Related Experiment Video
Updated: Jul 5, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Machine Learning Predictive Modeling for the Identification of Moderate Coronavirus Disease 2019 During the Pandemic:
Tao Wang1, Zhanqing Zhao2, Wenzhe Li3
1Department of Critical Care Medicine, Shanghai General Hospital, Shanghai, CHN.
Insights
A logistic regression model can predict moderate COVID-19 cases using age, respiratory rate, D-dimer, lactate dehydrogenase, and albumin. This model shows improved accuracy for patients aged 66 years or younger.
Area of Science:
- Medical research
- Machine learning in healthcare
- Infectious disease epidemiology
Background:
- Differentiating moderate COVID-19 from mild cases is crucial for timely treatment and resource allocation.
- Predictive models can aid in early identification of patients likely to develop moderate COVID-19.
- This study aimed to develop and validate a predictive model for moderate COVID-19.
Purpose of the Study:
- To construct and evaluate machine learning models for predicting moderate COVID-19.
- To identify key clinical and laboratory factors associated with moderate COVID-19 progression.
- To select the optimal model for predicting moderate COVID-19 occurrence.
Main Methods:
- Retrospective study of 231 COVID-19 patients.
- Data collected included demographics, clinical signs, comorbidities, and laboratory results.
- Machine learning models (BNB, LDA, SVM, LASSO, LR) were trained and compared using AUC, sensitivity, and specificity.
Main Results:
- A logistic regression (LR) model incorporating age, respiratory rate, lactate dehydrogenase, D-dimer, and albumin demonstrated predictive capability.
- The LR model achieved an AUC of 0.719, sensitivity of 0.681, and specificity of 0.635.
- The model showed enhanced predictive performance in patients aged ≤66 years (AUC = 0.7656).
Conclusions:
- The developed LR model effectively predicts moderate COVID-19.
- Key predictors include age, respiratory rate, D-dimer, lactate dehydrogenase, and albumin.
- The model is particularly useful for predicting moderate COVID-19 in younger patient cohorts (≤66 years).
Background:
Timely differentiation of moderate COVID-19 cases from mild cases is beneficial for early treatment and saves medical resources during the pandemic. We attempted to construct a model to predict the occurrence of moderate COVID-19 through a retrospective study.
Methods:
In this retrospective study, clinical data from patients with COVID-19 admitted to Hainan Western Central Hospital in Danzhou, China, between August 1, 2022, and August 31, 2022, was collected, including sex, age, signs on admission, comorbidities, imaging data, post-admission treatment, length of stay, and the results of laboratory tests on admission. The patients were classified into a mild-to-moderate-type group according to WHO guidance. Factors that differed between groups were included in machine learning models such as Bernoulli Naïve Bayes (BNB), linear discriminant analysis, support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), and logistic regression (LR) models. These models were compared to select the optimal model with the best predictive efficacy for moderate COVID-19. The predictive performance of the models was assessed using the area under the curve (AUC), sensitivity, specificity, and calibration plot.
Results:
A total of 231 patients with COVID-19 were included in this retrospective analysis. Among them, 152 (68.83%) were mild types, 72 (31.17%) were moderate types, and there were no patients with severe or critical types. A logistic regression model combined with age, respiratory rate (RR), lactate dehydrogenase (LDH), D-dimer, and albumin was selected to predict the occurrence of moderate COVID-19. The receiver operating characteristic curve (ROC) showed that AUC, sensitivity, and specificity in the model were 0.719, 0.681, and 0.635, respectively, in predicting moderate COVID-19. Calibration curve analysis revealed that the predicted probability of the model was in good agreement with the true probability. Stratified analysis showed better predictive efficacy after modeling for people aged ≤66 years (AUC = 0.7656) and a better calibration curve.
Conclusion:
The LR model, combined with age, RR, D-dimer, LDH, and albumin, can predict the occurrence of moderate COVID-19 well, especially for patients aged ≤66 years.
