Article Per Year (5 Year)
p-Index From 2021 - 2026
1.503
P-Index
This Author published in this journals
All Journal Lisan An Nathiq : Jurnal Bahasa dan Pendidikan Bahasa Arab Al Ibtidaiyah: Jurnal Pendidikan Guru Madrasah Ibtidaiyah Jurnal Pendidikan Terapan Vokatek : Jurnal Pengabdian Masyarakat Information Technology Education Journal Journal of Vocational, Informatics and Computer Education Edukasi Elita : Jurnal Inovasi Pendidikan
Nur Fakhrunnisaa
Unknown Affiliation
Humanities Computer Science & IT Education Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Information Technology Education Journal

 1 
Predicting Mental Health Disorders Using Machine Learning and Symptom-Based Behavioral Features Marwan Ramdhany Edy; Nur Fakhrunnisaa
Information Technology Education Journal Vol. 4, No. 1, February (2025)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v4i1.7156

Abstract

Mental health disorders, such as anxiety and depression, represent significant challenges in today's fast-paced world. Traditional methods of diagnosing and managing these conditions often fall short, leading to a growing interest in leveraging technology for better mental health outcomes. This paper explored the potential of using machine learning algorithms applied to psychological symptom data to enhance the prognosis of mental disorders. A dataset comprising 120 psychology patients with 17 essential symptoms used to diagnose Mania Bipolar Disorder, Depressive Bipolar Disorder, Major Depressive Disorder, and non-disordered participants was analyzed. The study evaluated the performance of various machine learning models, including RandomForestClassifier, ExtraTreesClassifier, XGBClassifier, LGBMClassifier, and CatBoostClassifier, using metrics such as precision and recall. ExtraTreesClassifier achieved the highest test accuracy of 0.8889, followed by RandomForestClassifier and LGBMClassifier with 0.8611, CatBoostClassifier with 0.8333, and XGBClassifier with 0.7222. Key predictors of mental health outcomes included "Mood_Swing_YES," "Optimism," and "Sexual_Activity." These findings suggest that integrating psychological symptom data with machine learning significantly improves the accuracy of mental health disorder prognosis, offering a promising avenue for more proactive and personalized mental health care. This research demonstrates the practical applicability of machine learning for personalized early detection and intervention in mental healthcare.
Co-Authors Andi Arif Pamessangi Edy, Marwan Ramdhany Fauziah Zainudin Hikmah Isnaini Indah Safitri M Arief Marwan Ramdhany Edy Mawardi Muhammad Yamin Nilam Permatasari Munir Nurul In Puput Putri Sintia Sucianti Umrah Sikki