Assessing in-hospital mortality risk in ICU lung cancer patients using machine learning: An analysis based on the MIMIC-IV database

Jianwei Wang, Lizhen Lin, Li-ping Qiu, Li-lan Zheng, Lu-xi Wu, Hui Lv, Haihua Xie

Abstract

Patients with advanced lung cancer admitted to the intensive care unit (ICU) face a substantially elevated risk of in-hospital mortality. Early identification of high-risk individuals is essential to support timely clinical decision-making.

Introduction

Lung cancer is a leading cause of cancer-related mortality worldwide, with a significant number of patients facing poor prognoses due to diagnoses made at advanced stages and inadequate treatment options [1–3]. The prognosis for lung cancer patients in the intensive care unit (ICU) is particularly bleak, with studies indicating in-hospital mortality rates that can be as high as 69% [4].

Materials and methods

This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV, v2.2) (https://physionet.org/content/mimiciv/2.1/) [16,17], a clinical database that includes 730,141 ICU admissions from Beth Israel Deaconess Medical Center between 2008 and 2019, located in the United States.

Results

Following a thorough screening process, a cohort of 1,755 patients from the MIMIC-IV database was identified for inclusion in this study, of which 368 individuals (21%) died after admission to the ICU.

Discussion

In contemporary healthcare, the accurate prediction of in – hospital mortality for intensive care unit (ICU) patients with advanced lung cancer is of paramount importance. This study, leveraging the rich data within the Medical Information Mart for Intensive Care – IV (MIMIC – IV) database, aimed to develop and validate machine learning (ML) models for this purpose.

Conclusion

In a clinical setting, especially at the bedside, healthcare providers need quick and easy – to – use tools for risk assessment. While the XGBoost model demonstrated the best performance in predicting in – hospital mortality among critically ill lung cancer patients, it may be complex for immediate use in a busy ICU environment.

Citation: Wang J, Lin L, Qiu L-p, Zheng L-l, Wu L-x, Lv H, et al. (2026) Assessing in-hospital mortality risk in ICU lung cancer patients using machine learning: An analysis based on the MIMIC-IV database. PLoS One 21(1): e0341259. https://doi.org/10.1371/journal.pone.0341259

Editor: Miquel Vall-llosera Camps, PLOS ONE, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND

Received: July 6, 2025; Accepted: January 5, 2026; Published: January 22, 2026

Copyright: © 2026 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All data are available from the Medical Information Mart for Intensive Care-IV (MIMIC-IV, v2.2) (https://physionet.org/content/mimiciv/2.1/).

Funding: The author(s) received no specific funding for this work.

Competing interests: The authors have declared that no competing interests exist.