Re-appraising the role of lymph node status in predicting survival in resected distal cholangiocarcinoma - A meta-analysis and systematic review

A machine learning predictive model for recurrence of resected distal cholangiocarcinoma: Development and validation of predictive model using artificial intelligence

INTRODUCTION

Distal Cholangiocarcinoma (dCCA) represents a challenge in hepatobiliary oncology, that requires nuanced post-resection prognostic modeling. Conventional staging criteria may oversimplify dCCA complexities, prompting the exploration of novel prognostic factors and methodologies, including machine learning algorithms. This study aims to develop a machine learning predictive model for recurrence after resected dCCA.

MATERIAL AND METHODS

This retrospective multicentric observational study included patients with dCCA from 13 international centers who underwent curative pancreaticoduodenectomy (PD). A LASSO-regularized Cox regression model was used to feature selection, examine the path of the coefficient and create a model to predict recurrence. Internal and external validation and model performance were assessed using the C-index score. Additionally, a web application was developed to enhance the clinical use of the algorithm.

RESULTS

Among 654 patients, LNR (Lymph Node Ratio) 15, neural invasion, N stage, surgical radicality, and differentiation grade emerged as significant predictors of disease-free survival (DFS). The model showed the best discrimination capacity with a C-index value of 0.8 (CI 95 %, 0.77%-0.86 %) and highlighted LNR15 as the most influential factor. Internal and external validations showed the model's robustness and discriminative ability with an Area Under the Curve of 92.4 % (95 % CI, 88.2%-94.4 %) and 91.5 % (95 % CI, 88.4%-93.5 %), respectively. The predictive model is available at https://imim.shinyapps.io/LassoCholangioca/.

CONCLUSIONS

This study pioneers the integration of machine learning into prognostic modeling for dCCA, yielding a robust predictive model for DFS following PD. The tool can provide information to both patients and healthcare providers, enhancing tailored treatments and follow-up.

Long-term Outcomes After Laparoscopic, Robotic, and Open Pancreatoduodenectomy for Distal Cholangiocarcinoma: An International Propensity Score-matched Cohort Study

OBJECTIVE

This study aimed to compare surgical and oncological outcomes after minimally invasive pancreatoduodenectomy (MIPD) versus open pancreatoduodenectomy (OPD) for distal cholangiocarcinoma (dCCA).

BACKGROUND

A dCCA might be a good indication for MIPD, as it is often diagnosed as primary resectable disease. However, multicenter series on MIPD for dCCA are lacking.

METHODS

This is an international multicenter propensity score-matched cohort study including patients after MIPD or OPD for dCCA in 8 centers from 5 countries (2010-2021). Primary outcomes included overall survival (OS) and disease-free interval (DFI). Secondary outcomes included perioperative and postoperative complications and predictors for OS or DFI. Subgroup analyses included robotic pancreatoduodenectomy (RPD) and laparoscopic pancreatoduodenectomy (LPD).

RESULTS

Overall, 478 patients after pancreatoduodenectomy for dCCA were included of which 97 after MIPD (37 RPD, 60 LPD) and 381 after OPD. MIPD was associated with less blood loss (300 vs 420 mL, P =0.025), longer operation time (453 vs 340 min; P <0.001), and less surgical site infections (7.8% vs 19.3%; P =0.042) compared with OPD. The median OS (30 vs 25 mo) and DFI (29 vs 18) for MIPD did not differ significantly between MIPD and OPD. Tumor stage (Hazard ratio: 2.939, P <0.001) and administration of adjuvant chemotherapy (Hazard ratio: 0.640, P =0.033) were individual predictors for OS. RPD was associated with a higher lymph node yield (18.0 vs 13.5; P =0.008) and less major morbidity (Clavien-Dindo 3b-5; 8.1% vs 32.1%; P =0.005) compared with LPD.

DISCUSSION

Both surgical and oncological outcomes of MIPD for dCCA are acceptable as compared with OPD. Surgical outcomes seem to favor RPD as compared with LPD but more data are needed. Randomized controlled trials should be performed to confirm these findings.

Lymph Node Ratio Nomogram-Based Prognostic Model for Resected Distal Cholangiocarcinoma

BACKGROUND

Several variables have been described as prognostic factors for resected distal cholangiocarcinoma (dCC), including lymph node metastases (N status) and lymph node ratio (LNR). The present study aimed to evaluate the prognostic value of LNR on survival and to establish a novel prognostic nomogram to predict the cancer-specific recurrence-free survival (RFS) of dCC.

STUDY DESIGN

Between December 2006 and September 2020, 415 consecutive patients who underwent pancreaticoduodenectomy (PD) for dCC in 10 centers were identified. Multivariate Cox analysis was used to identify all independent risk factors among several prognostic factors. A nomogram was then developed and assessed by integrating the independent prognostic factors into the model, and the concordance index (C-index) was used to evaluate its performance.

RESULTS

According to Cox regression multivariate analysis, a nomogram based on independent prognostic factor for RFS was performed including LNR 15 (hazard ratio [HR] 2.442, 95% CI 1.348-4.425, p = 0.003), perineural invasion (HR 3.100, 95% CI 1.183-8.122, p = 0.025), differentiation grade (HR 2.100, 95% CI 1.172-4.143, p = 0.021), and radicality of PD (HR 2.276, 95% CI 1.223-4.234, p = 0.009). The C-index of the nomogram, tailored based on the previous significant factors, was 0.8.

CONCLUSIONS

LNR15 yields a high prognostic efficiency for RFS. The nomogram based on LNR can provide an accurate prognosis assessment for patients with resected dCC.

Comparison of Four Lymph Node Stage Methods for Predicting the Prognosis of Distal Cholangiocarcinoma Patients After Surgery

Background

The metastatic status of regional lymph nodes is an effective risk factor for the prognosis of distal cholangiocarcinoma (dCCA). But existing lymph node staging is not accurate enough and is susceptible to interference. This study aims to explore the predictive ability of the log odds of positive lymph nodes (LODDS) staging system of dCCA compared with existing lymph node staging systems.

Methods

A total of 928 dCCA patients were selected from the Surveillance, Epidemiology, and End Results (SEER) database as the training cohort, and 207 dCCA patients from West China Hospital who underwent surgery were reviewed as the validation cohort. The least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression were conducted to identify the most meaningful factors relevant to prognosis. The performance of four lymph node stage systems was compared by a model-based approach.

Result

Age at diagnosis, pathological grade, American Joint Committee on Cancer (AJCC) tumor 7th T stage, tumor size, radiotherapy, chemotherapy, and lymph node stage system were independent prognostic factors. The model with the LODDS system had a better model fit with the highest C-index (0.679) and 1-/3-/5- area under the receiver operating characteristic curve (AUC) (0.739/0.671/0.658) as well as the lowest Akaike information criterion (AIC) (5,020.52). External validation results from 207 dCCA patients showed a C-index of 0.647 and 1-/3-/5-AUC of 0.740/0.683/0.589. Compared with the lymph node ratio (LNR), AJCC 8th N system, and 7th N system, the 5-year net reclassification improvement (NRI) of the LODDS system was 0.030 (95% CI: -0.079 to 0.147), 0.042 (95% CI: -0.062 to 0.139), and 0.040 (95% CI: -0.057 to 0.146), respectively. The integrated discrimination improvement (IDI) of LODDS improved compared with the LNR model (0.016; 95% CI: -0.001 to 0.036), AJCC 8th N system (0.020; 95% CI: 0.003-0.037), and AJCC 7th N system (0.019; 95% CI: 0.002-0.036). Decision curve analysis (DCA) also shows a greater net benefit of LODDS. In lymph node-negative patients, LODDS reveals a positive linear relationship with the hazard ratio (HR). The stage capacity of LODDS in a subgroup analysis stratified by examined lymph node number (ELNN) was consistent.

Conclusions

The LODDS lymph node stage system has superior predictive performance as compared with the LNR, AJCC 7th, and 8th lymph node stage systems. Meanwhile, LODDS has a more detailed staging ability and good stability.

A Nomogram Based on the Log Odds of Positive Lymph Nodes Predicts the Prognosis of Patients With Distal Cholangiocarcinoma After Surgery

Background: Lymph node (LN) metastasis is considered one of the most important risk factors affecting the prognosis of distal cholangiocarcinoma (DCC). This study aimed to demonstrate the superiority of log odds of positive lymph nodes (LODDS) compared with other LN stages, and to establish a novel prognostic nomogram to predict the cancer-specific survival (CSS) of DCC.

Methods: From the Surveillance, Epidemiology and End Results (SEER) database, the data of 676 patients after DCC radical operation were screened, and patients were randomly divided into training (n = 474) and validation sets (n = 474). The prognostic evaluation performance of the LODDS and American Joint Commission on Cancer (AJCC) N stage and lymph node ratio (LNR) were compared using the Akaike information criteria, receiver operating characteristic area under the curve (AUC), and C-index. Multivariate Cox analysis was used to screen independent risk factors, and a LODDS-based nomogram prognostic staging model was established. The nomogram's precision was verified by C-index, calibration curves, and AUC, and the results were compared with those of the AJCC TNM staging system.

Results:Compared with the other two stages of LN metastasis, LODDS was most effective in predicting CSS in patients with DCC. Multivariate analysis proved that LODDS, histologic grade, SEER historic stage, and tumor size were independent risk factors for DCC. The C-index of the nomogram, based on the above factors, in the validation set was 0.663. The 1-, 3-, and 5-y AUCs were 0.735, 0.679, and 0.745, respectively. Its good performance was also verified by calibration curves. In addition, the C-index and Kaplan-Meier analysis showed that the nomogram performed better than the AJCC TNM staging system.

Conclusion:For postoperative patients with DCC, the LODDS stage yielded better prognostic efficiency than the AJCC N and LNR stages. Compared with the AJCC TNM staging system, the nomogram, based on the LODDS, demonstrated superior performance.