Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
Objective
To provide a thorough comparative study among state-of-the-art machine learning methods and statistical methods for determining in-hospital mortality in COVID-19 patients using data upon hospital admission; to study the reliability of the predictions of the most effective methods by correlating the probability of the outcome and the accuracy of the methods; to investigate how explainable are the predictions produced by the most effective methods.
Materials and Methods
De-identified data were obtained from COVID-19 positive patients in 36 participating hospitals, from March 1 to September 30, 2020. Demographic, comorbidity, clinical presentation and laboratory data were used as training data to develop COVID-19 mortality prediction models. Multiple machine learning and traditional statistics models were trained on this prediction task using a folded cross-validation procedure, from which we assessed performance and interpretability metrics.
Results
The Stacking of machine learning models improved over the previous state-of-the-art results by more than 26% in predicting the class of interest (death), achieving 87.1% of AUROC and macro F1 of 73.9%. We also show that some machine learning models can be very interpretable and reliable, yielding more accurate predictions while providing a good explanation for the ‘why’.
Conclusion
The best results were obtained using the meta-learning ensemble model – Stacking. State-of the art explainability techniques such as SHAP-values can be used to draw useful insights into the patterns learned by machine-learning algorithms. Machine-learning models can be more explainable than traditional statistics models while also yielding highly reliable predictions.
Article activity feed
-
SciScore for 10.1101/2021.11.01.21265527: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources A prespecified case report form was used, applying Research Electronic Data Capture (REDCap) tools (15). REDCapsuggested: (REDCap, RRID:SCR_003445)Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:This is an intrinsic limitation of regression models, and the variable may be seen as non-significant due to the fact that it is a non-linear association. As previously …
SciScore for 10.1101/2021.11.01.21265527: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources A prespecified case report form was used, applying Research Electronic Data Capture (REDCap) tools (15). REDCapsuggested: (REDCap, RRID:SCR_003445)Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:This is an intrinsic limitation of regression models, and the variable may be seen as non-significant due to the fact that it is a non-linear association. As previously mentioned, an important limitation of regression models is collinearity. When exploiting LASSO regression in our previous work (4), we had to exclude some features which had shown to be important in the boosting model due to high collinearity. This may explain the difference in the features included in both models, despite the fact that all features included in both had previous evidence of association with COVID-19 prognosis. Another interesting remark is shown in Fig 4, in which we can see the relative importance of each feature. Here, again, age is the most important single feature (due to higher mean SHAP value), which is in line with previous studies (3,31,32). In an American study in intensive care units, age has shown higher discriminatory capacity when used in isolation (AUC 0.66) than the Sequential Organ Failure Assessment (SOFA) score (0.55) for mortality prediction, in a cohort study of adult patients from 18 ICUs in the US, with COVID-19 pneumonia. This score is widely used at emergency departments and ICUs worldwide to determine the extent of a person’s organ function or rate of failure (42). In the present study, the remaining features, when combined, yield higher predictive value in this task than just age. Reliability: Finally, we investigate issues related to the reliability of the models. Ne...
Results from TrialIdentifier: No clinical trial numbers were referenced.
Results from Barzooka: We did not find any issues relating to the usage of bar graphs.
Results from JetFighter: We did not find any issues relating to colormaps.
Results from rtransparent:- Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
- Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
- No protocol registration statement was detected.
Results from scite Reference Check: We found no unreliable references.
-