Building a Prediction Model to Detect Elevated Risk for Developing a Substance Use Disorder
- 1Department of Psychiatry, Rutgers Robert Wood Johnson Medical School
Abstract
sO_ST_ABSImportanceC_ST_ABSPreventing substance use disorder (SUD) is a top public health priority, but clinical practice currently lacks validated prognostic tools to identify risk before the onset of heavy use/problems.
ObjectiveTo determine whether models can predict SUD using genetic, behavioral, and environmental factors and to evaluate performance across substance types (alcohol, cannabis, tobacco), sex, and genetic similarity groups.
DesignThis prognostic study developed and validated a multi-domain risk model using data from four longitudinal cohorts (The National Longitudinal Study of Adolescent to Adult Health, Avon Longitudinal Study of Parents and Children, The Collaborative Study on the Genetics of Alcoholism, and FinnTwin12) with follow-up from early adolescence into young adulthood.
SettingPopulation-based and family-based samples from the United States, United Kingdom, and Finland.
ParticipantsThe analysis included participants with available genomic and behavioral data. The cohorts represented a spectrum of risk, ranging from nationally representative community samples to high-risk populations.
Exposure(s) (for observational studies)Predictors included polygenic scores for substance use-related phenotypes and 10 established early-life behavioral and environmental risk factors.
Main Outcome(s) and Measure(s)The outcomes were a diagnosis of moderate-to- severe SUD based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) criteria. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive value.
ResultsA total of 16,362 participants were included in the study (54.7% female; mean [SD] age 26.73 [3.36]). Genetic similarity group composition was 70.4% European, 16.8% African, 9.8% admixed American, 2.2% East Asian, and 0.7% South Asian. SUD prevalence was 22.0%. The integrated model achieved an AUC of 0.78 for predicting any SUD, with a sensitivity of 69% and a positive predictive value of 45%. Performance was comparable for specific substances (AUC range 0.74-0.82) and across genetic similarity groups (AUC range 0.61-0.82). The model demonstrated higher AUC in females compared with males.
Conclusions and RelevanceFindings highlight the potential utility of an SUD prediction model to inform clinicians and patients about risk for developing a SUD.
Key pointsO_ST_ABSQuestionC_ST_ABSCan we develop prediction models to detect elevated risk for developing a substance use disorder (SUD) prior to onset.?
FindingsUsing a harmonized dataset of four diverse longitudinal cohorts, we developed and evaluated a prediction model that integrates genetic, behavioral, and environmental predictors. The model demonstrated good discriminatory power to identify individuals at risk for future SUD.
MeaningThese findings establish a framework for integrating multi-domain, multi{-}informant data into clinical workflows, offering a basis for personalized risk stratification and prevention of SUDs.
Related
- Developing an outcomes framework for greenspace programmes supporting individuals experiencing problem substance use: a scoping review and analytical synthesis
- Genetic and Environmental Connections Shared between Transmissible Liability to Substance Use Disorder and Substance Use Initiation
- Dose–effect relationship of an acute isometric exercise session with different durations on blood pressure and arterial stiffness in prehypertensive substance use disorder individuals
- Perceived Effect of the COVID-19 Pandemic on Substance Use and Interest in Medications for Opioid Use Disorder and Naloxone Among People Who Use Opioids in the Southern United States
- Elevated environmental CO2 stimulates photosynthesis and induces differential oxidative responses in two Caribbean reef-building coral species
BibTeX
@misc{hung2026building,
title = {{Building a Prediction Model to Detect Elevated Risk for Developing a Substance Use Disorder}},
author = {I.-T. Hung and F. Aliev and S. I.-C. Kuo and A. Kim and G. Khan and H. E. Poore and G. F. Dash and M. Choi and H. Zhou and A. Latvala and S. Aaltonen and J. Kaprio and J. E. Salvatore and R. J. Rose and COGA Collaborators and D. M. Dick},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.16.26365759},
url = {https://www.medrxiv.org/content/10.64898/2026.10.16.26365759v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Building a Prediction Model to Detect Elevated Risk for Developing a Substance Use Disorder
AU - I.-T. Hung
AU - F. Aliev
AU - S. I.-C. Kuo
AU - A. Kim
AU - G. Khan
AU - H. E. Poore
AU - G. F. Dash
AU - M. Choi
AU - H. Zhou
AU - A. Latvala
AU - S. Aaltonen
AU - J. Kaprio
AU - J. E. Salvatore
AU - R. J. Rose
AU - COGA Collaborators
AU - D. M. Dick
PY - 2026
DA - 2026/10/16
PB - medRxiv
DO - 10.64898/2026.10.16.26365759
UR - https://www.medrxiv.org/content/10.64898/2026.10.16.26365759v1
AB - sO_ST_ABSImportanceC_ST_ABSPreventing substance use disorder (SUD) is a top public health priority, but clinical practice currently lacks validated prognostic tools to identify risk before the onset of heavy use/problems. ObjectiveTo determine whether models can predict SUD using genetic, behavioral, and environmental factors and to evaluate performance across substance types (alcohol, cannabis, tobacco), sex, and genetic similarity groups. DesignThis prognostic study developed and validated a multi-domain risk model using data from four longitudinal cohorts (The National Longitudinal Study of Adolescent to Adult Health, Avon Longitudinal Study of Parents and Children, The Collaborative Study on the Genetics of Alcoholism, and FinnTwin12) with follow-up from early adolescence into young adulthood. SettingPopulation-based and family-based samples from the United States, United Kingdom, and Finland. ParticipantsThe analysis included participants with available genomic and behavioral data. The cohorts represented a spectrum of risk, ranging from nationally representative community samples to high-risk populations. Exposure(s) (for observational studies)Predictors included polygenic scores for substance use-related phenotypes and 10 established early-life behavioral and environmental risk factors. Main Outcome(s) and Measure(s)The outcomes were a diagnosis of moderate-to- severe SUD based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) criteria. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive value. ResultsA total of 16,362 participants were included in the study (54.7% female; mean [SD] age 26.73 [3.36]). Genetic similarity group composition was 70.4% European, 16.8% African, 9.8% admixed American, 2.2% East Asian, and 0.7% South Asian. SUD prevalence was 22.0%. The integrated model achieved an AUC of 0.78 for predicting any SUD, with a sensitivity of 69% and a positive predictive value of 45%. Performance was comparable for specific substances (AUC range 0.74-0.82) and across genetic similarity groups (AUC range 0.61-0.82). The model demonstrated higher AUC in females compared with males. Conclusions and RelevanceFindings highlight the potential utility of an SUD prediction model to inform clinicians and patients about risk for developing a SUD. Key pointsO_ST_ABSQuestionC_ST_ABSCan we develop prediction models to detect elevated risk for developing a substance use disorder (SUD) prior to onset.? FindingsUsing a harmonized dataset of four diverse longitudinal cohorts, we developed and evaluated a prediction model that integrates genetic, behavioral, and environmental predictors. The model demonstrated good discriminatory power to identify individuals at risk for future SUD. MeaningThese findings establish a framework for integrating multi-domain, multi{-}informant data into clinical workflows, offering a basis for personalized risk stratification and prevention of SUDs.
ER -