The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer
Abstract Purpose To develop and validate a hybrid radiomics model to predict the overall survival in pancreatic cancer patients and identify risk factors that affect patient prognosis. Methods We conducted a retrospective analysis of 272 pancreatic cancer patients diagnosed at the First Affiliated H...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Gastroenterology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12876-025-04119-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234628584407040 |
|---|---|
| author | Zheng Dou Jiaxi Lin Chenghao Lu Xiaoting Ma Ruoxu Zhang Jinzhou Zhu Songbing Qin Chao Xu Jinli Li |
| author_facet | Zheng Dou Jiaxi Lin Chenghao Lu Xiaoting Ma Ruoxu Zhang Jinzhou Zhu Songbing Qin Chao Xu Jinli Li |
| author_sort | Zheng Dou |
| collection | DOAJ |
| description | Abstract Purpose To develop and validate a hybrid radiomics model to predict the overall survival in pancreatic cancer patients and identify risk factors that affect patient prognosis. Methods We conducted a retrospective analysis of 272 pancreatic cancer patients diagnosed at the First Affiliated Hospital of Soochow University from January 2013 to December 2023, and divided them into a training set and a test set at a ratio of 7:3. Pre-treatment contrast-enhanced computed tomography (CT), magnetic resonance imaging (MRI) images, and clinical features were collected. Dimensionality reduction was performed on the radiomics features using principal component analysis (PCA), and important features with non-zero coefficients were selected using the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation. In the training set, we built clinical prediction models using both random survival forests (RSF) and traditional Cox regression analysis. These models included a radiomics model based on contrast-enhanced CT, a radiomics model based on MRI, a clinical model, 3 bimodal models combining two types of features, and a multimodal model combining radiomics features with clinical features. Model performance evaluation in the test set was based on two dimensions: discrimination and calibration. In addition, risk stratification was performed in the test set based on predicted risk scores to evaluate the model’s prognostic utility. Results The RSF-based hybrid model performed best with a C-index of 0.807 and a Brier score of 0.101, outperforming the COX hybrid model (C-index of 0.726 and a Brier score of 0.145) and other unimodal and bimodal models. The SurvSHAP(t) plot highlighted CA125 as the most important variable. In the test set, patients were stratified into high- and low-risk groups based on the predicted risk scores, and Kaplan–Meier analysis demonstrated a significant survival difference between the two groups (p < 0.0001). Conclusion A multi-modal model using radiomics based on clinical tabular data and contrast-enhanced CT and MRI was developed by RSF, presenting strengths in predicting prognosis in pancreatic cancer patients. |
| format | Article |
| id | doaj-art-7d4b4706468f402aa1b781a0d4e56532 |
| institution | Kabale University |
| issn | 1471-230X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Gastroenterology |
| spelling | doaj-art-7d4b4706468f402aa1b781a0d4e565322025-08-20T04:03:06ZengBMCBMC Gastroenterology1471-230X2025-08-0125111410.1186/s12876-025-04119-zThe development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancerZheng DouJiaxi Lin0Chenghao Lu1Xiaoting Ma2Ruoxu Zhang3Jinzhou Zhu4Songbing Qin5Chao Xu6Jinli Li7Department of Gastroenterology, The First Affiliated Hospital of Soochow UniversityDepartment of Gastroenterology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiation Oncology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiation Oncology, The First Affiliated Hospital of Soochow UniversityDepartment of Gastroenterology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiation Oncology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiation Oncology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiation Oncology, The First Affiliated Hospital of Soochow UniversityAbstract Purpose To develop and validate a hybrid radiomics model to predict the overall survival in pancreatic cancer patients and identify risk factors that affect patient prognosis. Methods We conducted a retrospective analysis of 272 pancreatic cancer patients diagnosed at the First Affiliated Hospital of Soochow University from January 2013 to December 2023, and divided them into a training set and a test set at a ratio of 7:3. Pre-treatment contrast-enhanced computed tomography (CT), magnetic resonance imaging (MRI) images, and clinical features were collected. Dimensionality reduction was performed on the radiomics features using principal component analysis (PCA), and important features with non-zero coefficients were selected using the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation. In the training set, we built clinical prediction models using both random survival forests (RSF) and traditional Cox regression analysis. These models included a radiomics model based on contrast-enhanced CT, a radiomics model based on MRI, a clinical model, 3 bimodal models combining two types of features, and a multimodal model combining radiomics features with clinical features. Model performance evaluation in the test set was based on two dimensions: discrimination and calibration. In addition, risk stratification was performed in the test set based on predicted risk scores to evaluate the model’s prognostic utility. Results The RSF-based hybrid model performed best with a C-index of 0.807 and a Brier score of 0.101, outperforming the COX hybrid model (C-index of 0.726 and a Brier score of 0.145) and other unimodal and bimodal models. The SurvSHAP(t) plot highlighted CA125 as the most important variable. In the test set, patients were stratified into high- and low-risk groups based on the predicted risk scores, and Kaplan–Meier analysis demonstrated a significant survival difference between the two groups (p < 0.0001). Conclusion A multi-modal model using radiomics based on clinical tabular data and contrast-enhanced CT and MRI was developed by RSF, presenting strengths in predicting prognosis in pancreatic cancer patients.https://doi.org/10.1186/s12876-025-04119-zPancreatic cancerRandom survival forestMachine learningOverall survivalPredictive model |
| spellingShingle | Zheng Dou Jiaxi Lin Chenghao Lu Xiaoting Ma Ruoxu Zhang Jinzhou Zhu Songbing Qin Chao Xu Jinli Li The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer BMC Gastroenterology Pancreatic cancer Random survival forest Machine learning Overall survival Predictive model |
| title | The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer |
| title_full | The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer |
| title_fullStr | The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer |
| title_full_unstemmed | The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer |
| title_short | The development of a multimodal prediction model based on CT and MRI for the prognosis of pancreatic cancer |
| title_sort | development of a multimodal prediction model based on ct and mri for the prognosis of pancreatic cancer |
| topic | Pancreatic cancer Random survival forest Machine learning Overall survival Predictive model |
| url | https://doi.org/10.1186/s12876-025-04119-z |
| work_keys_str_mv | AT zhengdou thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jiaxilin thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT chenghaolu thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT xiaotingma thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT ruoxuzhang thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jinzhouzhu thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT songbingqin thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT chaoxu thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jinlili thedevelopmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT zhengdou developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jiaxilin developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT chenghaolu developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT xiaotingma developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT ruoxuzhang developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jinzhouzhu developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT songbingqin developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT chaoxu developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer AT jinlili developmentofamultimodalpredictionmodelbasedonctandmrifortheprognosisofpancreaticcancer |