Predicting 30-day mortality in hospitalized patients with community-acquired pneumonia using statistical and machine learning approaches.

Abstract

Background: Predicting if a hospitalized patient with community-acquired pneumonia (CAP) will or will not survive after admission to the hospital is important for research purposes as well as for institution of early patient management interventions. Although population-level mortality prediction scores for these patients have been around for many years, novel patient-level algorithms are needed. The objective of this study was to assess several statistical and machine learning models for their ability to predict 30-day mortality in hospitalized patients with CAP. Methods: This was a secondary analysis of the University of Louisville (UofL) Pneumonia Study database. Six different statistical and/or machine learning methods were used to develop patientlevel prediction models for hospitalized patients with CAP. For each model, nine different statistics were calculated to provide measures of the overall performance of the models. Results: A total of 3249 unique hospitalized patients with CAP were enrolled in the study, 2743 were included in the model building (training) dataset, while the remaining 686 were included in the testing dataset. From the full population, death at 30-days post discharge was documented in 458 (13.4%) patients. All models resulted in high variation in the ability to predict survivors and non-survivors at 30 days. Conclusions: In conclusion, this study suggests that accurate patient-level prediction of 30-day mortality in hospitalized patients with CAP is difficult with statistical and machine learning approaches. It will be important to evaluate novel variables and other modeling approaches to better predict poor clinical outcomes in these patients to ensure early and appropriate interventions are instituted.

Severity of disease and mortality for hospitalized patients with community-acquired viral pneumonia compared to patients with community-acquired bacterial pneumonia

“…A patient was defined as having CAP when the following 3 criteria were met: 1) presence of a new pulmonary infiltrate on chest radiograph and/or chest computed tomography scan at the time of hospitalization, defined by a board-certified radiologist's reading; 2) at least 1 of the following: a) new cough or increased cough or sputum production, b) fever >37.8°C (100.0°F) or hypothermia <35.6°C (96.0°F), c) changes in leukocyte count (leukocytosis: >11000 cells/μL; left shift: >10% band forms/mL; or leukopenia: <4000 cells/μL); and 3) no alternative diagnosis at the time of hospital discharge that justified the presence of criteria 1 and 2 [14].…”

Medical Big Data Analytics Using Machine Learning Algorithms

“…Classifiers such a naive Bayesian classifier, adaptive Bayesian network, and SVM was tested for performance and found that adaptive Bayesian network showed accuracy, sensitivity and specificity of 100% each respectively.The study Chen et al [33] reported that SVM with z score showed accuracy 84%, sensitivity 60% and specificity of 96% respectively. Study by Wiemken et al [42] analysed statistical and machine learning algorithm in prediction re-hospitalisation within 30 days among pneumonia patients. Datasets were obtained from hospital which included 3249 patients suffering from pneumonia.…”

Main factors influencing recovery in MERS Co-V patients using machine learning

“…Naives Bayes is based on the assumption that the factors of the dataset considered are in no way related to one another. It is based on Bayes' theorem which computes the conditional probability of the classification result based on independent factors [23]. Conditional probability is computed as shown in Eq.…”