Predicting Mental Health Outcomes: A Machine Learning Approach to Depression, Anxiety, and Stress

Abstract

Depression, anxiety, and stress are prevalent mental health disorders with profound effects on individuals and society. Early and accurate predictions of these conditions can significantly improve treatment outcomes. In this study, we applied three machine learning models—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest—to predict severity levels of these disorders based on Depression Anxiety Stress Scales (DASS) responses. Among the models, SVM demonstrated the highest performance, achieving 99% accuracy across all datasets, followed closely by Random Forest, particularly on the depression and stress datasets. These results highlight machine learning's potential in enhancing mental health diagnostics, with SVM proving the most effective for accurate classification.

References

[1] Howard LM, Khalifeh H. Perinatal mental health: a review of progress and challenges. World Psychiatry. 2020 Oct;19(3):313-27.

[2] Bertolote J. The roots of the concept of mental health. World psychiatry. 2008 Jun;7(2):113.

[3] Koutsimani P, Montgomery A, Georganta K. The relationship between burnout, depression, and anxiety: A systematic review and meta-analysis. Frontiers in psychology. 2019 Mar 13;10:284.

[4] Zadeh FS, Molani S, Orouskhani M, Rezaei M, Shafiei M, Abbasi H. Generative Adversarial Networks for Brain Images Synthesis: A Review. arXiv preprint arXiv:2305.15421. 2023 May 16.

[5] Yasaka K, Hatano S, Mizuki M, Okimoto N, Kubo T, Shibata E, Watadani T, Abe O. Effects of deep learning on radiologists’ and radiology residents’ performance in identifying esophageal cancer on CT. The British Journal of Radiology. 2023 Oct 1;96(1150):20220685.

[6] Liu C, Tian Y, Song Y. A systematic review of deep learning-based research on radiology report generation. arXiv preprint arXiv:2311.14199. 2023 Nov 23.

[7] Jiao T, Li F, Cui Y, Wang X, Li B, Shi F, Xia Y, Zhou Q, Zeng Q. Deep learning with an attention mechanism for differentiating the origin of brain metastasis using MR images. Journal of Magnetic Resonance Imaging. 2023 Nov;58(5):1624-35.

[8] Chen H, Kim S, Hardie JM, Thirumalaraju P, Gharpure S, Rostamian S, Udayakumar S, Lei Q, Cho G, Kanakasabapathy MK, Shafiee H. Deep learning-assisted sensitive detection of fentanyl using a bubbling-microchip. Lab on a Chip. 2022;22(23):4531-40.

[9] Degadwala S, Krishnamurthy VN, Vyas D. DeepSpine: Multi-Class Spine X-Ray Conditions Classification Using Deep Learning. In2024 3rd International Conference on Sentiment Analysis and Deep Learning (ICSADL) 2024 Mar 13 (pp. 8-13). IEEE.

[10] Ahmad A, Tariq A, Hussain HK, Gill AY. Revolutionizing Healthcare: How Deep Learning is poised to Change the Landscape of Medical Diagnosis and Treatment. Journal of Computer Networks, Architecture and High Performance Computing. 2023 Jul 11;5(2):458-71.

[11] Chen X. AI in Healthcare: Revolutionizing Diagnosis and Treatment through Machine Learning. MZ Journal of Artificial Intelligence. 2024 Jul 24;1(2).

[12] HaghighiKian SM, Shirinzadeh-Dastgiri A, Vakili-Ojarood M, Naseri A, Barahman M, Saberi A, Rahmani A, Shiri A, Masoudi A, Aghasipour M, Shahbazi A. A Holistic Approach to Implementing Artificial Intelligence in Lung Cancer. Indian Journal of Surgical Oncology. 2024 Sep 5:1-22.

[13] Abd Rahman R, Omar K, Noah SA, Danuri MS, Al-Garadi MA. Application of machine learning methods in mental health detection: a systematic review. Ieee Access. 2020 Oct 6;8:183952-64.

[14] Milne-Ives M, Selby E, Inkster B, Lam C, Meinert E. Artificial intelligence and machine learning in mobile apps for mental health: A scoping review. PLOS digital health. 2022 Aug 15;1(8):e0000079.

[15] Srividya M, Mohanavalli S, Bhalaji N. Behavioral modeling for mental health using machine learning algorithms. Journal of medical systems. 2018 May;42:1-2.

[16] Jain T, Jain A, Hada PS, Kumar H, Verma VK, Patni A. Machine learning techniques for prediction of mental health. In2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA) 2021 Sep 2 (pp. 1606-1613). IEEE.

[17] Gil M, Kim SS, Min EJ. Machine learning models for predicting risk of depression in Korean college students: identifying family and individual factors. Frontiers in Public Health. 2022 Nov 17;10:1023010.

[18] Qasrawi R, Polo SP, Al-Halawa DA, Hallaq S, Abdeen Z. Assessment and prediction of depression and anxiety risk factors in schoolchildren: machine learning techniques performance analysis. JMIR formative research. 2022 Aug 31;6(8):e32736.

[19] Li H, Li Y, Duan Y, Wang S, Liu M, Luo Y, Wang J, Chen Z, Yang P, Xie J. Risk factors for depression in China based on machine learning algorithms: A cross-sectional survey of 264,557 non-manual workers. Journal of Affective Disorders. 2024 Dec 15;367:617-22.

[20] Fiorini L, Cavallo F, Dario P, Eavis A, Caleb-Solly P. Unsupervised machine learning for developing personalised behaviour models using activity data. Sensors. 2017 May 4;17(5):1034.

[21] Boukhechba M, Baglione AN, Barnes LE. Leveraging mobile sensing and machine learning for personalized mental health care. Ergonomics in design. 2020 Oct;28(4):18-23.

[22] VENKATARAMANAIAH B, REDDY KG, RAMAKRISHNAN K, SATHISH M, RAJESH S. Real Time Mental Health Monitoring System using Machine Learning. In2024 Second International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI) 2024 Aug 28 (pp. 806-811). IEEE.

[23] https://www.kaggle.com/datasets/lucasgreenwell/depression-anxiety-stress-scales-responses/data

[24] https://medium.com/@roiyeho/random-forests-98892261dc49

[25] https://medium.com/@sachinsoni600517/k-nearest-neighbours-introduction-to-machine-learning-algorithms-9dbc9d9fb3b2