JOURNAL ARTICLE
Development and Evaluation of Machine Learning Models and Nomogram for the Prediction of Severe Acute Pancreatitis.
Journal of Gastroenterology and Hepatology 2023 January 19
BACKGROUND AND AIM: Severe acute pancreatitis (SAP) in patients progresses rapidly, and can cause multiple organ failures associated with high mortality. We aimed to train a machine learning (ML) model and establish a nomogram that could identify SAP, early in the course of acute pancreatitis (AP).
METHODS: In this retrospective study, 631 patients with AP were enrolled in the training cohort. For predicting SAP early, five supervised ML models were employed, such as random forest (RF), K-nearest neighbors (KNN), and naive Bayes (NB), which were evaluated by accuracy (ACC) and the areas under the receiver operating characteristic curve (AUC). The nomogram was established, and the predictive ability was assessed by the calibration curve and AUC. They were externally validated by an independent cohort of 109 patients with AP.
RESULTS: In the training cohort, the AUC of RF, KNN, and NB models were 0.969, 0.954 and 0.951, respectively, while the AUC of the Bedside Index for Severity in Acute Pancreatitis (BISAP), Ranson and Glasgow scores were only 0.796, 0.847 and 0.837, respectively. In the validation cohort, the RF model also showed the highest AUC, which was 0.961. The AUC for the nomogram was 0.888 and 0.955 in the training and validation cohort, respectively.
CONCLUSIONS: Our findings suggested that the RF model exhibited the best predictive performance, and the nomogram provided a visual scoring model for clinical practice. Our models may serve as practical tools for facilitating personalized treatment options and improving clinical outcomes through pre-treatment stratification of patients with AP.
METHODS: In this retrospective study, 631 patients with AP were enrolled in the training cohort. For predicting SAP early, five supervised ML models were employed, such as random forest (RF), K-nearest neighbors (KNN), and naive Bayes (NB), which were evaluated by accuracy (ACC) and the areas under the receiver operating characteristic curve (AUC). The nomogram was established, and the predictive ability was assessed by the calibration curve and AUC. They were externally validated by an independent cohort of 109 patients with AP.
RESULTS: In the training cohort, the AUC of RF, KNN, and NB models were 0.969, 0.954 and 0.951, respectively, while the AUC of the Bedside Index for Severity in Acute Pancreatitis (BISAP), Ranson and Glasgow scores were only 0.796, 0.847 and 0.837, respectively. In the validation cohort, the RF model also showed the highest AUC, which was 0.961. The AUC for the nomogram was 0.888 and 0.955 in the training and validation cohort, respectively.
CONCLUSIONS: Our findings suggested that the RF model exhibited the best predictive performance, and the nomogram provided a visual scoring model for clinical practice. Our models may serve as practical tools for facilitating personalized treatment options and improving clinical outcomes through pre-treatment stratification of patients with AP.
Full text links
Trending Papers
Helicobacter pylori Infection: Current Status and Future Prospects on Diagnostic, Therapeutic and Control Challenges.Antibiotics 2023 January 18
Fluid Resuscitation in Patients with Cirrhosis and Sepsis: A Multidisciplinary Perspective.Journal of Hepatology 2023 March 2
Glucagon-Like Peptide 1 Receptor Agonists Versus Sodium-Glucose Cotransporter 2 Inhibitors for Atherosclerotic Cardiovascular Disease in Patients With Type 2 Diabetes.Cardiology Research 2023 Februrary
Evaluation and Management of Pulmonary Hypertension in Noncardiac Surgery: A Scientific Statement From the American Heart Association.Circulation 2023 March 17
Physical interventions to interrupt or reduce the spread of respiratory viruses.Cochrane Database of Systematic Reviews 2023 January 31
Long COVID: major findings, mechanisms and recommendations.Nature Reviews. Microbiology 2023 January 14
What's New in the Treatment of Non-Alcoholic Fatty Liver Disease (NAFLD).Journal of Clinical Medicine 2023 Februrary 27
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app
Read by QxMD is copyright © 2021 QxMD Software Inc. All rights reserved. By using this service, you agree to our terms of use and privacy policy.
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app