{"doi":"10.1101/2020.06.09.20127092","title":"Using machine learning to predict COVID-19 infection and severity risk among 4,510 aged adults: a UK Biobank cohort study","abstract":"BACKGROUND: Many risk factors have emerged for novel 2019 coronavirus disease (COVID-19). It is relatively unknown how these factors collectively predict COVID-19 infection risk, as well as risk for a severe infection (i.e., hospitalization). METHODS: Among aged adults (69.3 ± 8.6 years) in UK Biobank, COVID-19 data was downloaded for 4,510 participants with 7,539 test cases. We downloaded baseline data from 10-14 years ago, including demographics, biochemistry, body mass, and other factors, as well as antibody titers for 20 common to rare infectious diseases. Permutation-based linear discriminant analysis was used to predict COVID-19 risk and hospitalization risk. Probability and threshold metrics included receiver operating characteristic curves to derive area under the curve (AUC), specificity, sensitivity, and quadratic mean. RESULTS: The \"best-fit\" model for predicting COVID-19 risk achieved excellent discrimination (AUC=0.969, 95% CI=0.934-1.000). Factors included age, immune markers, lipids, and serology titers to common pathogens like human cytomegalovirus. The hospitalization \"best-fit\" model was more modest (AUC=0.803, 95% CI=0.663-0.943) and included only serology titers. CONCLUSIONS: Accurate risk profiles can be created using standard self-report and biomedical data collected in public health and medical settings. It is also worthwhile to further investigate if prior host immunity predicts current host immunity to COVID-19.","journal":"medRxiv","year":2020,"id":120707,"datarank":0.8345108829562127,"base_score":2.302585092994046,"endowment":2.302585092994046,"self_citation_contribution":0.3453877639491069,"citation_network_contribution":0.48912311900710576,"self_endowment_contribution":0.3453877639491069,"citer_contribution":0.48912311900710576,"corpus_percentile":75.8722054614373,"corpus_rank":3120,"citation_count":9,"citer_count":8,"citers_with_citation_signal":7,"citers_with_endowment":7,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.7956,"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":559776,"name":"Sara A. Willette","orcid":null,"position":1,"is_corresponding":false},{"id":558764,"name":"Qian Wang","orcid":"0000-0001-7933-238X","position":2,"is_corresponding":false},{"id":447573,"name":"Colleen Pappas","orcid":"0000-0001-9140-3558","position":3,"is_corresponding":false},{"id":447566,"name":"Brandon S. Klinedinst","orcid":"0000-0003-2697-1852","position":4,"is_corresponding":false},{"id":448464,"name":"Scott T. Le","orcid":null,"position":5,"is_corresponding":false},{"id":447568,"name":"Brittany Larsen","orcid":"0000-0002-6088-5176","position":6,"is_corresponding":false},{"id":447572,"name":"Amy Pollpeter","orcid":"0000-0001-5122-7174","position":7,"is_corresponding":false},{"id":558765,"name":"Tianqi Li","orcid":"0000-0001-7215-2546","position":8,"is_corresponding":false},{"id":558766,"name":"Nicole Brenner","orcid":"0000-0002-7690-4925","position":9,"is_corresponding":false},{"id":390102,"name":"Tim Waterboer","orcid":"0000-0002-0616-6963","position":10,"is_corresponding":false},{"id":447577,"name":"Auriel A. Willette","orcid":"0000-0001-5131-8199","position":0,"is_corresponding":true}],"reference_count":40,"raw_metadata":null,"created_at":"2026-07-18T23:14:38.147936Z","pmid":"32577673","pmcid":"PMC7302228","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":[]}