Related Experiment Video
Updated: Nov 15, 2025
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Individualized prediction of COVID-19 adverse outcomes with MLHO
Hossein Estiri1,2,3, Zachary H Strasser4,5,6,7, Shawn N Murphy4,5,6,7,8
1Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA, 02144, USA. hestiri@mgh.harvard.edu.
Abstract:
The COVID-19 pandemic has devastated the world with health and economic wreckage. Precise estimates of adverse outcomes from COVID-19 could have led to better allocation of healthcare resources and more efficient targeted preventive measures, including insight into prioritizing how to best distribute a vaccination. We developed MLHO (pronounced as melo), an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health Outcomes. MLHO implements iterative sequential representation mining, and feature and model selection, for predicting patient-level risk of hospitalization, ICU admission, need for mechanical ventilation, and death. It bases this prediction on data from patients' past medical records (before their COVID-19 infection). MLHO's architecture enables a parallel and outcome-oriented model calibration, in which different statistical learning algorithms and vectors of features are simultaneously tested to improve prediction of health outcomes. Using clinical and demographic data from a large cohort of over 13,000 COVID-19-positive patients, we modeled the four adverse outcomes utilizing about 600 features representing patients' pre-COVID health records and demographics. The mean AUC ROC for mortality prediction was 0.91, while the prediction performance ranged between 0.80 and 0.81 for the ICU, hospitalization, and ventilation. We broadly describe the clusters of features that were utilized in modeling and their relative influence for predicting each outcome. Our results demonstrated that while demographic variables (namely age) are important predictors of adverse outcomes after a COVID-19 infection, the incorporation of the past clinical records are vital for a reliable prediction model. As the COVID-19 pandemic unfolds around the world, adaptable and interpretable machine learning frameworks (like MLHO) are crucial to improve our readiness for confronting the potential future waves of COVID-19, as well as other novel infectious diseases that may emerge.
Insights
Machine Learning for Health Outcomes (MLHO) predicts COVID-19 patient risks using past medical data. Incorporating clinical history significantly improves predictions of hospitalization, ICU admission, ventilation, and death.
Area of Science:
- Medical Informatics
- Computational Biology
- Epidemiology
Background:
- The COVID-19 pandemic caused significant health and economic disruption globally.
- Accurate prediction of adverse COVID-19 outcomes is crucial for resource allocation and preventive strategies, including vaccination prioritization.
Purpose of the Study:
- To develop and validate an end-to-end Machine Learning framework (MLHO) for predicting patient-level adverse health outcomes from COVID-19.
- To assess the predictive value of pre-infection clinical and demographic data for COVID-19 severity.
Main Methods:
- Developed MLHO, a Machine Learning framework using iterative feature and algorithm selection for predicting hospitalization, ICU admission, mechanical ventilation, and death.
- Utilized a cohort of over 13,000 COVID-19-positive patients, analyzing approximately 600 features from pre-infection medical records and demographics.
- Employed parallel, outcome-oriented model calibration to test various statistical learning algorithms and feature sets simultaneously.
Main Results:
- MLHO achieved a mean AUC ROC of 0.91 for mortality prediction and 0.80-0.81 for ICU admission, hospitalization, and ventilation prediction.
- Demographic variables like age were important, but pre-existing clinical records were vital for reliable outcome prediction.
- Identified key feature clusters influencing the prediction of each adverse outcome.
Conclusions:
- MLHO provides an adaptable and interpretable Machine Learning approach for predicting COVID-19 adverse outcomes.
- The framework's reliance on pre-infection clinical data highlights its potential for proactive healthcare management.
- MLHO can enhance preparedness for future infectious disease outbreaks.
More Related Videos
Related Concept Videos
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:18Steps in Outbreak Investigation
02:24Predicting Reaction Outcomes
01:13Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
01:21Cancer Survival Analysis
01:11Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...