Authors:
Victor Monteiro Silva
;
Damires Yluska De Souza Fernandes
and
Alex Sandro Da Cunha Rêgo
Affiliation:
Federal Institute of Paraíba, João Pessoa, Brazil
Keyword(s):
Data Analysis and Prediction, CAP, Probability of Death, ROC Curve, AUC.
Abstract:
Community-acquired Pneumonia (CAP) is a serious respiratory infection that can cause life-threatening risk in people of different ages, especially in elderly inpatients. Regarding this age group, mortality rates by CAP still can reach 30% of all respiratory causes of death. In this work, we propose a machine learning approach to predict mortality risk among elderly inpatients with CAP. The approach uses real world data of elderly people with CAP from a hospital in Brazil, collected from 2018 to 2021. Based on patients data as learning features, our approach is able not only to classify patients at risk of mortality during hospitalization, but also to estimate the probability concerning the prediction. Some classification models have been examined and, among them, the best performance in terms of Area under ROC Curve (AUC) value has been achieved by the Logistic Regression (LR) classifier (AUC=0.81). Accomplished results show that the presented approach outperforms CURB-65 score as ba
seline in terms of both AUC values and probability of patient death. Besides, our approach is able to output probabilities ranging from 50 to 99% w.r.t. positive classification, i.e., patients that may come to death. A statistical test confirms that the presented approach outperforms the baseline provided by the CURB-65.
(More)