A dynamic analysis of empirical survival outcomes after pancreatectomy for pancreatic ductal adenocarcinoma

Interpretable Prognostic Modeling for Postoperative Pancreatic Cancer Using Multi-machine Learning and Habitat Radiomics: A Multi-center Study

RATIONALE AND OBJECTIVES

Accurate risk stratification is critical for guiding personalized treatment in resectable pancreatic cancer (RPC). This retrospective study assessed the utility of habitat radiomics for predicting recurrence-free survival (RFS) in RPC patients.

MATERIALS AND METHODS

A total of 455 RPC patients were divided into training and external test sets from January 2018 to July 2024. Tumors were segmented into subregions using habitat radiomics to capture localized heterogeneity. Seven machine learning models, including random survival forest (RSF), were compared using Harrell's C-index. The optimal model underwent further validation through time-dependent ROC and Kaplan-Meier (KM) analyses. Shapley additive explanations (SHAP) and survival local interpretable model-agnostic explanations (SurvLIME) were applied to enhance model interpretability.

RESULTS

The RSF model based on habitat radiomics achieved a C-index of 0.828 in the training cohort and 0.702, 0.680 in external test sets, outperforming whole-tumor radiomics (p<0.05). Time-dependent ROC analysis showed AUCs of 0.71, 0.83, and 0.79 at 0.5, 1, and 2 years in the first test set, and 0.65, 0.79, and 0.75 in the second test set. KM analysis revealed that the predicted low-risk groups had significantly longer RFS compared to the predicted high-risk groups in both external test sets (all p<0.05). Interpretability analysis identified key variables, including Feature 1, Feature 5, Feature 2, and Feature 4 from Habitat Subregion 1, and Feature 3 from Habitat Subregion 3.

CONCLUSION

The habitat radiomics RSF machine learning model improves prognostic accuracy and interpretability for postoperative RPC, providing a promising tool for personalized management.

Multiscale deep learning radiomics for predicting recurrence-free survival in pancreatic cancer: A multicenter study

PURPOSE

This multicenter study aimed to develop and validate a multiscale deep learning radiomics nomogram for predicting recurrence-free survival (RFS) in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

A total of 469 PDAC patients from four hospitals were divided into training and test sets. Handcrafted radiomics and deep learning (DL) features were extracted from optimal regions of interest, encompassing both intratumoral and peritumoral areas. Univariate Cox regression, LASSO regression, and multivariate Cox regression selected features for three image signatures (intratumoral, peritumoral radiomics, and DL). A multiscale nomogram was constructed and validated against the 8th AJCC staging system.

RESULTS

The 4 mm peritumoral VOI yielded the best radiomics prediction, while a 15 mm expansion was optimal for deep learning. The multiscale nomogram demonstrated a C-index of 0.82 (95 % CI: 0.78-0.85) in the training set and 0.70 (95 % CI: 0.64-0.76) in the external test 1 (high-volume hospital), with the external test 2 (low-volume hospital) showing a C-index of 0.78 (95 % CI: 0.65-0.91). These outperformed the AJCC system's C-index (0.54-0.57). The area under the curve (AUC) for recurrence prediction at 0.5, 1, and 2 years was 0.89, 0.94, and 0.89 in the training set, with AUC values ranging from 0.75 to 0.97 in the external validation sets, consistently surpassing the AJCC system across all sets. Kaplan-Meier analysis confirmed significant differences in prognosis between high- and low-risk groups (P < 0.01 across all cohorts).

CONCLUSION

The multiscale nomogram effectively stratifies recurrence risk in PDAC patients, enhancing presurgical clinical decision-making and potentially improving patient outcomes.

Cure Probabilities After Resection of Pancreatic Ductal Adenocarcinoma: A Multi-Institutional Analysis of 2554 Patients

OBJECTIVE

To assess the probability of being cured of pancreatic ductal adenocarcinoma (PDAC) by pancreatic surgery.

BACKGROUND

Statistical cure implies that a patient treated for a specific disease will have the same life expectancy as if he/she never had that disease.

METHODS

Patients who underwent pancreatic resection for PDAC between 2010 and 2021 were retrospectively identified using a multi-institutional database. A nonmixture statistical cure model was applied to compare disease-free survival to the survival expected for a matched general population.

RESULTS

Among 2554 patients, either in the setting of upfront (n=1691) or neoadjuvant strategy (n=863), the cure model showed that the probability that surgery would offer the same life expectancy (and tumor-free) as the matched general population was 20.4% (95% CI: 18.3, 22.5). Cure likelihood reached the 95% of certainty (time to cure) after 5.3 years (95% CI: 4.7, 6.0). A preoperative model was developed based on tumor stage at diagnosis ( P =0.001), radiologic size ( P =0.001), response to chemotherapy ( P =0.007), American Society of Anesthesiology class ( P =0.001), and preoperative Ca19-9 ( P =0.001). A postoperative model with the addition of surgery type ( P =0.015), pathologic size ( P =0.001), tumor grading ( P =0.001), resection margin ( P =0.001), positive lymph node ratio ( P =0.001), and the receipt of adjuvant therapy ( P =0.001) was also developed.

CONCLUSIONS

Patients operated for PDAC can achieve a life expectancy similar to that of the general population, and the likelihood of cure increases with the passage of recurrence-free time. An online calculator was developed and available at https://aicep.website/?cff-form=15 .