Prediction of Long COVID Based on Severity of Initial COVID-19 Infection: Differences in predictive feature sets between hospitalized versus non-hospitalized index infections

{ 'institution': [{'name': 'medRxiv'}], 'indexed': {'date-parts': [[2023, 1, 21]], 'date-time': '2023-01-21T06:00:39Z', 'timestamp': 1674280839425}, 'posted': {'date-parts': [[2023, 1, 18]]}, 'group-title': 'Infectious Diseases (except HIV/AIDS)', 'reference-count': 13, 'publisher': 'Cold Spring Harbor Laboratory', 'content-domain': {'domain': [], 'crossmark-restriction': False}, 'accepted': {'date-parts': [[2023, 1, 18]]}, 'abstract': '<jats:title>Abstract</jats:title><jats:p>Long COVID is recognized as a significant ' 'consequence of SARS-COV2 infection. While the pathogenesis of Long COVID is still a subject ' 'of extensive investigation, there is considerable potential benefit in being able to predict ' 'which patients will develop Long COVID. We hypothesize that there would be distinct ' 'differences in the prediction of Long COVID based on the severity of the index infection, and ' 'use whether the index infection required hospitalization or not as a proxy for developing ' 'predictive models. We divide a large population of COVID patients drawn from the United ' 'States National Institutes of Health (NIH) National COVID Cohort Collaborative (N3C) Data ' 'Enclave Repository into two cohorts based on the severity of their initial COVID-19 illness ' 'and correspondingly trained two machine learning models: the Long COVID after Severe Disease ' 'Model (LCaSDM) and the Long COVID after Mild Disease Model (LCaMDM). The resulting models ' 'performed well on internal validation/testing, with a F1 score of 0.94 for the LCaSDM and ' '0.82 for the LCaMDM. There were distinct differences in the top 10 features used by each ' 'model, possibly reflecting the differences in type and amount of pathophysiological data ' 'between the hospitalized and non-hospitalized patients and/or reflecting different ' 'pathophysiological trajectories in the development of Long COVID. Of particular interest was ' 'the importance of Plant Hardiness Zone in the feature set for the LCaMDM, which may point to ' 'a role of climate and/or sunlight in the progression to Long COVID. Future work will involve ' 'a more detailed investigation of the potential role of climate and sunlight, as well as ' 'refinement of the predictive models as Long COVID becomes increasingly parsed into distinct ' 'clinical phenotypes.</jats:p>', 'DOI': '10.1101/2023.01.16.23284634', 'type': 'posted-content', 'created': {'date-parts': [[2023, 1, 18]], 'date-time': '2023-01-18T17:10:18Z', 'timestamp': 1674061818000}, 'source': 'Crossref', 'is-referenced-by-count': 0, 'title': 'Prediction of Long COVID Based on Severity of Initial COVID-19 Infection: Differences in ' 'predictive feature sets between hospitalized versus non-hospitalized index infections', 'prefix': '10.1101', 'author': [ {'given': 'Damien', 'family': 'Socia', 'sequence': 'first', 'affiliation': []}, {'given': 'Dale', 'family': 'Larie', 'sequence': 'additional', 'affiliation': []}, {'given': 'Sol', 'family': 'Feuerwerker', 'sequence': 'additional', 'affiliation': []}, { 'ORCID': 'http://orcid.org/0000-0003-4549-9004', 'authenticated-orcid': False, 'given': 'Gary', 'family': 'An', 'sequence': 'additional', 'affiliation': []}, {'given': 'Chase', 'family': 'Cockrell', 'sequence': 'additional', 'affiliation': []}], 'member': '246', 'reference': [ { 'key': '2023012009450858000_2023.01.16.23284634v1.1', 'unstructured': 'National Institutes of Health (NIH). National Center for Advancing ' 'Translational Sciences (NCATS). National COVID Cohort Collaborative Data ' 'Enclave Repository. Bethesda, Maryland: U.S. Department of Health and ' 'Human Services, National Institutes of Health, 2022.'}, { 'issue': '10', 'key': '2023012009450858000_2023.01.16.23284634v1.2', 'doi-asserted-by': 'crossref', 'first-page': 'e2238804', 'DOI': '10.1001/jamanetworkopen.2022.38804', 'article-title': 'Prevalence and correlates of long COVID symptoms among US adults', 'volume': '5', 'year': '2022', 'journal-title': 'JAMA network open'}, { 'issue': '1', 'key': '2023012009450858000_2023.01.16.23284634v1.3', 'first-page': '1', 'article-title': 'Burdens of post-acute sequelae of COVID-19 by severity of acute ' 'infection, demographics and health status', 'volume': '12', 'year': '2021', 'journal-title': 'Nature communications'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.4', 'doi-asserted-by': 'crossref', 'unstructured': 'Chen, T. and C. Guestrin (2016). Xgboost: A scalable tree boosting ' 'system. Proceedings of the 22nd acm sigkdd international conference on ' 'knowledge discovery and data mining: 785–794.', 'DOI': '10.1145/2939672.2939785'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.5', 'doi-asserted-by': 'publisher', 'DOI': '10.1136/jnnp-2021-327899'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.6', 'unstructured': 'Johnson, A. , Bulgarelli, L. , Pollard, T. , Horng, S. , Celi, L. A. , & ' 'Mark, R. (2020). Mimic-iv. PhysioNet. Available online at: ' 'https://physionet.org/content/mimiciv/1.0.'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.7', 'unstructured': 'U.S. Census Bureau. P1: Total Population. Available from: ' 'https://data.census.gov.'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.8', 'unstructured': 'PRISM Climate Group, Oregon State University, ' 'https://prism.oregonstate.edu, data created 4 Feb 2014, accessed 28 Oct. ' '2022.'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.9', 'unstructured': 'Google LLC. Google COVID-19 Community Mobility Reports”. [6/13/2021]. ' 'Available from: https://www.google.com/covid19/mobility.'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.10', 'unstructured': 'U.S. Department of Agriculture Economic Research Service. Educational ' 'attainment for adults age 25 and older for the U.S., States, and ' 'counties, 1970–2020. Available from: ' 'https://www.ers.usda.gov/data-products/county-level-data-sets/county-level-data-sets-download-data/'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.11', 'unstructured': 'U.S. Department of Agriculture Economic Research Service. 2013 ' 'Rural-Urban Continuum Codes. Available from: ' 'https://www.ers.usda.gov/data-products/county-level-data-sets/county-level-data-sets-download-data/'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.12', 'doi-asserted-by': 'crossref', 'unstructured': 'Zhang H , Zang C , Xu A , Zhang Y , Xu J , Bian J , Morozyuk D , Khullar ' 'D , Zhang Y , Nordvig AS , Schenck EJ , Shenkman EA , Rothman RL , Block ' 'JP , Lyman K , Weiner MG , Carton TW , Want F and Kaushal R. Data-driven ' 'indentification of post-acute SARS-COV2 infection subphenotypes. Nature ' 'Medicine (2022). DOI: https://doi.org/10.1038/s41591-022002116-3', 'DOI': '10.1038/s41591-022-02116-3'}, { 'key': '2023012009450858000_2023.01.16.23284634v1.13', 'doi-asserted-by': 'crossref', 'unstructured': 'Saunders C , Sperling S and Bendstrup E. A new paradigm is needed to ' 'explain long COVID. Lancet Resp Med (2023). Epub 5 January, 2023. DOI: ' 'https://doi.org/10.1016/S2213-2600(22)00501-X', 'DOI': '10.1016/S2213-2600(22)00501-X'}], 'container-title': [], 'original-title': [], 'link': [ { 'URL': 'https://syndication.highwire.org/content/doi/10.1101/2023.01.16.23284634', 'content-type': 'unspecified', 'content-version': 'vor', 'intended-application': 'similarity-checking'}], 'deposited': { 'date-parts': [[2023, 1, 20]], 'date-time': '2023-01-20T17:45:45Z', 'timestamp': 1674236745000}, 'score': 1, 'resource': {'primary': {'URL': 'http://medrxiv.org/lookup/doi/10.1101/2023.01.16.23284634'}}, 'subtitle': [], 'short-title': [], 'issued': {'date-parts': [[2023, 1, 18]]}, 'references-count': 13, 'URL': 'http://dx.doi.org/10.1101/2023.01.16.23284634', 'relation': {}, 'published': {'date-parts': [[2023, 1, 18]]}, 'subtype': 'preprint'}