Machine learning for prediction of in-hospital mortality in lung cancer patients admitted to intensive care unit

The in-hospital mortality in lung cancer patients admitted to intensive care unit (ICU) is extremely high. This study intended to adopt machine learning algorithm models to predict in-hospital mortality of critically ill lung cancer for providing relative information in clinical decision-making. Dat...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2023-01, Vol.18 (1), p.e0280606-e0280606
Main Authors: Huang, Tianzhi, Le, Dejin, Yuan, Lili, Xu, Shoujia, Peng, Xiulan
Format: Article
Language:English
Subjects:
Accuracy
Albumins
Algorithms
Analysis
Artificial intelligence
Bilirubin
Biology and Life Sciences
Cancer
Cancer patients
China
Computer and Information Sciences
Critical Illness
Critically ill
Data mining
Decision making
Decision trees
Disease prevention
Engineering and Technology
Feature extraction
Heart failure
Hospital Mortality
Hospital patients
Humans
Intensive care
Intensive Care Units
Learning algorithms
Lung cancer
Lung diseases
Lung Neoplasms
Machine Learning
Medical advice systems
Medical prognosis
Medicine and Health Sciences
Modelling
Mortality
Oncology, Experimental
Online databases
Patient admissions
Patient outcomes
Patients
Performance evaluation
Performance prediction
Physical Sciences
Prognosis
Regression analysis
Research and Analysis Methods
Sepsis
Training
Ventilators
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The in-hospital mortality in lung cancer patients admitted to intensive care unit (ICU) is extremely high. This study intended to adopt machine learning algorithm models to predict in-hospital mortality of critically ill lung cancer for providing relative information in clinical decision-making. Data were extracted from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) for a training cohort and data extracted from the Medical Information Mart for eICU Collaborative Research Database (eICU-CRD) database for a validation cohort. Logistic regression, random forest, decision tree, light gradient boosting machine (LightGBM), eXtreme gradient boosting (XGBoost), and an ensemble (random forest+LightGBM+XGBoost) model were used for prediction of in-hospital mortality and important feature extraction. The AUC (area under receiver operating curve), accuracy, F1 score and recall were used to evaluate the predictive performance of each model. Shapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance of each feature. Overall, there were 653 (24.8%) in-hospital mortality in the training cohort, and 523 (21.7%) in-hospital mortality in the validation cohort. Among the six machine learning models, the ensemble model achieved the best performance. The top 5 most influential features were the sequential organ failure assessment (SOFA) score, albumin, the oxford acute severity of illness score (OASIS) score, anion gap and bilirubin in random forest and XGBoost model. The SHAP summary plot was used to illustrate the positive or negative effects of the top 15 features attributed to the XGBoost model. The ensemble model performed best and might be applied to forecast in-hospital mortality of critically ill lung cancer patients, and the SOFA score was the most important feature in all models. These results might offer valuable and significant reference for ICU clinicians' decision-making in advance.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0280606