Related Experiment Video
Updated: Jul 9, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Using Multi-Modal Electronic Health Record Data for the Development and Validation of Risk Prediction Models for Long
Weijia Jin1,2, Wei Hao1,2, Xu Shi1
1Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI 48109, USA.
Insights
Predicting Post-Acute Sequelae of COVID-19 (PASC) is crucial. Overweight/obesity, prior statin use, and respiratory symptoms during infection are key predictors. A composite risk score aids in identifying individuals at higher risk for PASC.
Area of Science:
- Medical research
- Public health
- Data science
Background:
- Post-Acute Sequelae of COVID-19 (PASC) present a significant global health challenge.
- Identifying predictive factors for PASC is essential for proactive healthcare management.
Purpose of the Study:
- To uncover predictive factors for PASC using multi-modal data.
- To develop and evaluate a predictive model for PASC diagnoses.
Main Methods:
- Analysis of electronic health records from 92,301 COVID-19 patients.
- Utilized a Super Learner-based prediction approach for factor identification.
- Integrated model outputs into individual and composite risk scores for performance evaluation.
Main Results:
- Identified overweight/obesity, pre-infection HMG CoA reductase inhibitor use, and respiratory symptoms during COVID-19 as predictive factors for PASC.
- Developed a composite risk score with moderate discriminatory ability (AUC: 0.66).
- The composite risk score identified 10% of individuals with a 2.2-fold increased risk for PASC.
Conclusions:
- Several factors predictive of PASC diagnoses were identified.
- A composite risk score was developed to aid in PASC prediction.
- This risk score can help identify high-risk individuals and inform preventive strategies.
Background:
Post-Acute Sequelae of COVID-19 (PASC) have emerged as a global public health and healthcare challenge. This study aimed to uncover predictive factors for PASC from multi-modal data to develop a predictive model for PASC diagnoses.
Methods:
We analyzed electronic health records from 92,301 COVID-19 patients, covering medical phenotypes, medications, and lab results. We used a Super Learner-based prediction approach to identify predictive factors. We integrated the model outputs into individual and composite risk scores and evaluated their predictive performance.
Results:
Our analysis identified several factors predictive of diagnoses of PASC, including being overweight/obese and the use of HMG CoA reductase inhibitors prior to COVID-19 infection, and respiratory system symptoms during COVID-19 infection. We developed a composite risk score with a moderate discriminatory ability for PASC (covariate-adjusted AUC (95% confidence interval): 0.66 (0.63, 0.69)) by combining the risk scores based on phenotype and medication records. The combined risk score could identify 10% of individuals with a 2.2-fold increased risk for PASC.
Conclusions:
We identified several factors predictive of diagnoses of PASC and integrated the information into a composite risk score for PASC prediction, which could contribute to the identification of individuals at higher risk for PASC and inform preventive efforts.
