ArticleDrug and alcohol dependence2021
Ancestry may confound genetic machine learning: Candidate-gene prediction of opioid use disorder as an example.
Article in Drug and alcohol dependence, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 18 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
18 citing papers in PubMed, 18 citations in OpenAlex.
- Are polygenic scores for psychiatric and substance use outcomes "ready" for clinical application? Current state and next steps.Psychiatric genetics · 2026Review
- Machine learning models incorporating genotype and ancestry improve severe asthma risk prediction.Scientific reports · 2025Article
- Multi-ancestry Genome-wide Association Study of Inpatient Opioid Dosing Following Knee or Hip Arthroplasty.Research square · 2025Article
- Multi-ancestry Genome-wide Association Study of Inpatient Opioid Dosing Following Knee or Hip Arthroplasty.medRxiv : the preprint server for health sciences · 2025Article
- Harnessing machine learning in contemporary tobacco research.Toxicology reports · 2025Review
- Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare.Journal of the American Medical Informatics Association : JAMIA · 2025Article
- Concerns about genetic risk testing for opioid use disorder.The lancet. Psychiatry · 2025Article
- Utility of Candidate Genes From an Algorithm Designed to Predict Genetic Risk for Opioid Use Disorder.JAMA network open · 2025Article
- Principles and Policy Recommendations for Comprehensive Genetic Data Governance.Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · 2025Article
- A Comprehensive 4-layeredCurrent pharmaceutical biotechnology · 2025Article
- Generalized genetic liability to substance use disorders.The Journal of clinical investigation · 2024Review
- Genetic and non-genetic predictors of risk for opioid dependence.Psychological medicine · 2024Article
- Candidate Genes from an FDA-Approved Algorithm Fail to Predict Opioid Use Disorder Risk in Over 450,000 Veterans.medRxiv : the preprint server for health sciences · 2024Article
- Statistical and Machine Learning Analysis in Brain-Imaging Genetics: A Review of Methods.Behavior genetics · 2024Review
- Invited Expert Opinion- Bioinformatic and Limitation Directives to Help Adopt Genetic Addiction Risk Screening and Identify Preaddictive Reward Dysregulation: Required Analytic Evidence to Induce Dopamine Homeostatsis.Medical research archives · 2023Article
- Genetic Addiction Risk Severity Assessment Identifies Polymorphic Reward Genes as Antecedents to Reward Deficiency Syndrome (RDS) Hypodopaminergia's Effect on Addictive and Non-Addictive Behaviors in a Nuclear Family.Journal of personalized medicine · 2022Article
- Statistical Validation of Risk Alleles in Genetic Addiction Risk Severity (GARS) Test: Early Identification of Risk for Alcohol Use Disorder (AUD) in 74,566 Case-Control Subjects.Journal of personalized medicine · 2022Article
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors at 5 institutions in 1 country.
Funding
Abstract
backgroundMachine learning (ML) models are beginning to proliferate in psychiatry, however machine learning models in psychiatric genetics have not always accounted for ancestry. Using an empirical example of a proposed genetic test for OUD, and exploring a similar test for tobacco dependence and a simulated binary phenotype, we show that genetic prediction using ML is vulnerable to ancestral confounding.
methodsWe utilize five ML algorithms trained with 16 brain reward-derived "candidate" SNPs proposed for commercial use and examine their ability to predict OUD vs. ancestry in an out-of-sample test set (N = 1000, stratified into equal groups of n = 250 cases and controls each of European and African ancestry). We rerun analyses with 8 random sets of allele-frequency matched SNPs. We contrast findings with 11 genome-wide significant variants for tobacco smoking. To document generalizability, we generate and test a random phenotype.
resultsNone of the 5 ML algorithms predict OUD better than chance when ancestry was balanced but were confounded with ancestry in an out-of-sample test. In addition, the algorithms preferentially predicted admixed subpopulations. Random sets of variants matched to the candidate SNPs by allele frequency produced similar bias. Genome-wide significant tobacco smoking variants were also confounded by ancestry. Finally, random SNPs predicting a random simulated phenotype show that the bias attributable to ancestral confounding could impact any ML-based genetic prediction.
conclusionsResearchers and clinicians are encouraged to be skeptical of claims of high prediction accuracy from ML-derived genetic algorithms for polygenic traits like addiction, particularly when using candidate variants.
Indexed as
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.