A machine learning model based on mPASS and imaging features for early assessment of clinically relevant outcomes in acute pancreatitis.
4 affiliations
- 1Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Medical Imaging Key Laboratory of Sichuan Province, No.1 South Maoyuan Road, Nanchong, Sichuan, 637001, China.
- 2The Fourth People's Hospital of Zigong City, Zigong, Sichuan, China.
- 3The Second People's Hospital of Meishan City, Meishan, Sichuan, China.
- 4Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Medical Imaging Key Laboratory of Sichuan Province, No.1 South Maoyuan Road, Nanchong, Sichuan, 637001, China. [email protected].
Abstract
Objective
To develop and validate a machine learning (ML) model based on the modified pancreatitis activity scoring system (mPASS) and imaging features for the early assessment of multiple clinically relevant outcomes in acute pancreatitis (AP).Methods
A retrospective cohort of 420 AP patients was analyzed. Of these, 310 patients from the primary center were randomly divided into a training set and an internal validation set at a 3:1 ratio; an additional 110 patients from an external hospital served as the independent testing cohort. The Friedman test was used to compare mPASS scores at various time points. The Jonckheere‑Terpstra test assessed the ordinal trend between mPASS and 2012 Revised Atlanta Classification (RAC). The ML model was developed using the age‑adjusted Charlson Comorbidity Index (aCCI), mPASS and imaging features. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and Brier scores for calibration.Results
No significant difference was found between mPASS scores at admission and 24 h post-admission (P = 1.000), but significant differences were observed at subsequent time points (all P < 0.05). The mPASS score at 72 h post-admission demonstrated the best predictive performance for the majority of clinically relevant outcomes, with only a marginal exception. A significant ordinal relationship existed between mPASS and 2012 RAC (P < 0.001). In the testing dataset, AUCs for the ML model ranged from 0.704 to 0.935, exceeding 0.80 for most outcomes. Calibration was acceptable to excellent for most endpoints, though marginal for hospital stay and limited for time to oral refeeding. Overall, the ML model achieved performance generally comparable to that of mPASS and the 2012 RAC, with a significant improvement for complications.Conclusion
Our ML model supports simultaneous multi-outcome risk assessment at this single time point. While showing promise in supporting individualized clinical decision-making, its performance warrants further refinement and prospective multicenter validation.Clinical trial number
Not applicable (This study is a retrospective analysis and does not involve any prospective health care intervention on human participants).
Related
- Inferring clinically relevant molecular subtypes of pancreatic cancer from routine histopathology using deep learning
- Explainable Multimodal Prognostic Modeling Uncovers New Clinically Relevant Pathological Features in a Multi-Institutional Pancreatic Neuroendocrine Tumor Cohort
- Internal Evaluation of a Machine Learning-Based Random Forest Model for Clinically Relevant Postoperative Pancreatic Fistula After Pancreaticoduodenectomy: Limited Incremental Value of Inflammatory–Nutritional Markers
- Large-scale proteomic characterization reveals clinically relevant subtypes of early-stage papillary thyroid cancer for prognostic prediction
- ACE2 Polymorphisms rs2285666 and rs147311723 Are Clinically Relevant Variants in SARS-CoV-2 and Mycobacterium tuberculosis Co-infection.
BibTeX
@article{tao2026machine,
title = {{A machine learning model based on mPASS and imaging features for early assessment of clinically relevant outcomes in acute pancreatitis.}},
author = {Di Tao and Xing Hui Li and You Qiang Hu and Ting Ting Liu and Zi Sheng Zhao and Jun Hui Chen and Hou Dong Zuo and Yi Fan Ji and Xiao Ming Zhang},
journal = {BMC medical informatics and decision making},
year = {2026},
month = aug,
doi = {10.1186/s12911-026-03742-4},
url = {https://europepmc.org/article/MED/42958547},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - A machine learning model based on mPASS and imaging features for early assessment of clinically relevant outcomes in acute pancreatitis.
AU - Di Tao
AU - Xing Hui Li
AU - You Qiang Hu
AU - Ting Ting Liu
AU - Zi Sheng Zhao
AU - Jun Hui Chen
AU - Hou Dong Zuo
AU - Yi Fan Ji
AU - Xiao Ming Zhang
PY - 2026
DA - 2026/08/03
JO - BMC medical informatics and decision making
DO - 10.1186/s12911-026-03742-4
UR - https://europepmc.org/article/MED/42958547
AB - Objective To develop and validate a machine learning (ML) model based on the modified pancreatitis activity scoring system (mPASS) and imaging features for the early assessment of multiple clinically relevant outcomes in acute pancreatitis (AP).Methods A retrospective cohort of 420 AP patients was analyzed. Of these, 310 patients from the primary center were randomly divided into a training set and an internal validation set at a 3:1 ratio; an additional 110 patients from an external hospital served as the independent testing cohort. The Friedman test was used to compare mPASS scores at various time points. The Jonckheere‑Terpstra test assessed the ordinal trend between mPASS and 2012 Revised Atlanta Classification (RAC). The ML model was developed using the age‑adjusted Charlson Comorbidity Index (aCCI), mPASS and imaging features. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and Brier scores for calibration.Results No significant difference was found between mPASS scores at admission and 24 h post-admission (P = 1.000), but significant differences were observed at subsequent time points (all P < 0.05). The mPASS score at 72 h post-admission demonstrated the best predictive performance for the majority of clinically relevant outcomes, with only a marginal exception. A significant ordinal relationship existed between mPASS and 2012 RAC (P < 0.001). In the testing dataset, AUCs for the ML model ranged from 0.704 to 0.935, exceeding 0.80 for most outcomes. Calibration was acceptable to excellent for most endpoints, though marginal for hospital stay and limited for time to oral refeeding. Overall, the ML model achieved performance generally comparable to that of mPASS and the 2012 RAC, with a significant improvement for complications.Conclusion Our ML model supports simultaneous multi-outcome risk assessment at this single time point. While showing promise in supporting individualized clinical decision-making, its performance warrants further refinement and prospective multicenter validation.Clinical trial number Not applicable (This study is a retrospective analysis and does not involve any prospective health care intervention on human participants).
SN - 1472-6947
ER -