Predicting 30-day mortality of patients with pneumonia in an emergency department setting using machine-learning models

Abstract

Objective This study aimed to confirm the accuracy of a machine-learning-based model in predicting the 30-day mortality of patients with pneumonia and evaluating whether they were required to be admitted to the intensive care unit (ICU). Methods The study conducted a retrospective analysis of pneumonia patients at an emergency department (ED) in Seoul, Korea, from January 1, 2016 to December 31, 2017. Patients aged 18 years or older with a pneumonia registry designation on their electronic medical record were enrolled. We collected their demographic information, mental status, and laboratory findings. Three models were used: the pre-existing CURB-65 model, and the CURB-RF and Extensive CURB-RF models, which were machine-learning models that used a random forest algorithm. The primary outcomes were ICU admission from the ED or 30-day mortality. Receiver operating characteristic curves were constructed for the models, and the areas under these curves were compared. Results Out of the 1,974 pneumonia patients, 1,732 patients were eligible to be included in the study; from these, 473 patients died within 30 days or were initially admitted to the ICU from the ED. The area under receiver operating characteristic curves of CURB-65, CURB-RF, and extensive-CURB-RF were 0.615 (0.614-0.616), 0.701 (0.700-0.702), and 0.844 (0.843-0.845), respectively. Conclusion The proposed machine-learning models could predict the mortality of patients with pneumonia more accurately than the pre-existing CURB-65 model and can help decide whether the patient should be admitted to the ICU.

Performance of Machine Learning Algorithms for Predicting Adverse Outcomes in Community-Acquired Pneumonia

“…At present, only a few studies have reported the application of machine learning in pneumonia-related studies. And several studies have employed machine learning methods to predict mortality from pneumonia ( Cooper et al, 1997 ; Wiemken et al, 2017 ; Kang et al, 2020 ), while other adverse outcomes have received less attention, especially one-year post-enrollment status. Feng et al built a three-layer fully connected neural network to classify the prognosis of CAP patients with high accuracy and good generalizability by using ML techniques to predict CAP mortality ( Feng et al, 2021 ).…”

Real‐time interactive artificial intelligence of things–based prediction for adverse outcomes in adult patients with pneumonia in the emergency department

“…We Sequential Organ Failure Assessment (SOFA; 0.670, p < 0.001), and q-SOFA (0.642, p < 0.001). 14 Another study by Kang et al 15 recruited 1,732 adult patients with pneumonia in an ED. These investigators also reported that the AUC of their ML model was 0.844, better than CURB-65 with an AUC of 0.615.…”

Pneumonia Update for Emergency Clinicians

“…The authors of a recent Korean study found that combining procalcitonin level with pneumonia severity index was better at predicting short-term mortality than PCI alone [ 6 ]. There are studies looking at using machine-learning models, using data and algorithms helping computer programs to improve overtime to predict mortality of patients with pneumonia in the emergency department [ 26 ]. Since pneumonia caused by MDRO organisms, such as P. aeruginosa , extended-spectrum beta-lactamase-producing Enterobacteriaceae, or MRSA tends to have a severe course, but is relatively rare, there is an interest in identifying patients at risk for this malady.…”