Search

This study aims to develop a Machine Learning model to assess the risks faced by COVID-19 patients in a hospital setting, focusing specifically on predicting the complications leading to Intensive Care Unit (ICU) admission or mortality, which are minority classes compared to the majority class of discharged patients. We operate within a multiclass framework comprising three distinct classes, and address the challenge of dataset imbalance, a common source of model bias. To effectively manage this, we introduce the Multi-Thresholding meta-algorithm (MTh), an innovative output-level methodology that extends traditional thresholding from binary to multiclass classification. This methodology dynamically adjusts class probabilities using misclassification costs, making it highly effective in imbalanced datasets. Our approach is further enhanced by integrating the simplicity, transparency, and effectiveness of Bayesian networks to create a robust predictive model. Using patient admission data, the model accurately identifies key risk and protective factors for COVID-19 outcomes. Our findings indicate that certain patient characteristics, such as high Charlson Index and pre-existing conditions, significantly influence the risk of ICU admission and mortality. Moreover, we introduce an explanatory model that elucidates the interrelationships among these factors, demonstrating the influence of therapeutic limits on the overall risk assessment of COVID-19 patients. Overall, our research provides a significant contribution to the field of Machine Learning by offering a novel solution for multiclass classification in the context of imbalanced datasets. This model not only enhances predictive accuracy but also supports critical decision-making processes in healthcare, potentially improving patient outcomes and optimizing clinical resource allocation., Competing Interests: Declarations Conflict of interest The authors declare no potential conflict of interests nor competing interests.github.com/RosDelgado/MTh Code availability The computer programming code (R function) that has been developed and utilized in this study, to implement Algorithm 1 (the Multi-Thresholding meta-algorithm, MTh) is accessible under an open-access (MIT) license. You can find it at https://github.com/RosDelgado/MTh. Ethical implications The use of predictive models in clinical settings raises several important ethical considerations. First and foremost, privacy and data security are critical: patient data used for training and validating models must be protected, and all practices must comply with data protection regulations. Second, it is essential to address potential biases within the model to ensure that predictions are equitable across different patient groups and to prevent discrimination in care. Third, predictive models should be used to complement, rather than replace, clinical judgment. It is important to be transparent about the limitations and uncertainties inherent in the model’s predictions. Lastly, patients should be adequately informed about the use of predictive models in their care. Clear communication is necessary to help patients to understand how these models influence clinical decisions., (© 2024. The Author(s).)