Prediction of Disease Progression of COVID-19 Based upon Machine Learning
Fumin Xu1, Xiao Chen2, Xinru Yin1
1Department of Gastroenterology, Daping Hospital, Army Medical University, Chongqing, People's Republic of China.
Insights
Machine learning models accurately predict COVID-19 severity using clinical features like D-dimer, CRP, and age. This helps identify high-risk patients for timely intervention.
Area of Science:
- Medical Informatics
- Public Health
- Computational Biology
Background:
- COVID-19 (Coronavirus Disease 2019) has caused a global pandemic.
- Patient outcomes for COVID-19 vary significantly, necessitating risk stratification.
- Identifying patients at high risk for severe disease progression is crucial.
Purpose of the Study:
- To develop and evaluate machine learning models for predicting severe COVID-19.
- To identify key clinical features associated with COVID-19 disease progression.
Main Methods:
- Retrospective, multicenter cohort study including 455 COVID-19 patients.
- Univariate analysis to screen significant clinical features differentiating severe and non-severe cases.
- Development of machine learning classifier models (e.g., k-nearest neighbor, support vector machine) for prediction.
- Validation using independent test sets from two hospitals.
Main Results:
- Twenty-one features significantly differed between severe and non-severe COVID-19 groups.
- An optimal subset of eleven features in the k-nearest neighbor model showed high predictive performance (AUC).
- D-dimer, C-reactive protein (CRP), and age were identified as the most important predictors.
- A support vector machine model achieved the highest AUC on a test set.
Conclusions:
- Machine learning models successfully predict COVID-19 disease progression.
- Optimal-feature subsets enhance the accuracy of predictive models.
- Developed software enables prediction of disease severity based on machine learning.
Background:
Since December 2019, COVID-19 has spread throughout the world. Clinical outcomes of COVID-19 patients vary among infected individuals. Therefore, it is vital to identify patients at high risk of disease progression.
Methods:
In this retrospective, multicenter cohort study, COVID-19 patients from Huoshenshan Hospital and Taikang Tongji Hospital (Wuhan, China) were included. Clinical features showing significant differences between the severe and nonsevere groups were screened out by univariate analysis. Then, these features were used to generate classifier models to predict whether a COVID-19 case would be severe or nonsevere based on machine learning. Two test sets of data from the two hospitals were gathered to evaluate the predictive performance of the models.
Results:
A total of 455 patients were included, and 21 features showing significant differences between the severe and nonsevere groups were selected for the training and validation set. The optimal subset, with eleven features in the k-nearest neighbor model, obtained the highest area under the curve (AUC) value among the four models in the validation set. D-dimer, CRP, and age were the three most important features in the optimal-feature subsets. The highest AUC value was obtained using a support vector-machine model for a test set from Huoshenshan Hospital. Software for predicting disease progression based on machine learning was developed.
Conclusion:
The predictive models were successfully established based on machine learning, and achieved satisfactory predictive performance of disease progression with optimal-feature subsets.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Related Concept Videos
01:18Steps in Outbreak Investigation
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
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...
01:07End Point Prediction: Gran Plot
For potentiometric titration, the Gran plot is created by plotting...
02:07Tumor Progression
Colon cancer is one of the best-documented examples of tumor progression. Early mutation in the APC gene in colon cells causes a small growth on the colon wall called a polyp. With time, this polyp grows into a benign, pre-cancerous tumor. Further...
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.