Support vector machine for predicting anxiety in chemical dependency rehabilitation patients
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1333Keywords:
Anxiety, Dependences, Chemical, Machine LearningAbstract
Objective: Relate clinical variables of inpatients in chemical rehabilitation to anxiety, using the machine learning method. Method: A field study conducted in a Therapeutic Community, considering data from 25 inpatients. Among the parameters are the psychoactive substances of dependence, duration of use and abstinence, age, and the GAD-7 questionnaire. The algorithm used was the Support Vector Machine (SVM). The performance analysis metrics were the confusion matrix and AUC. Results: The prevalence of rehabilitation for cocaine or crack was 92% of the inpatients, followed by alcohol at 76%. The highest metrics were an accuracy of 68%, sensitivity of 89%, specificity of 88%, F1 score of 59%, and AUC of 0.91. Conclusion: The SVM algorithm proved to be promising for use in predicting anxiety in inpatients undergoing recovery from psychoactive substances.
References
Atendimento a pessoas com transtornos mentais por uso de álcool e drogas aumenta 12% no SUS [Internet]. Ministério da Saúde. 2022.
de Matos MB, de Mola CL, Trettim JP, Jansen K, da Silva RA, Souza LD de M, et al. Psychoactive substance abuse and dependence and its association with anxiety disorders: a population-based study of young adults in Brazil. Revista Brasileira de Psiquiatria. 2018 Feb 15;40(4):349–53. DOI: https://doi.org/10.1590/1516-4446-2017-2258
Soraya S, Mahdavi M, Saeidi M, Seddigh R, Nooraeen S, Sadri M, et al. Prevalence of anxiety disorders and its co-occurrence with substance use disorder: a clinical study. Middle East Current Psychiatry. 2022 Apr 20;29(1). DOI: https://doi.org/10.1186/s43045-022-00197-x
Chhetri B, Goyal LM, Mittal M. How machine learning is used to study addiction in digital healthcare: A systematic review. International Journal of Information Management Data Insights. 2023 Nov;3(2):100175. DOI: https://doi.org/10.1016/j.jjimei.2023.100175
Albagmi, Faisal Mashel, et al. Prediction of generalized anxiety levels during the Covid-19 pandemic: A machine learning-based modeling approach. Informatics in Medicine Unlocked. 28 (2022): 100854. DOI: https://doi.org/10.1016/j.imu.2022.100854
Pintelas EG, Kotsilieris T, Livieris IE, Pintelas P. A review of machine learning prediction methods for anxiety disorders. Proceedings of the 8th International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion. 2018 Jun 20; DOI: https://doi.org/10.1145/3218585.3218587
Castro RA de, Ruas RN, Abreu RC, Rocha RB, Ferreira R de F, Lasmar RC, et al. Crack: pharmacokinetics, pharmacodynamics, and clinical and toxic effects. Revista Médica de Minas Gerais [Internet]. 2015;25(2). Available from: http://rmmg.org/exportar-pdf/1782/v25n2a17.pdf DOI: https://doi.org/10.5935/2238-3182.20150045
Spitzer R, Kroenke K, Williams J, Löwe B. A Brief Measure for Assessing Generalized Anxiety Disorder: The GAD-7 [Internet]. Archives of internal medicine. 2006. Available from: https://pubmed.ncbi.nlm.nih.gov/16717171/ DOI: https://doi.org/10.1001/archinte.166.10.1092
de Amorim LBV, Cavalcanti GDC, Cruz RMO. The choice of scaling technique matters for classification performance. Applied Soft Computing [Internet]. 2023 Jan;133:109924. Available from: https://arxiv.org/pdf/2212.12343 DOI: https://doi.org/10.1016/j.asoc.2022.109924
Brereton RG, Lloyd GR. Support Vector Machines for classification and regression. The Analyst. 2010;135(2):230–67. DOI: https://doi.org/10.1039/B918972F
Li Y, Cui Z, Liao Q, Dong H, Zhang J, Shen W, et al. Support vector machine‐based multivariate pattern classification of methamphetamine dependence using arterial spin labeling. Addiction Biology. 2019 Jan 9;24(6):1254–62. DOI: https://doi.org/10.1111/adb.12705
Yang L, Shami A. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing. 2020 Nov;415:295–316. DOI: https://doi.org/10.1016/j.neucom.2020.07.061
King RD, Orhobor OI, Taylor CC. Cross-validation is safe to use. Nature Machine Intelligence [Internet]. 2021 Apr 1;3(4):276–6. Available from: https://www.nature.com/articles/s42256-021-00332-z DOI: https://doi.org/10.1038/s42256-021-00332-z
Rocha J de L, Salles EOT, Andreão RV. Detecção da Apneia Obstrutiva do Sono Através da Variabilidade da Frequência Cardíaca. J Health Inform [Internet]. 20º de julho de 2023 [citado 27º de maio de 2024];15(Especial). Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1084 DOI: https://doi.org/10.59681/2175-4411.v15.iEspecial.2023.1084
Yates LA, Aandahl Z, Richards SA, Brook BW. Cross validation for model selection: a review with examples from ecology. Ecological Monographs. 2022 Nov 13;93(1). DOI: https://doi.org/10.1002/ecm.1557
Marzban C. The ROC Curve and the Area under It as Performance Measures. Weather and Forecasting. 2004 Dec;19(6):1106–14. DOI: https://doi.org/10.1175/825.1
Hicks SA, Strümke I, Thambawita V, Hammou M, Riegler MA, Halvorsen P, et al. On evaluation metrics for medical applications of artificial intelligence. Scientific Reports [Internet]. 2022 Apr 8;12(1):5979. Available from: https://www.nature.com/articles/s41598-022-09954-8 DOI: https://doi.org/10.1038/s41598-022-09954-8
Tabares T, Vélez Álvarez, Consuelo, Salcedo B, Murillo Rendón, Santiago. Anxiety in Young People: Analysis from a Machine Learning Model. 2024 Jan 1 [cited 2024 May 27]; Available from: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4791415
Sau A, Bhakta I. Screening of anxiety and depression among seafarers using machine learning technology. Informatics in Medicine Unlocked. 2019;16:100228. DOI: https://doi.org/10.1016/j.imu.2019.100228
Park SJ, Lee SJ, Kim H, Kim JK, Chun JW, Lee SJ, et al. Machine learning prediction of dropping out of outpatients with alcohol use disorders. Le KNQ, editor. PLOS ONE. 2021 Aug 2;16(8):e0255626. DOI: https://doi.org/10.1371/journal.pone.0255626
Back SE, Brady KT. Anxiety Disorders with Comorbid Substance Use Disorders: Diagnostic and Treatment Considerations. Psychiatric Annals. 2008 Nov 1;38(11):724–9. DOI: https://doi.org/10.3928/00485713-20081101-01
Smith JP, Book SW. Anxiety and Substance Use Disorders: A Review. The Psychiatric times [Internet]. 2008;25(10):19–23. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2904966/
Gimeno C, Dorado ML, Roncero C, Szerman N, Vega P, Balanzá-Martínez V, et al. Treatment of Comorbid Alcohol Dependence and Anxiety Disorder: Review of the Scientific Evidence and Recommendations for Treatment. Frontiers in Psychiatry [Internet]. 2017 Sep 22;8(173). Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5614930/ DOI: https://doi.org/10.3389/fpsyt.2017.00173
Kampman KM. New Medications for the Treatment of Cocaine Dependence. Psychiatry (Edgmont) [Internet]. 2005 Dec 1;2(12):44–8. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2994240/
Schwartz EKC, Wolkowicz NR, De Aquino JP, MacLean RR, Sofuoglu M. Cocaine Use Disorder (CUD): Current Clinical Perspectives. Substance Abuse and Rehabilitation. 2022 Sep;Volume 13:25–46. DOI: https://doi.org/10.2147/SAR.S337338
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
