Early machine learning prediction of hospitalized patients at low risk of respiratory deterioration or mortality in community-acquired pneumonia: Derivation and validation of a multivariable model

Authors

  • Yewande E. Odeyemi Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States https://orcid.org/0000-0002-4446-198X
  • Amos Lal Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States image/svg+xml https://orcid.org/0000-0002-0021-2033
  • Erin F. Barreto Department of Pharmacy, Mayo Clinic, Rochester, Minnesota, United States
  • Allison M. LeMahieu Division of Clinical Trials and Biostatistics, Mayo Clinic, Rochester, Minnesota, United States https://orcid.org/0000-0003-1554-795X
  • Hemang Yadav Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States https://orcid.org/0000-0002-1889-2524
  • Ognjen Gajic Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States https://orcid.org/0000-0003-4218-0890
  • Phillip Schulte Division of Clinical Trials and Biostatistics, Mayo Clinic, Rochester, Minnesota, United States

DOI:

https://doi.org/10.17305/bb.2023.9754

Keywords:

Community-acquired pneumonia (CAP), machine learning, predictive modeling, advanced respiratory support, mortality

Abstract

Current prognostic tools for pneumonia predominantly focus on mortality, often neglecting other crucial outcomes such as the need for advanced respiratory support. The objective of this study was to develop and validate a tool that predicts the early risk of non-occurrence of respiratory deterioration or mortality. We conducted a single-center, retrospective cohort study involving hospitalized adult patients with community-acquired pneumonia (CAP) and acute hypoxic respiratory failure from January 2009 to December 2019 (n = 4379). We employed the gradient boosting machine (GBM) learning to create a model that estimates the likelihood of patients requiring advanced respiratory support (high flow nasal cannula [HFNC], non-invasive mechanical ventilation [NIMV], and invasive mechanical ventilation [IMV]) or facing mortality during hospitalization. This model utilized readily available data including demographic, physiologic, and laboratory data, sourced from electronic health records and obtained within the first six hours of admission. Out of the cohort, 890 patients (25.2%) either required advanced respiratory support or died during their hospital stay. Our predictive model displayed superior discrimination and higher sensitivity (cross-validation C-statistic = 0.71; specificity = 0.56; sensitivity = 0.72) compared to the pneumonia severity index (PSI) (C-statistic = 0.65; specificity = 0.91; sensitivity = 0.24; P value < 0.001), while maintaining a negative predictive value (NPV) of approximately 0.85. These data demonstrate that our machine learning model predicted the non-occurrence of respiratory deterioration or mortality among hospitalized CAP patients more accurately than the PSI. The enhanced sensitivity of this model holds potential for reliably excluding low-risk patients from pneumonia clinical trials.

Citations

Downloads

Download data is not yet available.
Early machine learning prediction of hospitalized patients at low-risk of respiratory deterioration or mortality in community-acquired pneumonia: Derivation and validation of a multivariable model

Downloads

Published

11-03-2024

Issue

Section

Translational and Clinical Research

Categories

How to Cite

1.
Early machine learning prediction of hospitalized patients at low risk of respiratory deterioration or mortality in community-acquired pneumonia: Derivation and validation of a multivariable model. Biomol Biomed [Internet]. 2024 Mar. 11 [cited 2024 Dec. 11];24(2):337–345. Available from: https://bjbms.org/ojs/index.php/bjbms/article/view/9754