Predicting COVID-19 hospitalisation and common disease risk from comorbid diagnoses in 13 million individuals
- 1British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK
Abstract
Predicting disease risk from prior diagnoses is fundamental to clinical decision-making, particularly during health emergencies such as the COVID-19 pandemic, when individuals with long-term conditions may be disproportionately vulnerable to adverse outcomes. Despite intense interest in developing models to predict disease risk from prior diagnoses 1-3, most prediction models do not estimate effects of each prior diagnosis on disease risk conditional on other diagnoses, limiting interpretability and clinical utility. We developed the Comorbidity Risk Score (CRS), trained on 13 million individuals (age 40-69) from linked electronic health record (EHR) datasets of the entire population of England, to predict COVID-19 hospitalisation and 87 other disease outcomes. CRS was trained at close to saturated sample size and precisely estimated the effects of 212 prior diagnoses on the 88 disease outcomes, conditional on all other prior diagnoses. Correlations of CRS effect sizes across outcomes (e.g. 0.76 for myocardial infarction vs. hyperlipidaemia) matched the corresponding genetic correlations (e.g. 0.79 for myocardial infarction vs. hyperlipidaemia), confirming that comorbidity architectures capture disease aetiology. On average, CRS identified 5% of the population with 3.4-fold higher disease risk, including myocardial infarction (4.4-fold), lung cancer (6.5-fold), and COVID-19 hospitalisation (6.3-fold). Using prior diagnoses alone, CRS outperformed state-of-the-art clinical COVID-19 models 4. Furthermore, CRS (N=13 million) substantially outperformed state-of-the-art AI 1 (N=0.5 million) and linear 3 (N=0.5 million) models in predicting disease risk, suggesting that training sample size outweighs model complexity. CRS attained near-perfect transferability across self-reported ethnicities (e.g., Black vs. White: AUROC ratio = 97.3%). Finally, CRS distinguished independently predictive comorbidities from indirect associations, e.g., lipid metabolism disorder was a strong predictor of myocardial infarction risk but not ischaemic stroke, after conditioning on other prior diagnoses. In conclusion, CRS provides a comprehensive resource for understanding the impact of comorbidities on COVID-19 and other future diseases, revealing disease aetiology while enabling powerful prediction of disease risk.
Related
- Excess hypoglycaemia-related hospitalisation in older adults with comorbid type 2 diabetes and dementia: a UK Biobank cohort study
- Pain Self-Efficacy as a Mediator between Fear-Avoidance Beliefs and Social Avoidance among Individuals with Comorbid Post- Traumatic Stress Disorder and Chronic Pain
- Burden and temporal trends of cardiovascular disease among medical inpatients and age-specific and sex-specific risk of CVD-related hospitalisation at a national referral hospital in Uganda: a retrospective cohort study
- Predicting the persistence of Long COVID 36 months after hospitalisation: a prospective Ukrainian cohort study
- Machine learning classification and regional differentiation of neuropathologically-confirmed Alzheimer’s disease and comorbid Lewy body disease
BibTeX
@misc{liu2026predicting,
title = {{Predicting COVID-19 hospitalisation and common disease risk from comorbid diagnoses in 13 million individuals}},
author = {H. Liu and M. A. Mizani and Y. Zhao and A. Wood and M. Inouye and A. L. Price and X. Jiang and CVD-COVID-UK/COVID-IMPACT Consortium},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.27.26361302},
url = {https://www.medrxiv.org/content/10.64898/2026.08.27.26361302v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Predicting COVID-19 hospitalisation and common disease risk from comorbid diagnoses in 13 million individuals
AU - H. Liu
AU - M. A. Mizani
AU - Y. Zhao
AU - A. Wood
AU - M. Inouye
AU - A. L. Price
AU - X. Jiang
AU - CVD-COVID-UK/COVID-IMPACT Consortium
PY - 2026
DA - 2026/08/27
PB - medRxiv
DO - 10.64898/2026.08.27.26361302
UR - https://www.medrxiv.org/content/10.64898/2026.08.27.26361302v1
AB - Predicting disease risk from prior diagnoses is fundamental to clinical decision-making, particularly during health emergencies such as the COVID-19 pandemic, when individuals with long-term conditions may be disproportionately vulnerable to adverse outcomes. Despite intense interest in developing models to predict disease risk from prior diagnoses 1-3, most prediction models do not estimate effects of each prior diagnosis on disease risk conditional on other diagnoses, limiting interpretability and clinical utility. We developed the Comorbidity Risk Score (CRS), trained on 13 million individuals (age 40-69) from linked electronic health record (EHR) datasets of the entire population of England, to predict COVID-19 hospitalisation and 87 other disease outcomes. CRS was trained at close to saturated sample size and precisely estimated the effects of 212 prior diagnoses on the 88 disease outcomes, conditional on all other prior diagnoses. Correlations of CRS effect sizes across outcomes (e.g. 0.76 for myocardial infarction vs. hyperlipidaemia) matched the corresponding genetic correlations (e.g. 0.79 for myocardial infarction vs. hyperlipidaemia), confirming that comorbidity architectures capture disease aetiology. On average, CRS identified 5% of the population with 3.4-fold higher disease risk, including myocardial infarction (4.4-fold), lung cancer (6.5-fold), and COVID-19 hospitalisation (6.3-fold). Using prior diagnoses alone, CRS outperformed state-of-the-art clinical COVID-19 models 4. Furthermore, CRS (N=13 million) substantially outperformed state-of-the-art AI 1 (N=0.5 million) and linear 3 (N=0.5 million) models in predicting disease risk, suggesting that training sample size outweighs model complexity. CRS attained near-perfect transferability across self-reported ethnicities (e.g., Black vs. White: AUROC ratio = 97.3%). Finally, CRS distinguished independently predictive comorbidities from indirect associations, e.g., lipid metabolism disorder was a strong predictor of myocardial infarction risk but not ischaemic stroke, after conditioning on other prior diagnoses. In conclusion, CRS provides a comprehensive resource for understanding the impact of comorbidities on COVID-19 and other future diseases, revealing disease aetiology while enabling powerful prediction of disease risk.
ER -