Machine learning for the rElapse risk eValuation in acute biliary pancreatitis: The deep learning MINERVA study
Mauro Podda1, Adolfo Pisanu2, Gianluca Pellino3,4
1Department of Surgical Science, Emergency Surgery Unit, University of Cagliari, Cagliari, Italy. mauro.podda@unica.it.
Background:
Mild acute biliary pancreatitis (MABP) presents significant clinical and economic challenges due to its potential for relapse. Current guidelines advocate for early cholecystectomy (EC) during the same hospital admission to prevent recurrent acute pancreatitis (RAP). Despite these recommendations, implementation in clinical practice varies, highlighting the need for reliable and accessible predictive tools. The MINERVA study aims to develop and validate a machine learning (ML) model to predict the risk of RAP (at 30, 60, 90 days, and at 1-year) in MABP patients, enhancing decision-making processes.
Methods:
The MINERVA study will be conducted across multiple academic and community hospitals in Italy. Adult patients with a clinical diagnosis of MABP, in accordance with the revised Atlanta Criteria, who have not undergone EC during index admission will be included. Exclusion criteria encompass non-biliary aetiology, severe pancreatitis, and the inability to provide informed consent. The study involves both retrospective data from the MANCTRA-1 study and prospective data collection. Data will be captured using REDCap. The ML model will utilise convolutional neural networks (CNN) for feature extraction and risk prediction. The model includes the following steps: the spatial transformation of variables using kernel Principal Component Analysis (kPCA), the creation of 2D images from transformed data, the application of convolutional filters, max-pooling, flattening, and final risk prediction via a fully connected layer. Performance metrics such as accuracy, precision, recall, and area under the ROC curve (AUC) will be used to evaluate the model.
Discussion:
The MINERVA study aims to address the specific gap in predicting RAP risk in MABP patients by leveraging advanced ML techniques. By incorporating a wide range of clinical and demographic variables, the MINERVA score aims to provide a reliable, cost-effective, and accessible tool for healthcare professionals. The project emphasises the practical application of AI in clinical settings, potentially reducing the incidence of RAP and associated healthcare costs.
Trial Registration:
ClinicalTrials.gov ID: NCT06124989.
Insights
This study develops a machine learning model to predict recurrent acute pancreatitis (RAP) in mild acute biliary pancreatitis (MABP) patients. The MINERVA model aims to improve clinical decisions and reduce healthcare costs associated with RAP.
Area of Science:
- Medical Informatics
- Machine Learning in Healthcare
- Gastroenterology
Background:
- Mild acute biliary pancreatitis (MABP) poses significant clinical and economic burdens due to potential relapse.
- Current guidelines recommend early cholecystectomy (EC) to prevent recurrent acute pancreatitis (RAP), but practice varies.
- There is a need for reliable tools to predict RAP risk in MABP patients.
Purpose of the Study:
- To develop and validate a machine learning (ML) model to predict the risk of RAP in MABP patients.
- To enhance clinical decision-making for MABP management.
- To provide a reliable, cost-effective, and accessible predictive tool for healthcare professionals.
Main Methods:
- The MINERVA study will collect retrospective and prospective data from adult MABP patients not undergoing EC during index admission.
- A machine learning model using convolutional neural networks (CNN) will be developed for risk prediction.
- The model involves data transformation (kPCA), image creation, convolutional filtering, and risk assessment using performance metrics like AUC.
Main Results:
- The study aims to validate the ML model's performance in predicting RAP at 30, 60, 90 days, and 1-year.
- Performance metrics including accuracy, precision, recall, and AUC will be used for evaluation.
- The developed MINERVA score is expected to offer reliable risk stratification.
Conclusions:
- The MINERVA study addresses the gap in predicting RAP risk in MABP patients using advanced ML.
- The practical application of AI in clinical settings can potentially reduce RAP incidence and healthcare costs.
- The MINERVA score aims to be a valuable tool for optimizing MABP patient care.
More Related Videos
Related Concept Videos
01:30Acute Pancreatitis II: Clinical Manifestations and Management
01:29Chronic Pancreatitis II: Collaborative Care
Assessment:
01:27Acute Pancreatitis I: Introduction
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:
01:24Chronic Pancreatitis I: Introduction
Pancreatitis is the inflammation of the pancreas, which occurs when the immune system becomes active and causes swelling, pain, and disruptions in organ function. Pancreatitis can manifest as either an acute or chronic condition.
Acute pancreatitis arises suddenly and lasts for a brief duration, while chronic pancreatitis is a long-term affliction...