Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Acute Pancreatitis II: Clinical Manifestations and Management

Acute Pancreatitis II: Clinical Manifestations and Management

Acute pancreatitis presents a complex medical emergency characterized by rapid onset inflammation of the pancreas, demanding timely diagnosis and management to prevent complications. The condition primarily manifests through severe upper abdominal pain that often radiates to the back. This pain intensifies following the consumption of fatty foods. Accompanying symptoms such as nausea, vomiting, abdominal distention, fever, dyspnea, cyanosis, and jaundice can vary in intensity but significantly...

Acute Pancreatitis I: Introduction

Acute Pancreatitis I: Introduction

Pancreatitis is inflammation of the pancreas, an organ located behind the stomach. It can be either acute or chronic.
Acute pancreatitis is characterized by rapid inflammation of the pancreas, often caused by factors like gallstone blockage or excessive alcohol consumption. Chronic pancreatitis, on the other hand, is a slow, progressive inflammation that may result from long-term alcohol abuse, obstructions in the pancreatic duct, or genetic factors.
The causes of acute pancreatitis include:

Acute Pancreatitis I: Introduction

Acute Pancreatitis I: Introduction

Acute pancreatitis is the sudden inflammation of the pancreas caused by the early activation of digestive enzymes, leading to the autodigestion of pancreatic tissue. This results in local inflammation and, in severe cases, systemic complications.EtiologyUnderstanding the underlying causes is crucial, as identifying the etiology guides treatment and anticipates complications. Acute pancreatitis can be triggered by various factors, typically grouped into the following clinical categories.Biliary...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Set-Regulation Performance of High-Temperature Hydration in Silicate/Aluminate Cements by Phosphorus-Doped Carbon Dot Polymers.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

Prognostic model of patients with acute pancreatitis based on prothrombin time-international normalized ratio to albumin ratio: a single-center retrospective study.

PeerJ·2026

Same author

Efficacy and safety of baloxavir marboxil vs. oseltamivir in Chinese outpatients with influenza B: an IPTW-adjusted real-world cohort study.

Naunyn-Schmiedeberg's archives of pharmacology·2026

Same author

Beyond 2D and CNNs: Future Directions for Deep Learning in Periodontal Diagnostics.

International dental journal·2026

Same author

Supramolecular Polymer-Based Delayed Crosslinking Weighted Fracturing Fluid with a Double Network for Ultra-Deep Reservoirs.

Gels (Basel, Switzerland)·2026

Same author

Development and Performance Evaluation of a Core-Shell Structure Gel Plugging Agent for Ultra-High-Temperature and High-Salinity Water-Based Drilling Fluids.

Gels (Basel, Switzerland)·2026

Search research articles

Related Experiment Videos

An interpretable XGboost algorithm for predicting 30-day mortality in acute pancreatitis using routine biomarkers.

Jun Zhou^1,2, Ying Chen^1,2, Jingping Liu^1,2

¹Department of Laboratory Medicine, the First Affiliated Hospital With Nanjing Medical University, Nanjing, Jiangsu, China.

BMC Medical Research Methodology

|June 25, 2026

Summary

This study developed a machine learning model to predict 30-day mortality in acute pancreatitis (AP) patients using five key lab parameters. The XGboost algorithm demonstrated strong predictive performance, offering a potential tool for risk stratification.

Keywords:

30-day mortality Acute pancreatitis Biomarker Machine learning Prediction model

Related Experiment Videos

Area of Science:

Medical Informatics
Machine Learning in Healthcare
Clinical Prediction Models

Background:

Acute pancreatitis (AP) poses a significant mortality risk.
Accurate prediction of 30-day mortality in AP is crucial for timely intervention.
Existing prognostic scores may have limitations in predicting AP outcomes.

Purpose of the Study:

To develop and validate a machine learning (ML) algorithm for predicting 30-day mortality in adult AP patients.
To identify key laboratory parameters for accurate mortality prediction.
To create an interpretable ML model for clinical utility.

Main Methods:

Retrospective analysis of 965 AP patients.
Feature selection using Least Absolute Shrinkage and Selection Operator (LASSO) regression.
Evaluation of eleven ML algorithms, with performance assessed by AUC.
Model interpretation using SHapley additive explanation (SHAP).

Main Results:

Extreme gradient boosting (XGboost) showed the best performance.
Key predictors identified: creatine kinase (CK), lactate dehydrogenase (LDH), age, prothrombin time (PT), and carbohydrate antigen 19-9 (CA19-9).
A five-feature XGboost model achieved high AUC (1.000 development, 0.847 validation).

Conclusions:

An interpretable XGboost algorithm using five parameters can predict 30-day mortality in AP.
The model shows promising internal performance but requires external validation.
A research prototype is available, but not for clinical decision-making.