Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients
Abstract Background Liver cirrhosis patients are at risk for esophagogastric variceal bleeding (EGVB). Herein, we aimed to estimate the EGVB risk in patients with liver cirrhosis using an artificial neural network (ANN). Methods We included 999 liver cirrhosis patients hospitalized at the Beijing Di...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-02-01
|
Series: | Diagnostic Pathology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13000-023-01293-0 |
_version_ | 1797865653570371584 |
---|---|
author | Yixin Hou Hao Yu Qun Zhang Yuying Yang Xiaoli Liu Xianbo Wang Yuyong Jiang |
author_facet | Yixin Hou Hao Yu Qun Zhang Yuying Yang Xiaoli Liu Xianbo Wang Yuyong Jiang |
author_sort | Yixin Hou |
collection | DOAJ |
description | Abstract Background Liver cirrhosis patients are at risk for esophagogastric variceal bleeding (EGVB). Herein, we aimed to estimate the EGVB risk in patients with liver cirrhosis using an artificial neural network (ANN). Methods We included 999 liver cirrhosis patients hospitalized at the Beijing Ditan Hospital, Capital Medical University in the training cohort and 101 patients from Shuguang Hospital in the validation cohort. The factors independently affecting EGVB occurrence were determined via univariate analysis and used to develop an ANN model. Results The 1-year cumulative EGVB incidence rates were 11.9 and 11.9% in the training and validation groups, respectively. A total of 12 independent risk factors, including gender, drinking and smoking history, decompensation, ascites, location and size of varices, alanine aminotransferase (ALT), γ-glutamyl transferase (GGT), hematocrit (HCT) and neutrophil-lymphocyte ratio (NLR) levels as well as red blood cell (RBC) count were evaluated and used to establish the ANN model, which estimated the 1-year EGVB risk. The ANN model had an area under the curve (AUC) of 0.959, which was significantly higher than the AUC for the North Italian Endoscopic Club (NIEC) (0.669) and revised North Italian Endoscopic Club (Rev-NIEC) indices (0.725) (all P < 0.001). Decision curve analyses revealed improved net benefits of the ANN compared to the NIEC and Rev-NIEC indices. Conclusions The ANN model accurately predicted the 1-year risk for EGVB in liver cirrhosis patients and might be used as a basis for risk-based EGVB surveillance strategies. |
first_indexed | 2024-04-09T23:12:44Z |
format | Article |
id | doaj.art-1da6e38ed9e54c4faf45553494b1e4d3 |
institution | Directory Open Access Journal |
issn | 1746-1596 |
language | English |
last_indexed | 2024-04-09T23:12:44Z |
publishDate | 2023-02-01 |
publisher | BMC |
record_format | Article |
series | Diagnostic Pathology |
spelling | doaj.art-1da6e38ed9e54c4faf45553494b1e4d32023-03-22T10:17:34ZengBMCDiagnostic Pathology1746-15962023-02-0118111010.1186/s13000-023-01293-0Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patientsYixin Hou0Hao Yu1Qun Zhang2Yuying Yang3Xiaoli Liu4Xianbo Wang5Yuyong Jiang6Center of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityCenter of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityCenter of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityInstitute of Liver Diseases, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese MedicineCenter of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityCenter of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityCenter of Integrative Medicine, Beijing Ditan Hospital, Capital Medical UniversityAbstract Background Liver cirrhosis patients are at risk for esophagogastric variceal bleeding (EGVB). Herein, we aimed to estimate the EGVB risk in patients with liver cirrhosis using an artificial neural network (ANN). Methods We included 999 liver cirrhosis patients hospitalized at the Beijing Ditan Hospital, Capital Medical University in the training cohort and 101 patients from Shuguang Hospital in the validation cohort. The factors independently affecting EGVB occurrence were determined via univariate analysis and used to develop an ANN model. Results The 1-year cumulative EGVB incidence rates were 11.9 and 11.9% in the training and validation groups, respectively. A total of 12 independent risk factors, including gender, drinking and smoking history, decompensation, ascites, location and size of varices, alanine aminotransferase (ALT), γ-glutamyl transferase (GGT), hematocrit (HCT) and neutrophil-lymphocyte ratio (NLR) levels as well as red blood cell (RBC) count were evaluated and used to establish the ANN model, which estimated the 1-year EGVB risk. The ANN model had an area under the curve (AUC) of 0.959, which was significantly higher than the AUC for the North Italian Endoscopic Club (NIEC) (0.669) and revised North Italian Endoscopic Club (Rev-NIEC) indices (0.725) (all P < 0.001). Decision curve analyses revealed improved net benefits of the ANN compared to the NIEC and Rev-NIEC indices. Conclusions The ANN model accurately predicted the 1-year risk for EGVB in liver cirrhosis patients and might be used as a basis for risk-based EGVB surveillance strategies.https://doi.org/10.1186/s13000-023-01293-0ALTArtificial neural networkAscitesGastroesophageal varicesGGHematocrit |
spellingShingle | Yixin Hou Hao Yu Qun Zhang Yuying Yang Xiaoli Liu Xianbo Wang Yuyong Jiang Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients Diagnostic Pathology ALT Artificial neural network Ascites Gastroesophageal varices GG Hematocrit |
title | Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
title_full | Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
title_fullStr | Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
title_full_unstemmed | Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
title_short | Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
title_sort | machine learning based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients |
topic | ALT Artificial neural network Ascites Gastroesophageal varices GG Hematocrit |
url | https://doi.org/10.1186/s13000-023-01293-0 |
work_keys_str_mv | AT yixinhou machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT haoyu machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT qunzhang machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT yuyingyang machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT xiaoliliu machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT xianbowang machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients AT yuyongjiang machinelearningbasedmodelforpredictingtheesophagogastricvaricealbleedingriskinlivercirrhosispatients |