{"doi":"10.1101/2020.09.12.20193342","title":"Ancestry May Confound Genetic Machine Learning: Candidate-Gene Prediction of Opioid Use Disorder as an Example","abstract":"Abstract Background Machine 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. Methods We 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. Results None 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. Conclusions Researchers 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.","journal":"medRxiv","year":2020,"id":122465,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":5,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.947,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":230694,"name":"Frank R. Wendt","orcid":"0000-0002-2108-6822","position":1,"is_corresponding":false},{"id":563704,"name":"Marco Galimberti","orcid":"0000-0001-6052-156X","position":2,"is_corresponding":false},{"id":229994,"name":"Renato Polimanti","orcid":"0000-0003-0745-6046","position":3,"is_corresponding":false},{"id":104455,"name":"Benjamin M. Neale","orcid":"0000-0003-1513-6077","position":4,"is_corresponding":false},{"id":11401,"name":"Henry R. Kranzler","orcid":"0000-0002-1018-0450","position":5,"is_corresponding":false},{"id":230005,"name":"Joel Gelernter","orcid":"0000-0002-4067-1859","position":6,"is_corresponding":false},{"id":230003,"name":"Howard J. Edenberg","orcid":"0000-0003-0344-9690","position":7,"is_corresponding":false},{"id":230004,"name":"Arpana Agrawal","orcid":"0000-0002-0313-793X","position":8,"is_corresponding":false},{"id":230692,"name":"Alexander S. Hatoum","orcid":"0000-0002-8002-7267","position":0,"is_corresponding":true}],"reference_count":36,"raw_metadata":null,"created_at":"2026-07-18T23:14:51.076430Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}