Hostname: page-component-7f64f4797f-zzvtc Total loading time: 0 Render date: 2025-11-06T04:04:53.371Z Has data issue: false hasContentIssue false
  • English
  • Français

Predicting adolescent depression and anxiety from multi-wave longitudinal data using machine learning

Published online by Cambridge University Press:  15 November 2022

Mariah T. Hawes Open the ORCID record for Mariah T. Hawes [Opens in a new window] ,
H. Andrew Schwartz ,
Youngseo Son  and
Daniel N. Klein
Mariah T. Hawes*
Affiliation:
Department of Psychology, Stony Brook University, Stony Brook, NY, USA
H. Andrew Schwartz
Affiliation:
Department of Computer Science, Stony Brook University, Stony Brook, NY, USA
Youngseo Son
Affiliation:
Department of Computer Science, Stony Brook University, Stony Brook, NY, USA
Daniel N. Klein
Affiliation:
Department of Psychology, Stony Brook University, Stony Brook, NY, USA
*
Author for correspondence: Mariah T. Hawes, E-mail: hawes2mt@gmail.com
Get access Rights & Permissions [Opens in a new window]

Abstract

Background

This study leveraged machine learning to evaluate the contribution of information from multiple developmental stages to prospective prediction of depression and anxiety in mid-adolescence.

Methods

A community sample (N = 374; 53.5% male) of children and their families completed tri-annual assessments across ages 3–15. The feature set included several important risk factors spanning psychopathology, temperament/personality, family environment, life stress, interpersonal relationships, neurocognitive, hormonal, and neural functioning, and parental psychopathology and personality. We used canonical correlation analysis (CCA) to reduce the large feature set to a lower dimensional space while preserving the longitudinal structure of the data. Ablation analysis was conducted to evaluate the relative contributions to prediction of information gathered at different developmental periods and relative to previous disorder status (i.e. age 12 depression or anxiety) and demographics (sex, race, ethnicity).

Results

CCA components from individual waves predicted age 15 disorder status better than chance across ages 3, 6, 9, and 12 for anxiety and 9 and 12 for depression. Only the components from age 12 for depression, and ages 9 and 12 for anxiety, improved prediction over prior disorder status and demographics.

Conclusions

These findings suggest that screening for risk of adolescent depression can be successful as early as age 9, while screening for risk of adolescent anxiety can be successful as early as age 3. Assessing additional risk factors at age 12 for depression, and going back to age 9 for anxiety, can improve screening for risk at age 15 beyond knowing standard demographics and disorder history.

Keywords

adolescenceanxietydepressionlongitudinalmachine learningrisk assessment

Information

Type
Original Article
Information
Psychological Medicine , Volume 53 , Issue 13 , October 2023 , pp. 6205 - 6211
Check for updates
Copyright
Copyright © The Author(s), 2022. 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.)

Article purchase

Temporarily unavailable

References

American Psychiatric Association (1994). Diagnostic and statistical manual of mental disorders: DSM-IV. Washington, DC: American Psychiatric Association.Google Scholar
American Psychiatric Association (2013). Diagnostic and statistical manual of mental disorders (DSM-5®). Washington, DC: American Psychiatric Publishing.Google Scholar
Andersson, S., Bathula, D. R., Iliadis, S. I., Walter, M., & Skalkidou, A. (2021). Predicting women with depressive symptoms postpartum with machine learning methods. Scientific Reports, 11(1), 1–15.10.1038/s41598-021-86368-yCrossRefGoogle ScholarPubMed
Axelson, D., Birmaher, B., Zelazny, J., Kaufman, J., & Gill, M. (2009). The schedule for affective disorders and schizophrenia-present and lifetime version (K-SADS-PL) 2009 working draft. Advanced Centre for Intervention and Services Research, Western Psychiatric Institute and Clinics.Google Scholar
Beesdo, K., Knappe, S., & Pine, D. S. (2009). Anxiety and anxiety disorders in children and adolescents: Developmental issues and implications for DSM-V. Psychiatric Clinics, 32(3), 483–524.Google ScholarPubMed
Bellón, J., de Dios Luna, J., King, M., Moreno-Küstner, B., Nazareth, I., Montón-Franco, C., … Vicens, C. (2011). Predicting the onset of major depression in primary care: International validation of a risk prediction algorithm from Spain. Psychological Medicine, 41(10), 2075–2088.10.1017/S0033291711000468CrossRefGoogle ScholarPubMed
Campbell, L. A., Brown, T. A., & Grisham, J. R. (2003). The relevance of age of onset to the psychopathology of generalized anxiety disorder. Behavior Therapy, 34(1), 31–48.10.1016/S0005-7894(03)80020-5CrossRefGoogle Scholar
Caspi, A., Houts, R. M., Ambler, A., Danese, A., Elliott, M. L., Hariri, A., … Ramrakha, S. (2020). Longitudinal assessment of mental health disorders and comorbidities across 4 decades among participants in the Dunedin birth cohort study. JAMA Network Open, 3(4), e203221–e203221.10.1001/jamanetworkopen.2020.3221CrossRefGoogle ScholarPubMed
Coutanche, M., & Hallion, L. (2019). Machine learning for clinical psychology and clinical neuroscience. In Wright, A. & Hallquist, M. (Eds.), The Cambridge handbook of research methods in clinical psychology (pp. 467–482). Cambridge: Cambridge University Press.Google Scholar
de Lijster, J. M., Dierckx, B., Utens, E. M., Verhulst, F. C., Zieldorff, C., Dieleman, G. C., & Legerstee, J. S. (2017). The age of onset of anxiety disorders: A meta-analysis. Canadian Journal of Psychiatry. Revue Canadienne de Psychiatrie, 62(4), 237.10.1177/0706743716640757CrossRefGoogle Scholar
Dwyer, D. B., Falkai, P., & Koutsouleris, N. (2018). Machine learning approaches for clinical psychology and psychiatry. Annual Review of Clinical Psychology, 14, 91–118.10.1146/annurev-clinpsy-032816-045037CrossRefGoogle ScholarPubMed
Eichstaedt, J. C., Smith, R. J., Merchant, R. M., Ungar, L. H., Crutchley, P., Preoţiuc-Pietro, D., … Schwartz, H. A. (2018). Facebook language predicts depression in medical records. Proceedings of the National Academy of Sciences, 115(44), 11203–11208.10.1073/pnas.1802331115CrossRefGoogle ScholarPubMed
Eliot, M., Ferguson, J., Reilly, M. P., & Foulkes, A. S. (2011). Ridge regression for longitudinal biomarker data. The International Journal of Biostatistics, 7(1), 1–11.10.2202/1557-4679.1353CrossRefGoogle ScholarPubMed
Essau, C. A., Lewinsohn, P. M., Olaya, B., & Seeley, J. R. (2014). Anxiety disorders in adolescents and psychosocial outcomes at age 30. Journal of Affective Disorders, 163, 125–132.10.1016/j.jad.2013.12.033CrossRefGoogle ScholarPubMed
Fawcett, C., & Hoos, H. H. (2016). Analysing differences between algorithm configurations through ablation. Journal of Heuristics, 22(4), 431–458.10.1007/s10732-014-9275-9CrossRefGoogle Scholar
Fleisher, W. P., & Katz, L. Y. (2001). Early onset major depressive disorder. Paediatrics & Child Health, 6(7), 444–448.10.1093/pch/6.7.444CrossRefGoogle ScholarPubMed
Fried, E. I., & Robinaugh, D. J. (2020). Systems all the way down: Embracing complexity in mental health research. BMC Medicine, 18(205), 1–4.10.1186/s12916-020-01668-wCrossRefGoogle ScholarPubMed
GBD 2017 Disease and Injury Incidence and Prevalence Collaborators (2018). Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: A systematic analysis for the Global Burden of Disease Study 2017. The Lancet, 392(10159), 1789–1858.10.1016/S0140-6736(18)32279-7CrossRefGoogle Scholar
Guntuku, S. C., Yaden, D. B., Kern, M. L., Ungar, L. H., & Eichstaedt, J. C. (2017). Detecting depression and mental illness on social media: An integrative review. Current Opinion in Behavioral Sciences, 18, 43–49.10.1016/j.cobeha.2017.07.005CrossRefGoogle Scholar
Hastie, T., Tibshirani, R., & Jermone, F. (2009). The elements of statistical learning: Data mining, inference and prediction (2nd ed.). New York, NY: Springer-Verlag.10.1007/978-0-387-84858-7CrossRefGoogle Scholar
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112). New York, NY: Springer.10.1007/978-1-4614-7138-7CrossRefGoogle Scholar
Kessler, R. C., Chiu, W. T., Demler, O., & Walters, E. E. (2005). Prevalence, severity, and comorbidity of 12-month DSM-IV disorders in the national comorbidity survey replication. Archives of General Psychiatry, 62(6), 617–627.10.1001/archpsyc.62.6.617CrossRefGoogle ScholarPubMed
Kessler, R. C., van Loo, H. M., Wardenaar, K. J., Bossarte, R. M., Brenner, L. A., Cai, T., … de Jonge, P. (2016). Testing a machine-learning algorithm to predict the persistence and severity of major depressive disorder from baseline self-reports. Molecular Psychiatry, 21(10), 1366–1371.10.1038/mp.2015.198CrossRefGoogle ScholarPubMed
King, M., Walker, C., Levy, G., Bottomley, C., Royston, P., Weich, S., … Rotar, D. (2008). Development and validation of an international risk prediction algorithm for episodes of major depression in general practice attendees: The PredictD study. Archives of General Psychiatry, 65(12), 1368–1376.10.1001/archpsyc.65.12.1368CrossRefGoogle ScholarPubMed
Klein, D. N., & Finsaas, M. C. (2017). The stony brook temperament study: Early antecedents and pathways to emotional disorders. Child Development Perspectives, 11(4), 257–263.10.1111/cdep.12242CrossRefGoogle Scholar
Koul, A., Becchio, C., & Cavallo, A. (2018). Cross-validation approaches for replicability in psychology. Frontiers in Psychology, 9, 1117.10.3389/fpsyg.2018.01117CrossRefGoogle ScholarPubMed
Kumar, P., Garg, S., & Garg, A. (2020). Assessment of anxiety, depression and stress using machine learning models. Procedia Computer Science, 171, 1989–1998.10.1016/j.procs.2020.04.213CrossRefGoogle Scholar
Liu, Y., Hankey, J., Cao, B., & Chokka, P. (2021). Screening for major depressive disorder in a tertiary mental health centre using EarlyDetect: A machine learning-based pilot study. Journal of Affective Disorders Reports, 3, 100062.10.1016/j.jadr.2020.100062CrossRefGoogle Scholar
McLeod, G. F., Horwood, L. J., & Fergusson, D. M. (2016). Adolescent depression, adult mental health and psychosocial outcomes at 30 and 35 years. Psychological Medicine, 46(7), 1401–1412.10.1017/S0033291715002950CrossRefGoogle ScholarPubMed
Miché, M., Studerus, E., Meyer, A. H., Gloster, A. T., Beesdo-Baum, K., Wittchen, H.-U., & Lieb, R. (2020). Prospective prediction of suicide attempts in community adolescents and young adults, using regression methods and machine learning. Journal of Affective Disorders, 265, 570–578.10.1016/j.jad.2019.11.093CrossRefGoogle Scholar
Naicker, K., Galambos, N. L., Zeng, Y., Senthilselvan, A., & Colman, I. (2013). Social, demographic, and health outcomes in the 10 years following adolescent depression. Journal of Adolescent Health, 52(5), 533–538.10.1016/j.jadohealth.2012.12.016CrossRefGoogle ScholarPubMed
Nemesure, M. D., Heinz, M. V., Huang, R., & Jacobson, N. C. (2021). Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence. Scientific Reports, 11(1), 1–9.10.1038/s41598-021-81368-4CrossRefGoogle Scholar
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., … Dubourg, V. (2011). Scikit-learn: Machine learning in Python. The Journal of Machine Learning research, 12, 2825–2830.Google Scholar
Rice, M. E., & Harris, G. T. (2005). Comparing effect sizes in follow-up studies: ROC area, Cohen's d, and r. Law and Human Behavior, 29(5), 615–620.10.1007/s10979-005-6832-7CrossRefGoogle 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, 189–196.10.1016/j.jpsychires.2019.12.006CrossRefGoogle ScholarPubMed
Sato, J. R., Moll, J., Green, S., Deakin, J. F., Thomaz, C. E., & Zahn, R. (2015). Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression. Psychiatry Research: Neuroimaging, 233(2), 289–291.10.1016/j.pscychresns.2015.07.001CrossRefGoogle ScholarPubMed
Schwartz, H. A., Giorgi, S., Sap, M., Crutchley, P., Ungar, L., & Eichstaedt, J. (2017). Dlatk: Differential language analysis toolkit. Paper presented at the Proceedings of the 2017 conference on empirical methods in natural language processing: System demonstrations.Google Scholar
Shatte, A. B., Hutchinson, D. M., & Teague, S. J. (2019). Machine learning in mental health: A scoping review of methods and applications. Psychological Medicine, 49(9), 1426–1448.10.1017/S0033291719000151CrossRefGoogle ScholarPubMed
Su, D., Zhang, X., He, K., & Chen, Y. (2021). Use of machine learning approach to predict depression in the elderly in China: A longitudinal study. Journal of Affective Disorders, 282, 289–298.10.1016/j.jad.2020.12.160CrossRefGoogle Scholar
Tackett, J. L., Brandes, C. M., King, K. M., & Markon, K. E. (2019). Psychology's replication crisis and clinical psychological science. Annual Review of Clinical Psychology, 15, 579–604.10.1146/annurev-clinpsy-050718-095710CrossRefGoogle ScholarPubMed
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 & Community Health, 68(5), 418–424.10.1136/jech-2013-202845CrossRefGoogle ScholarPubMed
Whelan, R., & Garavan, H. (2014). When optimism hurts: Inflated predictions in psychiatric neuroimaging. Biological Psychiatry, 75(9), 746–748.10.1016/j.biopsych.2013.05.014CrossRefGoogle ScholarPubMed
Witten, D. M., Tibshirani, R., & Hastie, T. (2009). A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. Biostatistics (Oxford, England), 10(3), 515–534.10.1093/biostatistics/kxp008CrossRefGoogle ScholarPubMed
Yarkoni, T., & Westfall, J. (2017). Choosing prediction over explanation in psychology: Lessons from machine learning. Perspectives on Psychological Science, 12(6), 1100–1122.10.1177/1745691617693393CrossRefGoogle ScholarPubMed
Zhang, Y., Wang, S., Hermann, A., Joly, R., & Pathak, J. (2021). Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women. Journal of Affective Disorders, 279, 1–8.10.1016/j.jad.2020.09.113CrossRefGoogle ScholarPubMed
Supplementary material: File

Hawes et al. supplementary material

Hawes et al. supplementary material 1

Download Hawes et al. supplementary material(File)
File 36.4 KB
Supplementary material: File

Hawes et al. supplementary material

Hawes et al. supplementary material 2

Download Hawes et al. supplementary material(File)
File 68.3 KB
Supplementary material: File

Hawes et al. supplementary material

Hawes et al. supplementary material 3

Download Hawes et al. supplementary material(File)
File 48.1 KB