What question did this study set out to answer?

The aim is to examine how machine learning models predict mortality risk in COVID-19 patients across different subgroups.

March 8, 2026Open Access

Predictive divergence in machine learning models for clinical mortality risk: A multicohort study of covid-19 patients

Key Points

The aim is to examine how machine learning models predict mortality risk in COVID-19 patients across different subgroups.
Conducted a multicohort analysis of COVID-19 patients
Evaluated various machine learning algorithms
Compared individual and subgroup prediction outcomes
Models showed similar overall performance but diverged significantly in individual predictions
No single algorithm consistently outperformed others across all patient subgroups
Findings emphasize the limitations of global performance metrics

Abstract

This study demonstrates that ML models with similar overall performance can yield substantially divergent predictions at both the individual and subgroup levels, and that no single algorithm consistently outperforms others across all patient subgroups. These findings highlight the limitations of relying solely on global performance metrics and underscore the need for context-aware evaluation of ML models in heterogeneous clinical populations.

Connected Papers

Building similarity graph...

Analyzing shared references across papers

Discussion

Authors

Júlia Chaves Neuenschwander Magalhães

Alexandre Dias Porto Chiavegatto Filho

Journals

PLoS ONE

Actions

Institutions

Universidade de São Paulo

References and Citations

Connected Papers

Building similarity graph...

Analyzing shared references across papers

Predictive divergence in machine learning models for clinical mortality risk: A multicohort study of covid-19 patients

Key Points

Abstract

Citation Network

Connected Papers

Discussion

Authors

Journals

Actions

Institutions

References and Citations

Citation Network

Connected Papers

Discussion

Cite this study