Next Article in Journal
Potential of Carbohydrate Antigen 19-9 and Serum Apolipoprotein A2-Isoforms in the Diagnosis of Stage 0 and IA Pancreatic Cancer
Previous Article in Journal
Differential Functional Changes in Visual Performance during Acute Exposure to Microgravity Analogue and Their Potential Links with Spaceflight-Associated Neuro-Ocular Syndrome
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Machine Learning Models for Predicting Mortality in Patients with Cirrhosis and Acute Upper Gastrointestinal Bleeding at an Emergency Department: A Retrospective Cohort Study

by
Shih-Chien Tsai
1,†,
Ching-Heng Lin
2,3,†,
Cheng-C. J. Chu
2,
Hsiang-Yun Lo
1,
Chip-Jin Ng
1,
Chun-Chuan Hsu
1,* and
Shou-Yen Chen
1,4,*
1
Department of Emergency Medicine, Chang Gung Memorial Hospital, Chang Gung University, Linkou, Taoyuan 333, Taiwan
2
Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Linkou, Taoyuan 333, Taiwan
3
Bachelor Program in Artificial Intelligence, Chang Gung University, Taoyuan 333, Taiwan
4
Graduate Institute of Management, College of Management, Chang Gung University, Taoyuan 333, Taiwan
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work as first authors.
Diagnostics 2024, 14(17), 1919; https://doi.org/10.3390/diagnostics14171919
Submission received: 31 July 2024 / Revised: 28 August 2024 / Accepted: 29 August 2024 / Published: 30 August 2024
(This article belongs to the Special Issue Applications of Artificial Intelligence in Gastrointestinal Diseases)

Abstract

Background: Cirrhosis is a major global cause of mortality, and upper gastrointestinal (GI) bleeding significantly increases the mortality risk in these patients. Although scoring systems such as the Child–Pugh score and the Model for End-stage Liver Disease evaluate the severity of cirrhosis, none of these systems specifically target the risk of mortality in patients with upper GI bleeding. In this study, we constructed machine learning (ML) models for predicting mortality in patients with cirrhosis and upper GI bleeding, particularly in emergency settings, to achieve early intervention and improve outcomes. Methods: In this retrospective study, we analyzed the electronic health records of adult patients with cirrhosis who presented at an emergency department (ED) with GI bleeding between 2001 and 2019. Data were divided into training and testing sets at a ratio of 90:10. The ability of three ML models—a linear regression model, an XGBoost (XGB) model, and a three-layer neural network model—to predict mortality in the patients was evaluated. Results: A total of 16,025 patients with cirrhosis and 32,826 ED visits for upper GI bleeding were included in the study. The in-hospital and ED mortality rates were 11.2% and 2.2%, respectively. The XGB model exhibited the highest performance in predicting both in-hospital and ED mortality (area under the receiver operating characteristic curve: 0.866 and 0.861, respectively). International normalized ratio, renal function, red blood cell distribution width, age, and white blood cell count were the strongest predictors in all the ML models. The median ED length of stay for the ED mortality group was 17.54 h (7.16–40.01 h). Conclusions: ML models can be used to predict mortality in patients with cirrhosis and upper GI bleeding. Of the three models, the XGB model exhibits the highest performance. Further research is required to determine the actual efficacy of our ML models in clinical settings.
Keywords: machine learning; cirrhosis; gastrointestinal bleeding; emergency department; mortality machine learning; cirrhosis; gastrointestinal bleeding; emergency department; mortality

Share and Cite

MDPI and ACS Style

Tsai, S.-C.; Lin, C.-H.; Chu, C.-C.J.; Lo, H.-Y.; Ng, C.-J.; Hsu, C.-C.; Chen, S.-Y. Machine Learning Models for Predicting Mortality in Patients with Cirrhosis and Acute Upper Gastrointestinal Bleeding at an Emergency Department: A Retrospective Cohort Study. Diagnostics 2024, 14, 1919. https://doi.org/10.3390/diagnostics14171919

AMA Style

Tsai S-C, Lin C-H, Chu C-CJ, Lo H-Y, Ng C-J, Hsu C-C, Chen S-Y. Machine Learning Models for Predicting Mortality in Patients with Cirrhosis and Acute Upper Gastrointestinal Bleeding at an Emergency Department: A Retrospective Cohort Study. Diagnostics. 2024; 14(17):1919. https://doi.org/10.3390/diagnostics14171919

Chicago/Turabian Style

Tsai, Shih-Chien, Ching-Heng Lin, Cheng-C. J. Chu, Hsiang-Yun Lo, Chip-Jin Ng, Chun-Chuan Hsu, and Shou-Yen Chen. 2024. "Machine Learning Models for Predicting Mortality in Patients with Cirrhosis and Acute Upper Gastrointestinal Bleeding at an Emergency Department: A Retrospective Cohort Study" Diagnostics 14, no. 17: 1919. https://doi.org/10.3390/diagnostics14171919

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop