Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases

Abstract

Pancreatic necrosis is a consistent prognostic factor in acute pancreatitis (AP). However, the clinical scores currently in use are either too complicated or require data that are unavailable on admission or lack sufficient predictive value. We therefore aimed to develop a tool to aid in necrosis prediction. The XGBoost machine learning algorithm processed data from 2387 patients with AP. The confidence of the model was estimated by a bootstrapping method and interpreted via the 10th and the 90th percentiles of the prediction scores. Shapley Additive exPlanations (SHAP) values were calculated to quantify the contribution of each variable provided. Finally, the model was implemented as an online application using the Streamlit Python-based framework. The XGBoost classifier provided an AUC value of 0.757. Glucose, C-reactive protein, alkaline phosphatase, gender and total white blood cell count have the most impact on prediction based on the SHAP values. The relationship between the size of the training dataset and model performance shows that prediction performance can be improved. This study combines necrosis prediction and artificial intelligence. The predictive potential of this model is comparable to the current clinical scoring systems and has several advantages over them.

Gut microbiota on admission as predictive biomarker for acute necrotizing pancreatitis

“…However, these clinical laboratory items are likely to fail considering they are not specific for the complex pathophysiology of NP. A research team recently used machine learning strategy to process data from 2387 AP patients measured in the first 24h of clinical admission ( 36 ). They released an on-admission prediction model for NP online which stressed the impacts of gender, total white blood cell count, glucose, alkaline phosphatase, and CRP.…”

Acute pancreatitis: A review of diagnosis, severity prediction and prognosis assessment from imaging technology, scoring system and artificial intelligence

“…Zhou et al [ 155 ] demonstrated that the XGBoost algorithm possesses the capability to precisely predict the severity of AP, offering clinicians valuable assistance in identifying severe AP at an early stage. In a prospective cohort study integrating necrosis prediction with AI, the XGBoost machine learning algorithm was employed to analyze the data from 2387 AP patients[ 156 ]. This model in the predictive capability rivals those existing clinical scoring systems, and its performance is anticipated to improve with continued use[ 156 ].…”

“…In a prospective cohort study integrating necrosis prediction with AI, the XGBoost machine learning algorithm was employed to analyze the data from 2387 AP patients[ 156 ]. This model in the predictive capability rivals those existing clinical scoring systems, and its performance is anticipated to improve with continued use[ 156 ]. In the United States, Thapa et al [ 7 ] applied machine learning algorithms to predict which AP patients need SAP treatment and developed three models using logistic regression, neural networks, and XGBoost.…”

Persistently High Procalcitonin and C-Reactive Protein Are Good Predictors of Infection in Acute Necrotizing Pancreatitis: A Systematic Review and Meta-Analysis

“…AP is an inflammatory condition, thus exhibiting systemic manifestations of inflammation, including fever, tachycardia, hypotension, elevated white blood cell count (WBC), and increased levels of C-reactive protein (CRP) [5][6][7]. These characteristics do not differentiate between inflammation and infection, leading to an excessive utilization of antibiotics across the entire range of disease severity without distinguishing between the two [8].…”