Rural Depression Patients Judgment Model Based on Machine Learning

Mingjiu Yang

doi:10.62051/ijcsit.v4n3.49

Authors

Mingjiu Yang

DOI:

https://doi.org/10.62051/ijcsit.v4n3.49

Keywords:

Depression, Machine learning, Prediction

Abstract

Depression is a serious mental disorder. According to data released by the World Health Organization last year, there are approximately 300 million people suffering from depression worldwide. Due to the backwardness of medical care in rural areas and the low level of understanding of depression among residents, mental illness affects individuals in rural areas more seriously than in urban areas. However, with the development of artificial intelligence technology, related techniques such as machine learning have made initial gains in the field of depression determination and treatment. In this paper, based on a survey of data from Busara Center in Kenya, various machine learning methods such as K-NN, Naive Bayes methods, Support Vector Machine Classifier and Random Forest Classifier were used and evaluated for the most accurate model. The results show that Random Forest Classifier has the highest accuracy, at 0.794.

Downloads

Download data is not yet available.

References

[1] World Health Organization. (2023). Depressive disorder (depression). https://www.who.int/news-room/fact-sheets/detail/depression

[2] Rong, J., Ge, Y., Meng, N., Xie T., Ding H. Prevalence rate of depression in Chinese elderly from 2010 to 2019: a meta-analysis. Chinese Journal of Evidence-Based Medicine, 20(1), 26-31.

[3] Fu, X. et al. (2022). The mediation and interaction of depressive symptoms in activities of daily living and active aging in rural elderly: A cross-sectional survey. Frontiers in Public Health, 10, 942311.

[4] Xu, R., Liu, Y., Mu, T., Ye Y., Xu C. (2022). Determining the association between different living arrangements and depressive symptoms among over-65-year-old people: The moderating role of outdoor activities. Frontiers in Public Health, 10, 954416.

[5] Han, J., & Feng, L. (2020). Research progress on the application of artificial intelligence in the field of depression. Beijing Medicine, 42(4), 317-319+322. https://doi.org/10.15932/j.0253-9713.2020.04.013

[6] Yuan, G., Zhao, J., Zheng, D., Liu B. (2021). Study on distinguishing the severity of depression with Self-Rating Depression Scale and Beck Depression Inventory. Journal of Nervous and Mental Diseases and Mental Health, 21(12), 868-873.

[7] Xu, L. (2020). Research on depression recognition based on facial expression behavior patterns [Doctoral dissertation, Lanzhou University]. CNKI. https://doi.org/10.27204/d.cnki.glzhu.2020.000281

[8] Liu, D., Ye, J. Y., & Li, L. (2022). Feature extraction and implementation of depression based on machine learning. Experimental Technology and Management, 39(04), 153-157.

[9] Zhou, R., Zhu, G., Li, S., Duan, W., Li, J. (2024). Building domain lexicon oriented to behavioral features in depression. Big Data, 1-16.

[10] Cummins, N., Sethu, V., Epps, J., Schnieder, S., & Krajewski, J. (2015). Analysis of acoustic space variability in speech affected by depression. Speech Communication, 75, 27-49.

[11] Dogrucu, A., Perucic, A., Isaro, A., Ball, D., Toto, E., Rundensteiner, E. A., Agu, E., Davis-Martin, R., & Boudreaux, E. (2020). Moodable: On feasibility of instantaneous depression assessment using machine learning on voice samples with retrospectively harvested smartphone and social media data. Smart Health, 17, 100118.

[12] Stolicyn, A., Steele, J. D., & Seriès, P. (2022). Prediction of depression symptoms in individual subjects with face and eye movement tracking. Psychological Medicine, 52(9), 1784–1792.