decision Tree and K-Nearest Neighbour (KNN), were employed for prediction. The Decision Tree model achieved an accuracy of 73%, while KNN attained 100%, suggesting high predictive power, albeit with potential overfitting risks. These findings align with recent studies promoting the integration of AI-driven analytics in workplace wellness programs to detect hidden behavioral trends and enable early interventions. The results demonstrate that machine learning models can offer valuable insights into employee well-being and preventative strategies. Future research should focus on incorporating larger, more diverse datasets and adopting explainable AI (XAI) techniques to enhance interpretability, fairness, and trust in predictive systems for mental health in the workplace. I. INTRODUCTION Workplace mental health is increasingly acknowledged as a critical determinant of both individual well-being and organizational success [1], [2], [3] . It plays a significant role in influencing employees’ cognitive abilities, decision-making, and overall productivity, which are crucial for fostering sustainable organizational growth. Mental health challenges, such as stress, anxiety, and depression, can severely impair an employee's performance, leading to higher absenteeism, burnout, and reduced job satisfaction. Given the increasing demand for efficiency and the evolving nature of work environments, addressing mental health in the workplace has become paramount. The World Health Organization (WHO) highlights that mental health is an essential aspect of overall health, emphasizing its importance in achieving organizational and societal wellbeing [4] . In sectors like technology, employees often face additional pressures due to long working hours, tight deadlines, and job insecurity, which can heighten the risk of mental health issues [5] . Despite the growing recognition of the importance of mental health in the workplace, significant barriers remain in addressing these challenges. Stigma surrounding mental health continues to prevent many employees from seeking help, with fears of judgment or negative consequences. Moreover, limited resources and unequal access to mental health care exacerbate these issues, creating disparities in support for employees facing psychological distress [6], [7] . These barriers contribute to underutilization of mental health services in many organizations, hindering efforts to create a supportive and inclusive work environ

FAQs

What dataset is used to predict treatment-seeking behavior in workplace mental health?

The study uses the Open Sourcing Mental Illness (OSMI) dataset, which contains 1,387 anonymized responses from the 2014 OSMI survey.

Which factors were identified as key predictors of help-seeking behavior?

Key predictors include family history of mental illness and work interference due to psychological distress.

How did the Decision Tree and KNN models perform?

The Decision Tree model achieved 73% accuracy, while KNN attained 100%, indicating strong predictive power with a noted potential overfitting risk for KNN.

Aug 3, 2026

Upload by Valentina