Advanced search
Publication Cover
International Journal of General Medicine Volume 14, 2021 - Issue
Submit an article Journal homepage
158
Views
6
CrossRef citations to date
0
Altmetric
Original Research

A Comprehensive Way to Access Hospital Death Prediction Model for Acute Mesenteric Ischemia: A Combination of Traditional Statistics and Machine Learning

Wenhan Wu1 Institute of Digestive Surgery of Sichuan University, Chengdu, 610041, Sichuan;2 Department of Gastrointestinal Surgery, West China Hospital, West China School of Medicine, Sichuan University, Chengdu, 610041, SichuanORCID Iconhttps://orcid.org/0000-0002-4284-9016
ORCID Icon &
Zongguang Zhou1 Institute of Digestive Surgery of Sichuan University, Chengdu, 610041, Sichuan;2 Department of Gastrointestinal Surgery, West China Hospital, West China School of Medicine, Sichuan University, Chengdu, 610041, SichuanCorrespondence[email protected]
Pages 591-602 | Published online: 25 Feb 2021

Figures & data

Figure 1 Diagram of developing AMI hospital mortality prediction models.

Figure 1 Diagram of developing AMI hospital mortality prediction models.

Table 1 Baseline Patient Demographics, Clinical and Laboratory Characteristics, and Outcomes

Table 2 Univariate Analysis for Potential Risk Factors in the Training Cohort

Table 3 Multivariate Logistic Regression Model for Hospital Mortality in the Training Cohort

Figure 2 The hospital death risk-prediction nomogram for AMI.

Figure 2 The hospital death risk-prediction nomogram for AMI.

Table 4 The Comparison of Various Machine Learning Classifiers’ Performance Using Different Variable Selection Methods in the Validation Cohort

Figure 3 Comparison of ROC curves among nomogram and machine learning classifiers for the prediction of hospital death of patients with AMI in the validation cohort.

Notes: (A) Comparison of ROC curves among three machine learning classifiers using clinical variables determined by Lasso; (B) Comparison of ROC curves among three machine learning classifiers using clinical variables determined by Boruta; (C) Comparison of ROC curves between the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) and nomogram.
Figure 3 Comparison of ROC curves among nomogram and machine learning classifiers for the prediction of hospital death of patients with AMI in the validation cohort.

Figure 4 Calibration curves for the nomogram and the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) in the validation cohort.

Notes: (A) Calibration curve for the nomogram in the validation cohort. (B) Calibration curve for the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) in the validation cohort.
Figure 4 Calibration curves for the nomogram and the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) in the validation cohort.

Figure 5 Decision curves for the nomogram and the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) in the validation cohort.

Figure 5 Decision curves for the nomogram and the optimal machine learning classifier (XGBoost using clinical variables determined by Boruta) in the validation cohort.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.