{"doi":"10.2139/ssrn.3771320","title":"Prediction of COVID-19 Status Using Baseline Demographics and Lab Data","abstract":"Background: The global surge in COVID-19 cases underscores the need for fast, scalable, and reliable testing. Current COVID-19 diagnostic tests are limited by turnaround time, limited availability, or occasional false findings.<br><br>Methods: In this study, we developed a machine learning-based framework for predicting COVID-19 positive test status relying only on readily available baseline data, including patient demographics, comorbidities, and common lab values. Leveraging a cohort of 31,739 adults within an academic health system, we divided the patient data into a training set (patient encounters through April 13, 2020) and a test set (patient encounters from April 13, 2020 through June 2, 2020). We trained our machine learning models on the training set and evaluated model performance on the test set.<br><br>Findings: We trained and tested multiple types of machine learning models, achieving an area under the curve of 0·75 in the test set. Feature importance analyses highlighted serum calcium levels, aspartate aminotransferase levels, and oxygen saturation as key predictors. Additionally, we identified an optimal probability threshold for patient screening and developed a single decision tree model that provided an operable method for stratifying sub-populations.<br><br>Interpretation: Overall, this study provides a proof-of-concept that COVID-19 status prediction models can be developed using only baseline data. Our machine learning models can be adapted to a variety of global pandemic scenarios, as the resulting prediction could complement existing tests to enhance screening and pandemic containment workflows.<br><br>Funding: Icahn School of Medicine at Mount Sinai, New York, NY.<br><br>Declaration of Interests: J.F. is an employ of Outco Inc. All other authors declare no competing financial interests.<br><br>Ethics Approval Statement: This study utilized de-identified data extracted from the electronic health record and as such was considered nonhuman subject research. Therefore, this study was exempted from the Mount Sinai IRB review and approval process. All analyses were carried out in accordance with relevant guidelines and regulations.","journal":"SSRN Electronic Journal","year":2021,"id":8766,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0426,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1996,"name":"Tomi Jun","orcid":"0000-0002-2120-1704","position":1,"is_corresponding":false},{"id":74371,"name":"Jordi Frank","orcid":null,"position":2,"is_corresponding":false},{"id":7238,"name":"Sharon Nirenberg","orcid":"0000-0002-8556-4213","position":3,"is_corresponding":false},{"id":7239,"name":"Patricia Kovatch","orcid":"0000-0001-8368-1742","position":4,"is_corresponding":false},{"id":1998,"name":"Kuan-lin Huang","orcid":"0000-0002-3237-4248","position":5,"is_corresponding":false},{"id":72835,"name":"Jimmy Zhang","orcid":"0000-0003-2369-2292","position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":null,"created_at":"2026-03-01T18:20:47.508186Z","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":[]}