Title: Suicidal behaviour screening using machine learning techniques

Authors: Anju Bhandari Gandhi; Devendra Prasad; Umesh Kumar Lilhore; Deepak Kumar Verma; Sarita Simaiya

Addresses: Panipat Institute of Engineering and Technology, Samalkha, Panipat, Haryana, India ' Panipat Institute of Engineering and Technology, Samalkha, Panipat, Haryana, India ' Department of Computer Science and Engineering, Chandigarh University, Gharuan Mohali, Punjab, India ' Chhatrapati Shahu Ji Maharaj University, Kalyanpur, Kanpur Uttar Pradesh, India ' Apex Institute of Technology (CSE), Chandigarh University, Gharuan Mohali, Punjab 140413, India

Abstract: In a fast-growing world, patients of anxiety and depression are more vulnerable to attempt an obnoxious step like suicide. Therefore periodic screening of these patients can be done for their wellbeing as well as to stop the negative flow of energy. We aimed to explore the potential of machine learning to identify and predict suicidal behaviour in patients with anxiety and stress by comparing the performance of machine learning algorithms (logistic regression, random forest, decision tree and multi-layer perceptron classifier). The analysis is performed using a python programming language for the screening of patients aiming to predict the risk of suicides. Random forest classifier outperforms with an accuracy of 95%. This current research work leverages the application of machine learning in the domain of the healthcare sector in the automated screening of patients. This artificial intelligence based solution reduces time consumption. This present kind of analysis can affect a remarkable monitoring system for healthcare departments.

Keywords: machine learning; suicidal features; algorithm; depression; counselling.

DOI: 10.1504/IJBET.2023.129191

International Journal of Biomedical Engineering and Technology, 2023 Vol.41 No.2, pp.111 - 125

Received: 03 Aug 2020
Accepted: 21 Dec 2020

Published online: 01 Mar 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article