Challenges in the application of a mortality prediction model for COVID-19 patients on an Indian cohort

TL;DR

This paper examines the limitations of a COVID-19 mortality prediction model based on machine learning when applied to an Indian patient cohort, highlighting challenges in generalizability and deployment.

Contribution

It critically evaluates an existing ML-based COVID-19 mortality prediction model on an Indian dataset, revealing its technical limitations and challenges in practical application.

Findings

The model's performance drops significantly on Indian data.

Technical challenges hinder deployment across different populations.

Limitations of the model's clinical utility are identified.

Abstract

Many countries are now experiencing the third wave of the COVID-19 pandemic straining the healthcare resources with an acute shortage of hospital beds and ventilators for the critically ill patients. This situation is especially worse in India with the second largest load of COVID-19 cases and a relatively resource-scarce medical infrastructure. Therefore, it becomes essential to triage the patients based on the severity of their disease and devote resources towards critically ill patients. Yan et al. 1 have published a very pertinent research that uses Machine learning (ML) methods to predict the outcome of COVID-19 patients based on their clinical parameters at the day of admission. They used the XGBoost algorithm, a type of ensemble model, to build the mortality prediction model. The final classifier is built through the sequential addition of multiple weak classifiers. The clinically operable decision rule was obtained from a 'single-tree XGBoost' and used lactic dehydrogenase (LDH), lymphocyte and high-sensitivity C-reactive protein (hs-CRP) values. This decision tree achieved a 100% survival prediction and 81% mortality prediction. However, these models have several technical challenges and do not provide an out of the box solution that can be deployed for other populations as has been reported in the "Matters Arising" section of Yan et al. Here, we show the limitations of this model by deploying it on one of the largest datasets of COVID-19 patients containing detailed clinical parameters collected from India.