Hostname: page-component-8448b6f56d-c47g7 Total loading time: 0 Render date: 2024-04-24T11:58:47.161Z Has data issue: false hasContentIssue false

Prediction of depression cases, incidence, and chronicity in a large occupational cohort using machine learning techniques: an analysis of the ELSA-Brasil study

Published online by Cambridge University Press:  04 June 2020

Diego Librenza-Garcia
Affiliation:
Laboratory of Molecular Psychiatry, Hospital de Clínicas de Porto Alegre, Porto Alegre, Brazil Programa de Pós-Graduação em Psiquiatria e Ciências do Comportamento, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, Canada
Ives Cavalcante Passos
Affiliation:
Laboratory of Molecular Psychiatry, Hospital de Clínicas de Porto Alegre, Porto Alegre, Brazil Programa de Pós-Graduação em Psiquiatria e Ciências do Comportamento, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
Jacson Gabriel Feiten
Affiliation:
Laboratory of Molecular Psychiatry, Hospital de Clínicas de Porto Alegre, Porto Alegre, Brazil Programa de Pós-Graduação em Psiquiatria e Ciências do Comportamento, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
Paulo A. Lotufo
Affiliation:
Department of Internal Medicine, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil Hospital Universitário, Universidade de São Paulo, São Paulo, Brazil
Alessandra C. Goulart
Affiliation:
Department of Internal Medicine, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil Hospital Universitário, Universidade de São Paulo, São Paulo, Brazil
Itamar de Souza Santos
Affiliation:
Department of Internal Medicine, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil Hospital Universitário, Universidade de São Paulo, São Paulo, Brazil
Maria Carmen Viana
Affiliation:
Department of Social Medicine, Postgraduate Program in Public Health, Center of Psychiatric Epidemiology (CEPEP), Federal University of Espírito Santo, Vitória, Brazil
Isabela M. Benseñor
Affiliation:
Department of Internal Medicine, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil Hospital Universitário, Universidade de São Paulo, São Paulo, Brazil
Andre Russowsky Brunoni*
Affiliation:
Department of Internal Medicine, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil Hospital Universitário, Universidade de São Paulo, São Paulo, Brazil Laboratory of Neurosciences (LIM-27), Department and Institute of Psychiatry, Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil
*
Author for correspondence: Andre Russowsky Brunoni, E-mail: brunoni@usp.br

Abstract

Abstract

Background

Depression is highly prevalent and marked by a chronic and recurrent course. Despite being a major cause of disability worldwide, little is known regarding the determinants of its heterogeneous course. Machine learning techniques present an opportunity to develop tools to predict diagnosis and prognosis at an individual level.

Methods

We examined baseline (2008–2010) and follow-up (2012–2014) data of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), a large occupational cohort study. We implemented an elastic net regularization analysis with a 10-fold cross-validation procedure using socioeconomic and clinical factors as predictors to distinguish at follow-up: (1) depressed from non-depressed participants, (2) participants with incident depression from those who did not develop depression, and (3) participants with chronic (persistent or recurrent) depression from those without depression.

Results

We assessed 15 105 and 13 922 participants at waves 1 and 2, respectively. The elastic net regularization model distinguished outcome levels in the test dataset with an area under the curve of 0.79 (95% CI 0.76–0.82), 0.71 (95% CI 0.66–0.77), 0.90 (95% CI 0.86–0.95) for analyses 1, 2, and 3, respectively.

Conclusions

Diagnosis and prognosis related to depression can be predicted at an individual subject level by integrating low-cost variables, such as demographic and clinical data. Future studies should assess longer follow-up periods and combine biological predictors, such as genetics and blood biomarkers, to build more accurate tools to predict depression course.

Type
Original Article
Copyright
Copyright © The Author(s), 2020. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Andersson, N., Gustafsson, L., Okkels, N., Taha, F., Cole, S., Munk-Jørgensen, P., & Goodwin, R. (2015). Depression and the risk of autoimmune disease: A nationally representative, prospective longitudinal study. Psychological Medicine, 45(16), 35593569. doi: 10.1017/S0033291715001488.CrossRefGoogle ScholarPubMed
Andrews, G. (2008). Reducing the burden of depression. The Canadian Journal of Psychiatry, 53, 420427.CrossRefGoogle ScholarPubMed
Aquino, E. M. L., Barreto, S. M., Bensenor, I. M., Carvalho, M. S., Chor, D., Duncan, B. B., … Szklo, M. (2012). Brazilian Longitudinal Study of Adult Health (ELSA-Brasil): Objectives and design. American Journal of Epidemiology, 175, 315324.CrossRefGoogle ScholarPubMed
Beard, J. R., Tracy, M., Vlahov, D., & Galea, S. (2008). Trajectory and socioeconomic predictors of depression in a prospective study of residents of New York City. Annals of Epidemiology, 18, 235243.CrossRefGoogle Scholar
Berk, R. A. (2016). Statistical learning from a regression perspective. Springer International Publishing / Springer Nature Switzerland AG.CrossRefGoogle Scholar
Bostwick, J. M., & Pankratz, V. S. (2000). Reviews and overviews affective disorders and suicide risk: A reexamination. American Journal of Psychiatry, 157, 19251932.CrossRefGoogle Scholar
Brenes, G. A. (2007). Anxiety, depression, and quality of life in primary care patients. Primary Care Companion to the Journal of Clinical Psychiatry, 9, 437443.CrossRefGoogle ScholarPubMed
Brodersen, K. H., Ong, C. S., Stephan, K. E., & Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. 20th International Conference on Pattern Recognition, pp. 3121–3124. IEEE.CrossRefGoogle Scholar
Brown, L. C., Majumdar, S. R., Newman, S. C., & Johnson, J. A. (2005). History of depression increases risk of type 2 diabetes in younger adults. Diabetes Care, 28, 10631067.CrossRefGoogle ScholarPubMed
Brunoni, A. R., Nunes, M. A., Figueiredo, R., Barreto, S. M., da Fonseca, M. d. J., Lotufo, P. A., & Benseñor, I. M. (2013). Patterns of benzodiazepine and antidepressant use among middle-aged adults. The Brazilian longitudinal study of adult health (ELSA-Brasil). Journal of Affective Disorders, 151, 7177.CrossRefGoogle Scholar
Brunoni, A. R., Santos, I. S., Passos, I. C., Goulart, A. C., Koyanagi, A., Carvalho, A. F., … Benseñor, I. M. (2020). Socio-demographic and psychiatric risk factors in incident and persistent depression: An analysis in the occupational cohort of ELSA-Brasil. Journal of Affective Disorders, 263, 252257.CrossRefGoogle ScholarPubMed
Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, 249259. doi: 10.1016/j.neunet.2018.07.011.CrossRefGoogle ScholarPubMed
Bzdok, D., Altman, N., & Krzywinski, M. (2018). Statistics versus machine learning. Nature Methods, 15, 233234.CrossRefGoogle ScholarPubMed
Chor, D., de Alves, M. G., Giatti, L., Cade, N. V., Nunes, M. A., del Molina, M. C. B., … de Oliveira, L. C. (2013). Questionnaire development in ELSA-Brasil: Challenges of a multidimensional instrument. Revista de Saúde Pública, 47, 2736.CrossRefGoogle ScholarPubMed
Das-Munshi, J., Castro-Costa, E., Dewey, M. E., Nazroo, J., & Prince, M. (2014). Cross-cultural factorial validation of the Clinical Interview Schedule-Revised (CIS-R); findings from a nationally representative survey (EMPIRIC). International Journal of Methods in Psychiatric Research, 23, 229244.CrossRefGoogle Scholar
Dwyer, D. B., Falkai, P., & Koutsouleris, N. (2018). Machine learning approaches for clinical psychology and psychiatry. Annual Review of Clinical Psychology, 14, 91118.CrossRefGoogle ScholarPubMed
Gan, Y., Gong, Y., Tong, X., Sun, H., Cong, Y., Dong, X., … Lu, Z. (2014). Depression and the risk of coronary heart disease: A meta-analysis of prospective cohort studies. BMC Psychiatry, 14, 371. doi: 10.1186/s12888-014-0371-z.CrossRefGoogle ScholarPubMed
Goodwin, R. D., & Gorman, J. M. (2002). Psychopharmacologic treatment of generalized anxiety disorder and the risk of major depression. American Journal of Psychiatry, 159, 19351937.CrossRefGoogle ScholarPubMed
Head, J., Stansfeld, S. A., Ebmeier, K. P., Geddes, J. R., Allan, C. L., Lewis, G., & Kivimäki, M. (2013). Use of self-administered instruments to assess psychiatric disorders in older people: Validity of the General Health Questionnaire, the Center for Epidemiologic Studies Depression Scale and the self-completion version of the revised Clinical Interview Sch. Psychological Medicine, 43, 26492656.CrossRefGoogle Scholar
Jacobson, N. C., & Newman, M. G. (2017). Anxiety and depression as bidirectional risk factors for one another: A meta-analysis of longitudinal studies. Psychological Bulletin, 143, 11551200.CrossRefGoogle ScholarPubMed
Kessler, R. C. (2012). The costs of depression. Psychiatric Clinics of North America, 35, 114.CrossRefGoogle ScholarPubMed
Kuehner, C. (2003). Gender differences in unipolar depression: An update of epidemiological findings and possible explanations. Acta Psychiatrica Scandinavica, 108, 163174.CrossRefGoogle ScholarPubMed
Kupfer, D. J., Frank, E., & Phillips, M. L. (2012). Major depressive disorder: New clinical, neurobiological, and treatment perspectives. The Lancet, 379, 10451055.CrossRefGoogle ScholarPubMed
Lépine, J. P., & Briley, M. (2011). The increasing burden of depression. Neuropsychiatric Disease and Treatment, 7(Suppl 1), 37. doi: 10.2147/NDT.S19617.Google ScholarPubMed
Lewis, G., Pelosi, A. J., Araya, R., & Dunn, G. (1992). Measuring psychiatric disorder in the community: A standardized assessment for use by lay interviewers. Psychological Medicine, 22, 465486.CrossRefGoogle ScholarPubMed
Luque, A., Carrasco, A., Martín, A., & de las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 216231.CrossRefGoogle Scholar
Musliner, K. L., Munk-Olsen, T., Eaton, W. W., & Zandi, P. P. (2016). Heterogeneity in long-term trajectories of depressive symptoms: Patterns, predictors and outcomes. Journal of Affective Disorders, 192, 199211.CrossRefGoogle ScholarPubMed
Nunes, M. A., Pinheiro, A. P., Bessel, M., Brunoni, A. R., Kemp, A. H., Benseñor, I. M., … Schmidt, M. I. (2016). Common mental disorders and sociodemographic characteristics: Baseline findings of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Revista Brasileira de Psiquiatria, 38, 9197.CrossRefGoogle Scholar
O'Neil, A., Fisher, A. J., Kibbey, K. J., Jacka, F. N., Kotowicz, M. A., Williams, L. J., … Pasco, J. A. (2016). Depression is a risk factor for incident coronary heart disease in women: An 18-year longitudinal study. Journal of Affective Disorders, 196, 117124.CrossRefGoogle ScholarPubMed
Ösby, U., Brandt, L., Correia, N., Ekbom, A., & Sparén, P. (2001). Excess mortality in bipolar and unipolar disorder in Sweden. Archives of General Psychiatry, 58, 844.CrossRefGoogle ScholarPubMed
Piccinelli, M., Tessari, E., Bortolomasi, M., Piasere, O., Semenzin, M., Garzotto, N., & Tansella, M. (1997). Efficacy of the alcohol use disorders identification test as a screening tool for hazardous alcohol intake and related disorders in primary care: A validity study. BMJ, 314, 420420.CrossRefGoogle ScholarPubMed
Rai, D., Zitko, P., Jones, K., Lynch, J., & Araya, R. (2013). Country- and individual-level socioeconomic determinants of depression: Multilevel cross-national comparison. British Journal of Psychiatry, 202, 195203.CrossRefGoogle ScholarPubMed
R Core Team. (2018). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from https://www.R-project.org/Google Scholar
Rosellini, A. J., Liu, S., Anderson, G. N., Sbi, S., Tung, E. S., & Knyazhanskaya, E. (2020). Developing algorithms to predict adult onset internalizing disorders: An ensemble learning approach. Journal of Psychiatric Research, 121, 189196.CrossRefGoogle Scholar
Salk, R. H., Hyde, J. S., & Abramson, L. Y. (2017). Gender differences in depression in representative national samples: Meta-analyses of diagnoses and symptoms. Psychological Bulletin, 143, 783822.CrossRefGoogle ScholarPubMed
Saluja, G., Iachan, R., Scheidt, P. C., Overpeck, M. D., Sun, W., & Giedd, J. N. (2004). Prevalence of and risk factors for depressive symptoms among young adolescents. Archives of Pediatrics & Adolescent Medicine, 158, 760.CrossRefGoogle ScholarPubMed
Skapinakis, P., Weich, S., Lewis, G., Singleton, N., & Araya, R. (2006). Socio-economic position and common mental disorders. British Journal of Psychiatry, 189, 109117.CrossRefGoogle ScholarPubMed
Spijker, J., de Graaf, R., Bijl R, V., Beekman, A. T. F., Ormel, J., & Nolen, W. A. (2004). Determinants of persistence of major depressive episodes in the general population. Results from the Netherlands Mental Health Survey and Incidence Study (NEMESIS). Journal of Affective Disorders, 81, 231240.CrossRefGoogle Scholar
van Buuren, S. (2018). Flexible imputation of missing data (2nd ed.). New York: Chapman and Hall/CRC. https://doi.org/10.1201/9780429492259COPYCrossRefGoogle Scholar
Wang, J., Sareen, J., Patten, S., Bolton, J., Schmitz, N., & Birney, A. (2014). A prediction algorithm for first onset of major depression in the general population: Development and validation. Journal of Epidemiology and Community Health, 68, 418424.CrossRefGoogle ScholarPubMed
Weger, M., & Sandi, C. (2018). High anxiety trait: A vulnerable phenotype for stress-induced depression. Neuroscience & Biobehavioral Reviews, 87, 2737.CrossRefGoogle ScholarPubMed
Supplementary material: PDF

Librenza-Garcia et al. supplementary material

Librenza-Garcia et al. supplementary material

Download Librenza-Garcia et al. supplementary material(PDF)
PDF 460.1 KB