Creative Commons source reading · Data quality and algorithm evaluation
Development of interpretable machine learning models for predicting the probability of sepsis in patients with pulmonary fibrosis in the intensive care unit: based on MIMIC-IV and multi-database validation
Xia Y; Yang J
Originally published in Front Cell Infect Microbiol · 2026-09-07
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractBackgroundLimited by small sample size, single-institution design, and insufficient comprehensive external validation across heterogeneous healthcare systems, no study to date has systematically validated the predictive performance of machine learning models for sepsis occurrence in an intensive care unit (ICU) population with concomitant pulmonary fibrosis through multiple large-scale databases.MethodsThis retrospective multi-database study utilized two large databases to establish and validate a machine learning model for predicting the probability of sepsis occurrence in ICU patients with pulmonary fibrosis. In this study, 542 patients from the MIMIC-IV database were divided into a training set (381 patients) and an internal validation set (161 patients) in a 7:3 ratio, and external validation was performed on the MIMIC-III…
Discussion
Patients with pulmonary fibrosis in the ICU represent a special population with an extremely severe prognosis. Pulmonary fibrosis is characterized pathologically by progressive interstitial collagen deposition and irreversible gas exchange impairment, which severely limits patients’ compensatory capacity against infectious insults (Warheit-Niemi et al., 2022; Singh et al., 2025). Once sepsis is superimposed, patients with pulmonary fibrosis face a higher risk of mortality and requirement for invasive mechanical ventilation, and acute exacerbation of IPF itself can have systemic consequences, causing extra-pulmonary organ failure (Zhuang et al., 2020). However, previous studies have rarely focused on the ICU population with pulmonary fibrosis, and to date, no study has systematically validated the predictive performance of machine…
Conclusion
This study is the first to develop and validate a machine learning model for predicting sepsis in ICU patients with pulmonary fibrosis across multiple databases. The ANN model, combined with SHAP interpretability, provides a reliable decision-making tool for clinical decision support, and its consistency has been verified in two databases, including our internal validation cohort.
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
