Identifying risk factors of post-COVID-19 conditions with machine learning and deep learning algorithms
Guohai Zhou1, Scott P Kelly2, Ling Li2
1Pfizer Global Medical Epidemiology, 500 Arcola Rd, Collegeville, PA 19426, USA.
Insights
Post-COVID-19 conditions (PCC) impact millions. Machine learning models identified age, comorbidity score, and healthcare use as key predictors for developing PCC after SARS-CoV-2 infection.
Area of Science:
- Epidemiology
- Machine Learning
- Public Health
Background:
- Post-COVID-19 conditions (PCC) affect millions globally, necessitating research into their epidemiology and risk factors.
- Understanding real-world drivers of PCC is crucial for early diagnosis and effective management.
Purpose of the Study:
- To quantitatively evaluate the progression to newly developed PCC.
- To identify individual-level risk factors for developing new PCC at various time points following SARS-CoV-2 infection.
Main Methods:
- Applied multiple machine learning and deep learning models to a large US electronic health database (2020-2022).
- Analyzed patients with recent COVID-19 infection to assess PCC development.
- Evaluated risk factors at 60, 74, 90, and 120 days post-infection.
Main Results:
- Patients with new PCC were older, had higher comorbidity scores, and were more likely to smoke or have obesity, hyperlipidemia, or hypertension.
- Machine learning models consistently identified age, Charlson comorbidity score, and early healthcare utilization as leading risk factors.
- Disseminated intravascular coagulation was a significant predictor for cardiovascular or secondary PCC.
Conclusions:
- Machine learning models effectively predict new PCC occurrence.
- Key predictors include Charlson comorbidity score, age, and healthcare utilization frequency.
- These models offer utility for individualized risk prediction of Post-COVID-19 conditions.
Introduction:
Post-COVID-19 conditions (PCC) affect millions of people in the United States. Early diagnosis and PCC management requires an understanding of the epidemiology and drivers behind PCC in the real world.
Methods:
We applied multiple machine learning and deep learning models to a large electronic health database of patients with a recent COVID-19 infection in the United States from 2020 to 2022 to quantitatively evaluate progression to newly developed PCC and identify the individual-level risk factors for developing new PCC at 60, 74, 90, and 120 days following initial SARS-CoV-2 infection.
Results:
Patients with newly developed primary or secondary PCC were older; had higher Charleson comorbidity scores; and were more likely to smoke, have a body mass index ≥30, or have hyperlipidemia or hypertension than those without evidence of newly developed PCC. Three different machine learning models used to evaluate both the full study period and the Omicron era (beginning January 2022) consistently identified age, the Charlson comorbidity score, and healthcare utilization within 30 days of the index COVID-19 infection as the leading risk factors for developing new primary or secondary PCC. The presence of disseminated intravascular coagulation at baseline was among the 10 strongest predictors of newly developed cardiovascular or secondary PCC in the full study period and the Omicron era.
Conclusion:
Multiple machine learning and deep learning models identified the Charlson comorbidity score, age, and frequency of healthcare utilization, which may help predict the occurrence of new PCC and demonstrated the utility of the models for individualized risk prediction.
