There is a well-established trend of increasing prevalence of mental health disorders among children and young people. Understanding patterns across diagnostic categories and predicting future changes is crucial for effective interventions and service planning.
Methods:
We employed advanced time series analysis techniques, autoregressive integrated moving average-based time series modelling and forecasting, to analyse two decades of routinely collected data from the Western Australian Child and Adolescent Mental Health Services system. The large-scale dataset, with consistent sampling intervals, enabled robust time series analyses to account for secular, seasonal and random fluctuations. Models estimated both historical and forecasted future trends in mental health presentations at Western Australian Child and Adolescent Mental Health Services.
Results:
Modelling of historical data from 2004 to 2024 shows significant increases for anxiety disorders, mood disorders, personality disorders, sleep disorders, attention deficit hyperactivity disorder (ADHD) and autism and eating disorders. Forecasting to 2044 suggests that while anxiety disorders will decrease, ADHD, autism, eating disorders and sleep disorders will continue to increase.
Conclusions:
We have established autoregressive integrated moving average modelling and forecasting as a robust, sophisticated and useful statistical approach to characterising historical and future trends in youth mental health. The ability to forecast into the future with confidence means we can identify what services are most needed and where gaps exist in current service provision or fund distribution permitting strategic allocation of finite resources and supporting complex funding decisions. Importantly, our findings encourage other health care services, locally and internationally, to use autoregressive integrated moving average modelling and forecasting to capitalize on routine health data to support proactive service planning initiatives.
AnokyeRAcheampongEOwusuI, et al. (2018) Time series analysis of malaria in Kumasi: Using ARIMA models to forecast future incidence. Cogent Social Sciences4. DOI: 10.1080/23311886.2018.1461544.
BatesDMächlerMBolkerB, et al. (2015) Fitting linear mixed-effects models using lme4. Journal of Statistical Software67: 1–48.
4.
BernalJLCumminsSGasparriniA (2017) Interrupted time series regression for the evaluation of public health interventions: A tutorial. International Journal of Epidemiology46: 348–355.
5.
BesongAEKibuODTanueEA, et al. (2025) Significance of the ARIMA epidemiological modeling to predict the rate of HIV and AIDS in the Kumba Health District of Cameroon. Frontiers in Public Health13: 1526454.
6.
CollishawS (2015) Annual research review: Secular trends in child and adolescent mental health. Journal of Child Psychology and Psychiatry, and Allied Disciplines56: 370–393.
7.
CollishawSMaughanBGoodmanR, et al. (2004) Time trends in adolescent mental health. Journal of Child Psychology and Psychiatry45: 1350–1362.
8.
CrabtreeBFRaySCSchmidtPM, et al. (1990) The individual over time: Time series applications in health care research. Journal of Clinical Epidemiology43: 241–260.
9.
Department of Health (2025) About us. Government of Western Australia. Available at: www.health.wa.gov.au/About-us (accessed 9 July 2025).
10.
FrancesABatstraL (2013) Why so many epidemics of childhood mental disorder?Journal of Developmental and Behavioral Pediatrics: JDBP34: 291–292.
11.
GBD 2019 Diseases and Injuries Collaborators (2020) Global burden of 369 diseases and injuries in 204 countries and territories, 1990-2019: A systematic analysis for the Global Burden of Disease Study 2019. Lancet396: 1204–1222.
12.
HafekostJJohnsonSLawrenceD, et al. (2016a) Introducing ‘Young Minds Matter’. The Australian Economic Review49: 503–514.
13.
HafekostJLawrenceDBoterhovendeHaanK, et al. (2016b) Methodology of young minds matter: The second Australian Child and Adolescent Survey of mental health and wellbeing. The Australian and New Zealand Journal of Psychiatry50: 866–875.
14.
HyndmanRJKhandakarY (2008) Automatic time series forecasting: The forecast package for R. Journal of Statistical Software27: 1–22.
15.
KielingCBuchweitzCCayeA, et al. (2024) Worldwide prevalence and disability from mental disorders across childhood and adolescence: Evidence from the global burden of disease study. JAMA Psychiatry81: 347–356.
16.
KimERubinsteinSMNeadKT, et al. (2019) The evolving use of electronic health records (EHR) for research. Seminars in Radiation Oncology29: 354–361.
17.
LenthR (2005) Emmeans: Estimated Marginal Means, aka Least-Squares Means (Version 1.11.1-00001). Available at: https://rvlenth.github.io/emmeans/ (accessed 29 December 2025).
18.
LiWLawKLE (2024) Deep learning models for time series forecasting: A review. IEEE Access12: 92306–92327.
19.
MadiganSRacineNVaillancourtT, et al. (2023) Changes in depression and anxiety among children and adolescents from before to during the COVID-19 pandemic: A systematic review and meta-analysis. JAMA Pediatrics177: 567–581.
20.
McGorryPDGunasiriHMeiC, et al. (2024a). The youth mental health crisis: Analysis and solutions. Frontiers in Psychiatry15: 1517533.
21.
McGorryPDMeiCDalalN, et al. (2024b) The Lancet Psychiatry Commission on youth mental health. The Lancet. Psychiatry11: 731–774.
22.
McMartinSEKingsburyMDykxhoorn, et al. (2014) Time trends in symptoms of mental illness in children and adolescents in Canada. CMAJ186: E672–E678.
23.
MohammadiM-RSalmanianMKeshavarziZ (2021) The global prevalence of conduct disorder: A systematic review and meta-analysis. Iranian Journal of Psychiatry16: 205–225.
24.
MojtabaiROlfsonM (2024) Trends in Mental Disorders in Children and Adolescents Receiving Treatment in the State Mental Health System. Journal of the American Academy of Child & Adolescent Psychiatry64:906–920.
25.
MpuhuaCAMSouzaOFDDaboinBEG, et al. (2025) Proportional stroke mortality in Espirito Santo, Brazil: A 20-year joinpoint regression study. Epidemiologia6: 28.
26.
OspinaRGondimJALeivaV, et al. (2023) An overview of forecast analysis with ARIMA models during the COVID-19 pandemic: Methodology and case study in Brazil. Mathematics11: 3096.
27.
PadmanabhanVBellagardaCADondziloL, et al. (2025) Impact of a Pediatric Mental Health Crisis Service in the emergency department on hospital resource utilization: An interrupted time series analysis. Journal of Child Psychology and Psychiatry, and Allied Disciplines66: 1713–1723.
28.
PatelVSaxenaSLundC, et al. (2018) The Lancet Commission on global mental health and sustainable development. Lancet392: 1553–1598.
29.
PeiperNCRidenourTAHochwaltB, et al. (2016) Overview on prevalence and recent trends in adolescent substance use and abuse. Child and Adolescent Psychiatric Clinics of North America25: 349–365.
30.
PhamTTranTPhungD, et al. (2017) Predicting healthcare trajectories from medical records: A deep learning approach. Journal of Biomedical Informatics69: 218–229.
31.
PolanczykGVSalumGASugayaLS, et al. (2015) Annual research review: A meta-analysis of the worldwide prevalence of mental disorders in children and adolescents. Journal of Child Psychology and Psychiatry, and Allied Disciplines56: 345–365.
32.
PotrebnyTNilsenSABakkenA, et al. (2025) Secular trends in mental health problems among young people in Norway: A review and meta-analysis. Eur Child Adolesc Psychiatry34: 69–81.
33.
R Core Team (2021) R: A language and environment for statistical computing. R Foundation for Statistical Computing. Available at: www.R-project.org/ (accessed 29 December 2025).
34.
SabryMAbd-El-LatifHBadraN (2007) Comparison between regression and Arima models in forecasting traffic volume. Australian Journal of Basic and Applied Science1: 126–136.
35.
SaccoRCamilleriNEberhardtJ, et al. (2024) A systematic review and meta-analysis on the prevalence of mental disorders among children and adolescents in Europe. European Child & Adolescent Psychiatry33: 2877–2894.
36.
SantomauroDFHerreraAMMShadidJ, et al. (2021) Global prevalence and burden of depressive and anxiety disorders in 204 countries and territories in 2020 due to the COVID-19 pandemic. Lancet398: 1700–1712.
37.
SatoRC (2013) Disease management with ARIMA model in time series. Einstein11: 128–131.
38.
SiambaSOtienoAKoechJ (2023) Application of ARIMA, and hybrid ARIMA Models in predicting and forecasting tuberculosis incidences among children in Homa Bay and Turkana Counties, Kenya. PLoS Digital Health2: e0000084.
39.
SilvaABDSAraújoACDMFriasPGD, et al. (2021) Auto-Regressive Integrated Moving Average Model (ARIMA): Conceptual and methodological aspects and applicability in infant mortality. Revista Brasileira de Saúde Materno Infantil21: 647–656.
40.
WatsonLQiSDeIureALinkC, et al. (2021) Using Autoregressive Integrated Moving Average (ARIMA) modelling to forecast symptom complexity in an ambulatory oncology clinic: Harnessing predictive analytics and patient-reported outcomes. International Journal of Environmental Research and Public Health18: 8635.
41.
WuYWangLTaoM, et al. (2023) Changing trends in the global burden of mental disorders from 1990 to 2019 and predicted levels in 25 years. Epidemiology and Psychiatric Sciences32: e63.
42.
ZegerSLIrizarryRAPengRD (2004) On time series analysis of public health and biomedical data. Johns Hopkins University, Department of Biostatistics Working Papers, Issue. http://biostats.bepress.com/jhubiostat/paper54 (accessed 29 December 2025).
