ABSTRACT
Background: The recent use of artificial intelligence (AI) in medical research is noteworthy. However, most research has focused on medical imaging. Although the importance of laboratory tests in the clinical field is acknowledged by clinicians, they are undervalued in medical AI research. Our study aims to develop an early prediction AI model for pneumonia mortality, primarily using laboratory test results. Materials and methods: We developed a mortality prediction model using initial laboratory results and basic clinical information of patients with pneumonia. Several machine learning (ML) models and a deep learning method-multilayer perceptron (MLP)-were selected for model development. The area under the receiver operating characteristic curve (AUROC) and F1-score were optimized to improve model performance. In addition, an ensemble model was developed by blending several models to improve the prediction performance. We used 80,940 data instances for model development. Results: Among the ML models, XGBoost exhibited the best performance (AUROC = 0.8989, accuracy = 0.88, F1-score = 0.80). MLP achieved an AUROC of 0.8498, accuracy of 0.86, and F1-score of 0.75. The performance of the ensemble model was the best among the developed models, with an AUROC of 0.9006, accuracy of 0.90, and F1-score of 0.81. Several laboratory tests were conducted to identify risk factors that affect pneumonia mortality using the "Feature importance" technique and SHapley Additive exPlanations. We identified several laboratory results, including systolic blood pressure, serum glucose level, age, aspartate aminotransferase-to-alanine aminotransferase ratio, and monocyte-to-lymphocyte ratio, as significant predictors of mortality in patients with pneumonia. Conclusions: Our study demonstrates that the ensemble model, incorporating XGBoost, CatBoost, and LGBM techniques, outperforms individual ML and deep learning models in predicting pneumonia mortality. Our findings emphasize the importance of integrating AI techniques to leverage laboratory test data effectively, offering a promising direction for advancing AI applications in medical research and clinical decision-making.
ABSTRACT
BACKGROUND: The decision to discontinue intensive care unit (ICU) treatment during the end-oflife stage has recently become a significant concern in Korea, with an observed increase in life-sustaining treatment (LST) withdrawal. There is a growing demand for evidence-based support for patients, families, and clinicians in making LST decisions. This study aimed to identify factors influencing LST decisions in ICU inpatients and to analyze their impact on healthcare utilization. METHODS: We retrospectively reviewed medical records of ICU patients with neurological disorders, infectious disorders, or cancer who were treated at a single university hospital between January 1, 2019 and July 7, 2021. Factors influencing the decision to withdraw LST were compared between those who withdrew LST and those who did not. RESULTS: Among 54,699 hospital admissions, LST was withdrawn in 550 cases (1%). Cancer was the most common diagnosis, followed by pneumonia and cerebral infarction. Among ICU inpatients, LST was withdrawn from 215 (withdrawal group). The withdrawal group was older (78 vs. 75 years, P=0.002), had longer total hospital stays (16 vs. 11 days, P<0.001), and higher ICU readmission rates than the control group. There were no significant differences in the healthcare costs of ICU stay between the two groups. Most LST decisions (86%) were made by family. CONCLUSIONS: The decisions to withdraw LST of ICU inpatients were influenced by age, readmission, and disease category. ICU costs were similar between the withdrawal and control groups. Further research is needed to tailor LST decisions in the ICU.