Development and evaluation of a risk algorithm predicting alcohol dependence after early onset of regular alcohol use

Chrianna Bharat, Meyer D. Glantz, Sergio Aguilar‐gaxiola, Jordi Alonso, Ronny Bruffaerts, Brendan Bunting, José Miguel Caldas‐de‐almeida, Graça Cardoso, Stephanie Chardoul, Peter De Jonge, Oye Gureje, Josep Maria Haro, Meredith G. Harris, Elie G. Karam, Norito Kawakami, Andrzej Kiejna, Viviane Kovess‐masfety, Sing Lee, John J. Mcgrath, Jacek MoskalewiczFernando Navarro‐mateu, Charlene Rapsey, Nancy A. Sampson, Kate M. Scott, Hisateru Tachimori, Margreet Ten Have, Gemma Vilagut, Bogdan Wojtyniak, Miguel Xavier, Ronald C. Kessler, Louisa Degenhardt

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
56 Downloads (Pure)


Aims: Likelihood of alcohol dependence (AD) is increased among people who transition to greater levels of alcohol involvement at a younger age. Indicated interventions delivered early may be effective in reducing risk, but could be costly. One way to increase cost‐effectiveness would be to develop a prediction model that targeted interventions to the subset of youth with early alcohol use who are at highest risk of subsequent AD. Design: A prediction model was developed for DSM‐IV AD onset by age 25 years using an ensemble machine‐learning algorithm known as ‘Super Learner’. Shapley additive explanations (SHAP) assessed variable importance. Setting and Participants: Respondents reporting early onset of regular alcohol use (i.e. by 17 years of age) who were aged 25 years or older at interview from 14 representative community surveys conducted in 13 countries as part of WHO's World Mental Health Surveys. Measurements: The primary outcome to be predicted was onset of life‐time DSM‐IV AD by age 25 as measured using the Composite International Diagnostic Interview, a fully structured diagnostic interview. Findings: AD prevalence by age 25 was 5.1% among the 10 687 individuals who reported drinking alcohol regularly by age 17. The prediction model achieved an external area under the curve [0.78; 95% confidence interval (CI) = 0.74–0.81] higher than any individual candidate risk model (0.73–0.77) and an area under the precision‐recall curve of 0.22. Overall calibration was good [integrated calibration index (ICI) = 1.05%]; however, miscalibration was observed at the extreme ends of the distribution of predicted probabilities. Interventions provided to the 20% of people with highest risk would identify 49% of AD cases and require treating four people without AD to reach one with AD. Important predictors of increased risk included younger onset of alcohol use, males, higher cohort alcohol use and more mental disorders. Conclusions: A risk algorithm can be created using data collected at the onset of regular alcohol use to target youth at highest risk of alcohol dependence by early adulthood. Important considerations remain for advancing the development and practical implementation of such models.
Original languageEnglish
Pages (from-to)954-966
Number of pages13
Issue number5
Early online date7 Jan 2023
Publication statusPublished (in print/issue) - 31 May 2023

Bibliographical note

Funding Information:
In the past 3 years, L.D. has received investigator‐initiated untied educational grants for studies of opioid medications in Australia from Indivior, Mundipharma and Seqirus. M.G.H. reports consulting fees from RAND Corporation outside the submitted work. N.K. reports grants and consulting fees outside the submitted work. He received grants from Fujitsu Japan, Ltd and SBAtWork Corporation and consulting fees from Occupational Health Foundation, Japan Dental Association, Sekisui Chemicals, Junpukai Health Care Center and Osaka Chamber of Commerce and Industry. R.C.K. and N.A.S. report research grants from National Institute of Mental Health, USA (Grants: R01 MH070884; U01 MH60220); John D. and Catherine T. MacArthur Foundation; Pfizer Foundation; US Public Health Service (Grants: R13‐MH066849, R01‐MH069864 and R01 DA016558); Fogarty International Center (Grant: R03‐TW006481); Pan American Health Organization; Eli Lilly and Company; Ortho‐McNeil Pharmaceutical; GlaxoSmithKline; Bristol‐Myers Squibb; National Institute of Drug Abuse; Substance Abuse and Mental Health Services Administration, USA; Robert Wood Johnson Foundation (Grant 044708); and John W. Alden Trust. In the past 3 years, R.C.K. was a consultant for Datastat, Inc., Holmusk, RallyPoint Networks, Inc. and Sage Therapeutics. He has stock options in Mirah, PYM and Roga Sciences. H.T. reports research grants from the Ministry of Health, Labour and Welfare, Japan. All other authors report no conflicts of interest.

Publisher Copyright:
© 2023 The Authors. Addiction published by John Wiley & Sons Ltd on behalf of Society for the Study of Addiction.


  • alcohol dependence
  • childhood
  • predictive modelling
  • machine learning
  • Adolescence
  • alcohol use
  • dependence
  • discrimination
  • calibration


Dive into the research topics of 'Development and evaluation of a risk algorithm predicting alcohol dependence after early onset of regular alcohol use'. Together they form a unique fingerprint.

Cite this