Dataset Information

Multi-institutional development and external validation of machine learning-based models to predict relapse risk of pancreatic ductal adenocarcinoma after radical resection.

ABSTRACT:

Background

Surgical resection is the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC) and the survival of patients after radical resection is closely related to relapse. We aimed to develop models to predict the risk of relapse using machine learning methods based on multiple clinical parameters.

Methods

Data were collected and analysed of 262 PDAC patients who underwent radical resection at 3 institutions between 2013 and 2017, with 183 from one institution as a training set, 79 from the other 2 institution as a validation set. We developed and compared several predictive models to predict 1- and 2-year relapse risk using machine learning approaches.

Results

Machine learning techniques were superior to conventional regression-based analyses in predicting risk of relapse of PDAC after radical resection. Among them, the random forest (RF) outperformed other methods in the training set. The highest accuracy and area under the receiver operating characteristic curve (AUROC) for predicting 1-year relapse risk with RF were 78.4% and 0.834, respectively, and for 2-year relapse risk were 95.1% and 0.998. However, the support vector machine (SVM) model showed better performance than the others for predicting 1-year relapse risk in the validation set. And the k neighbor algorithm (KNN) model achieved the highest accuracy and AUROC for predicting 2-year relapse risk.

Conclusions

By machine learning, this study has developed and validated comprehensive models integrating clinicopathological characteristics to predict the relapse risk of PDAC after radical resection which will guide the development of personalized surveillance programs after surgery.

SUBMITTER: Li X

PROVIDER: S-EPMC8243478 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesThis study aimed to develop and externally validate a nomogram for predicting liver metastasis after radical resection in patients with pancreatic ductal adenocarcinoma (PDAC).MethodsA total of 247 PDAC patients who underwent radical resection were retrospectively reviewed from January 2015 to March 2022 at Ningbo Medical Centre Lihuili Hospital Eastern Section, and used as a training cohort to develop the nomogram. 83 PDAC patients from the Ningbo Medical Centre Lihuili Hospital Xingning Section were enrolled as the validation cohort. The postoperative liver metastasis was recorded during the follow-up, and the liver metastasis-free survival was defined as the time from operation to the date of liver metastasis diagnosis or death. The nomogram was established based on independent prognostic factors selected by LASSO and multivariate Cox regression model. The performance was assessed using the concordance index (C-index) and calibration curves. The receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to determine the clinical utility of the nomogram model.ResultsFrom the training cohort of 247 patients, a total of 132 patients developed liver metastasis during the follow-up, the 1-, 2- and 3- year liver metastasis-free survival were 52.4%, 43.5% and 40% respectively. The LASSO and multivariate Cox regression analysis indicated that postoperative CA125 (hazard ratio [HR] = 1.007, p <0.001), tumor differentiation (HR = 1.640, p = 0.010), tumor size (HR = 1.520, p = 0.029), lymph node ratio (HR = 1.897, p = 0.002) and portal/superior mesenteric/splenic vein invasion degree (PV/SMV/SV) (HR = 2.829, p <0.001) were the independent factors of liver metastasis. A nomogram with independent factors was developed and the C-index was 0.760 (95% confidence interval [CI], 0.720-0.799) and 0.739 (95% CI, 0.669-0.810) in the training and validation cohorts, respectively. The areas under curve (AUC) of the nomogram at 1-, 2- and 3-year were 0.815, 0.803 and 0.773 in the training cohort, and 0.765, 0.879 and 0.908 in the validation cohort, respectively, higher than those in TNM stage. Decision curve analysis (DCA) analysis revealed that the nomogram model provided superior net benefit in clinical utility. Liver metastasis-free survival curves showed a significant discriminatory ability for liver metastasis risk based on the nomogram (p <0.001).ConclusionsThe nomogram showed high accuracy in predicting liver metastasis for PDAC after radical resection, and may serve as a clinical support tool to guide personalized and prescient intervention.

Project description:BackgroundThe high recurrence rate after radical resection of pancreatic ductal adenocarcinoma (PDAC) leads to its poor prognosis. We aimed to develop a model to preoperatively predict the risk of recurrence based on computed tomography (CT) radiomics and multiple clinical parameters.MethodsDatasets were retrospectively collected and analysed of 220 PDAC patients who underwent contrast-enhanced computed tomography (CE-CT) and received radical resection at 3 institutions in China between 2013 and 2017, with 153 from one institution as a training set, the remaining 67 as a validation set. For each patient, CT radiomics features were extracted from intratumoral and peritumoral regions to establish intratumoral, peritumoral and combined radiomics models using artificial neural network (ANN) algorithm. By incorporating clinical factors, radiomics-clinical nomograms were finally built by multivariable logistic regression analysis to predict 1- and 2-year recurrence risk.FindingsThe developed radiomics model integrating intratumoral and peritumoral radiomics features was superior to the conventionally constructed model merely using intratumoral radiomics features. Further, radiomics-clinical nomograms outperformed other models in predicting 1-year recurrence with an area under the receiver operating characteristic curve (AUROC) of 0.916 (95%CI, 0.860-0.955) in the training set and 0.764 (95%CI, 0.644-0.859) in the validation set, and 2-year recurrence with an AUROC of 0.872 (95%CI: 0.809-0.921) in the training set and 0.773 (95%CI, 0.654-0.866) in the validation set.InterpretationThis study has developed and externally validated a radiomics-clinical nomogram integrating intra- and peritumoral CT radiomics signature as well as clinical factors to predict the recurrence risk of PDAC after radical resection, which will facilitate optimized and individualized treatment strategies.FundingThis work was supported by the National Key R&D Program of China [grant number: 2018YFE0114800], the General Program of National Natural Science Foundation of China [grant number: 81772562, 2017; 81871351, 2018], the Fundamental Research Funds for the Central Universities [grant number: 2021FZZX005-08], and Zhejiang Provincial Key Projects of Technology Research [grant number: WKJ-ZJ-2033].