Clinical explainable machine learning models for early identification of patients at risk of hospital-acquired urinary tract infection

Autor: Jakobsen, Rune Sejer, Nielsen, Thomas Dyhre, Leutscher, Peter, Koch, Kristoffer
Rok vydání: 2023
Předmět:
Zdroj: Jakobsen, R S, Nielsen, T D, Leutscher, P & Koch, K 2023, ' Clinical explainable machine learning models for early identification of patients at risk of hospital-acquired urinary tract infection ', Journal of Hospital Infection . https://doi.org/10.1016/j.jhin.2023.03.017
ISSN: 0195-6701
DOI: 10.1016/j.jhin.2023.03.017
Popis: Background: Machine learning (ML) models for early identification of patients at risk of hospital-acquired urinary tract infections (HA-UTI) may enable timely and targeted preventive and therapeutic strategies. However, clinicians are often challenged in the interpretation of the predictive outcomes provided by the ML models, which often reach different performances.Aim: To train ML models for predicting patients at risk of HA-UTI using available data from electronic health records at the time of hospital admission. We focused on the performance of different ML models and clinical explainability.Methods: This retrospective study investigated patient data representing 138.560 hospital admissions in the North Denmark Region from 01.01.2017 to 31.12.2018. We extracted 51 health socio-demographic and clinical features in a full dataset and used the χ2 test in addition to expert knowledge for feature selection, resulting in two reduced datasets. Seven different ML models were trained and compared between the three datasets. We applied the SHapley Additive exPlanation (SHAP) method to support population- and patient-level explainability.Findings: The best-performing ML model was a neural network based on the full dataset, reaching an area under the curve (AUC) of 0.758. The neural network was also the best-performing ML model based on the reduced datasets, reaching an AUC of 0.746. Clinical explainability was demonstrated with a SHAP summary- and forceplot.Conclusion: Within 24h of hospital admission, the ML models were able to identify patients at risk of developing HA-UTI, providing new opportunities to develop efficient strategies for the prevention of HA-UTI. Using SHAP, we demonstrate how risk predictions can be explained at individual patient level and for the patient population in general. Background: Machine learning (ML) models for early identification of patients at risk of hospital-acquired urinary tract infections (HA-UTI) may enable timely and targeted preventive and therapeutic strategies. However, clinicians are often challenged in the interpretation of the predictive outcomes provided by the ML models, which often reach different performances.Aim: To train ML models for predicting patients at risk of HA-UTI using available data from electronic health records at the time of hospital admission. We focused on the performance of different ML models and clinical explainability.Methods: This retrospective study investigated patient data representing 138.560 hospital admissions in the North Denmark Region from 01.01.2017 to 31.12.2018. We extracted 51 health socio-demographic and clinical features in a full dataset and used the χ2 test in addition to expert knowledge for feature selection, resulting in two reduced datasets. Seven different ML models were trained and compared between the three datasets. We applied the SHapley Additive exPlanation (SHAP) method to support population- and patient-level explainability.Findings: The best-performing ML model was a neural network based on the full dataset, reaching an area under the curve (AUC) of 0.758. The neural network was also the best-performing ML model based on the reduced datasets, reaching an AUC of 0.746. Clinical explainability was demonstrated with a SHAP summary- and forceplot.Conclusion: Within 24h of hospital admission, the ML models were able to identify patients at risk of developing HA-UTI, providing new opportunities to develop efficient strategies for the prevention of HA-UTI. Using SHAP, we demonstrate how risk predictions can be explained at individual patient level and for the patient population in general.
Databáze: OpenAIRE
Externí odkaz: