PREDICTION OF PATIENT’S WILLINGNESS FOR TREATMENT OF MENTAL ILLNESS USING MACHINE LEARNING APPROACHES - AI and ML classifiers for predicting treatment-seeking behavior

Q: What does the study aim to predict regarding mental illness?

The study predicts patient willingness to seek treatment for mental illness, supporting early identification of individuals more likely to seek care.

Q: Which dataset and sample size are used in the experiments?

The Open Sourcing Mental Illness (OSMI) dataset is used, containing 1259 samples for research and experimentation.

Q: Which machine learning classifiers show the highest accuracy in the results?

Random Forest and Gradient Boosting achieve the highest accuracy, with Random Forest at 0.81 and Gradient Boosting at 0.83. Other models show comparable but lower performance, including Logistic Regression at 0.8.

Aug 4, 2026

Upload by Hazel

Mental illness affects thoughts, emotions, and social interaction, and stigma can delay or reduce treatment-seeking. This study investigates how Artificial Intelligence and Machine Learning algorithms can predict individuals’ willingness to seek treatment, enabling earlier outreach and support from healthcare providers. Using the OSMI dataset with 1259 samples, the research evaluates classifiers including Random Forest, Gradient Boosting, SVM, KNN, and Logistic Regression, achieving the best accuracy with Random Forest (0.81) and Gradient Boosting (0.83).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

INTRODUCTION

Mental illness impact and stigma

Role of timely monitoring in mental well-being

Machine learning for improving treatment-seeking

Study aims and proposed predictive system

ABSTRACT AND METHODOLOGY OVERVIEW

Dataset and sample size

Classifiers evaluated

Model performance and conclusions

Submitted: 2024-03-15 | Revised: 2024-05-30 | Accepted: 2024-05-31 Keywords: Machine Learning, mental health prediction, treatment willingness, healthcare, predictive analysis Mohammed Chachan YOUNIS [0000-0002-9035-0738]* PREDICTION OF PATIENT’S WILLINGNESS FOR TREATMENT OF MENTAL ILLNESS USING MACHINE LEARNING APPROACHES Abstract Mental illness is a physical condition that significantly changes a person’s thoughts, emotions, and capacity to interact with others. The purpose of this study was to explore the application of Artificial Intelligence (AI) and Machine Learning (ML) algorithms in predicting behaviour regarding seeking treatment for mental illnesses, to support healthcare providers in reaching out to and supporting individuals more likely to seek treatment, leading to early detection, enhanced outcomes. The Open Sourcing Mental Illness (OSMI) dataset contains 1259 samples used for research and experiment. The study uses several classifiers (Random Forest, Gradient Boosting, SVM, KNN, and Logistic Regression) to take advantage on their unique capabilities and applicability for various parts of the prediction task. Experiments performed in Jupiter notebook and the major findings revealed varying levels of accuracy among the classifiers, with the Random Forest and 0.81 and Gradient Boosting classifiers 0.83 achieving highest accuracy, while the accuracy for SVM 0.82 and KNN 0.83 also give good result but Logistic Regression classifier had a lower accuracy 0.8. In conclusion, this research demonstrates the potential of AI and machine learning in predicting individual behaviour and offers valuable insights into mental health treatment-seeking behaviour. 1. INTRODUCTION The human brain is made up of millions of neurons which play an important part in both the body’s internal and external communication as well as in interpersonal contact with other people. Nevertheless, disturbances in neuron transmission can have an effect not only on the interior state of the individual, but also on their overall well-being. A person’s thoughts, feelings, and the ways in which they interact with other people are all severely impacted when that person has a mental illness. Mental diseases provide a huge worldwide health concern, affecting millions and having far-reaching social and economic consequences (Tanet al., 2024) . Regrettably, stigmas from society frequently encourage individuals to keep their mental health concerns a secret, which contributes to the widespread misunderstanding that doing so indicates a lack of personal integrity on their behalf with the result p < 0.05. The workforce in the scientific community is subjected to high stress due to long working * University of Mosul, Department of Computer Science, College of Computer Science and Mathematics, Iraq hours, and the strain of achieving deadlines, which contribute to the possibility of difficulties with mental health (Bijl et at., 1998) . When the far-reaching effects of mental illness on a society are considered, it becomes clear that innovative approaches to provide treatment and prevention are required, in order to detect the problem and act faster. An integral part of these efforts is timely monitoring an individual’s psychological well-being (Sun et al., 2010), which includes intellectual, psychological, and policy-related components and influences an individual’s thoughts, feelings, and responses in a wide range of situations. Anxiety, social phobia, sadness, obsessive compulsive disorder, addictions, and borderline personality disorder are only a few of the mental disorders that can be caused by a wide variety of psychological difficulties. It is essential to address mental health and encourage a desire to seek therapy across a wide range of demographic groupings, as anxiety and discontent are experiences that are common to all people regardless of their background. Machine learning models can help improve mental health treatment (Nova, 2023) . M

FAQs

What does the study aim to predict regarding mental illness?

The study predicts patient willingness to seek treatment for mental illness, supporting early identification of individuals more likely to seek care.

Which dataset and sample size are used in the experiments?

The Open Sourcing Mental Illness (OSMI) dataset is used, containing 1259 samples for research and experimentation.

Which machine learning classifiers show the highest accuracy in the results?

Random Forest and Gradient Boosting achieve the highest accuracy, with Random Forest at 0.81 and Gradient Boosting at 0.83. Other models show comparable but lower performance, including Logistic Regression at 0.8.

Aug 4, 2026

Upload by Hazel