Prediction of Long COVID Based on Severity of Initial COVID-19 Infection: Differences in predictive feature sets between hospitalized versus non-hospitalized index infections
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.
Authors Statement: CC conceived the project strategy and developed environmental and demographic inputs. DS and DL implemented the ML model, and performed data cleaning, feature selection, ML model evaluation. SF parsed and interpreted clinical data features, aided in model analysis and extensively edited the manuscript. GA assisted with project design and manuscript development.
References: 1. National Institutes of Health (NIH). National Center for Advancing Translational Sciences (NCATS). National COVID Cohort Collaborative Data Enclave Repository. Bethesda,
Census, Bureau, P1: Total Population
Chen, Guestrin, Xgboost: A scalable tree boosting system
Johnson, Bulgarelli, Pollard, Horng, Celi et al., Mimic-iv. PhysioNet
Kachaner, Lemogne, Ranque, De Broucker, Meppiel, Somatic symptom disorder in patients with post-COVID-19 neurological symptoms: a preliminary report from the somatic study (Somatic Symptom Disorder Triggered by COVID-19), J Neurol Neurosurg Psychiatry
Perlis, Santillana, Ognyanova, Safarpour, Trujillo et al., Prevalence and correlates of long COVID symptoms among US adults, JAMA network open
Xie, Bowe, Al-Aly, Burdens of post-acute sequelae of COVID-19 by severity of acute infection, demographics and health status, Nature communications
Zhang, Zang, Xu, Zhang, Xu et al., Data-driven indentification of post-acute SARS-COV2 infection subphenotypes, Nature Medicine, doi:10.1038/s41591-022002116-3