It is the lymph node ratio that determines survival and recurrence patterns in resected distal cholangiocarcinoma. A multicenter international study

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.

Patterns, timing and predictors of recurrence following pancreaticoduodenectomy for distal cholangiocarcinoma: An international multicentre retrospective cohort study

INTRODUCTION

Patients undergoing pancreaticoduodenectomy for distal cholangiocarcinoma (dCCA) often develop cancer recurrence. Establishing timing, patterns and risk factors for recurrence may help inform surveillance protocol strategies or select patients who could benefit from additional systemic or locoregional therapies. This multicentre retrospective cohort study aimed to determine timing, patterns, and predictive factors of recurrence following pancreaticoduodenectomy for dCCA.

MATERIALS AND METHODS

Patients who underwent pancreaticoduodenectomy for dCCA between June 2012 and May 2015 with five years of follow-up were included. The primary outcome was recurrence pattern (none, local-only, distant-only or mixed local/distant). Data were collected on comorbidities, investigations, operation details, complications, histology, adjuvant and palliative therapies, recurrence-free and overall survival. Univariable tests and regression analyses investigated factors associated with recurrence.

RESULTS

In the cohort of 198 patients, 129 (65%) developed recurrence: 30 (15%) developed local-only recurrence, 44 (22%) developed distant-only recurrence and 55 (28%) developed mixed pattern recurrence. The most common recurrence sites were local (49%), liver (24%) and lung (11%). 94% of patients who developed recurrence did so within three years of surgery. Predictors of recurrence on univariable analysis were cancer stage, R1 resection, lymph node metastases, perineural invasion, microvascular invasion and lymphatic invasion. Predictors of recurrence on multivariable analysis were female sex, venous resection, advancing histological stage and lymphatic invasion.

CONCLUSION

Two thirds of patients have cancer recurrence following pancreaticoduodenectomy for dCCA, and most recur within three years of surgery. The commonest sites of recurrence are the pancreatic bed, liver and lung. Multiple histological features are associated with recurrence.

Prognostic risk factors in 113 patients undergoing cephalic duodenopancreatectomy for distal cholangiocarcinoma

INTRODUCTION

Distal cholangiocarcinoma is a malignant epithelial neoplasia that affects the extrahepatic bile ducts, below the cystic duct. No relevant relationship between perioperative factors and worse long-term outcome has been proved.

OBJECTIVE

To analyze the risk factors for mortality and long-term recurrence of distal cholangiocarcinoma in resected patients.

MATERIALS AND METHODS

A single-center prospective database of patients operated on for distal cholangiocarcinoma between 1990 and 2021 was analyzed in order to investigate mortality and recurrence factors.

RESULTS

One hundred and thirteen patients have undergone surgery, with mean actuarial survival of 100.2 (76-124) months after resection. The bivariate study did not show differences between patients depending on age or preoperative variables studied. When multivariate analysis was performed, the presence of affected adenopathy was a risk factor for long-term mortality. The presence of affected lymph nodes, tumor recurrence, and biliary fistula during the postoperative period implied worse actuarial survival when comparing the Kaplan-Meier curves.

CONCLUSIONS

The presence of affected lymph nodes influence the prognosis of the disease. The occurrence of biliary fistula during postoperative cholangiocarcinoma distal could aggravate long-term outcomes, a finding that should be reaffirmed in future studies.

Subserosal Layer and/or Pancreatic Invasion Based on Anatomical Features as a Novel Prognostic Indicator in Patients with Distal Cholangiocarcinoma

The American Joint Committee on Cancer (AJCC) 8th edition T-staging system for distal cholangiocarcinoma (DCC) proposes classification according to the depth of invasion (DOI); nevertheless, DOI measurement is complex and irreproducible. This study focused on the fibromuscular layer and evaluated whether the presence or absence of penetrating fibromuscular invasion of DCC contributes to recurrence and prognosis. In total, 55 patients pathologically diagnosed with DCC who underwent surgical resection from 2002 to 2022 were clinicopathologically examined. Subserosal layer and/or pancreatic (SS/Panc) invasion, defined as penetration of the fibromuscular layer and invasion of the subserosal layer or pancreas by the cancer, was assessed with other clinicopathological prognostic factors to investigate recurrence and prognostic factors. According to the AJCC 8th edition, there were 11 T1, 28 T2, and 16 T3 cases, with 44 (80%) cases of SS/Panc invasion. The DOI was not significantly different for both recurrence and prognostic factors. In the multivariate analysis, only SS/Panc was identified as an independent factor for prognosis (hazard ratio: 16.1; 95% confidence interval: 2.1-118.8, p = 0.006). In conclusion, while the determination of DOI in DCC does not accurately reflect recurrence and prognosis, the presence of SS/Panc invasion may contribute to the T-staging system.

Indications for resection of recurrent lesions in patients with distal cholangiocarcinoma based on prognostic factors: a single-institute retrospective study and brief literature review

BACKGROUND

To evaluate the effectiveness of surgery for recurrent distal cholangiocarcinoma and determine surgical indications based on prognostic factors for the recurrence of distal cholangiocarcinoma.

METHODS

We analysed the outcomes of 101 patients who underwent surgical resection for distal cholangiocarcinoma between 2000 and 2018. The clinicopathological factors and prognosis of primary and recurrent distal cholangiocarcinoma were investigated.

RESULTS

Of the 101 patients with resected distal cholangiocarcinoma, 52 (51.5%) had relapsed. Seven (13.5%) and 45 patients (86.5%) underwent resection of recurrent lesions and palliative therapy, respectively. There were no major complications requiring therapeutic intervention after metastasectomy. The median overall survival in patients with and without surgery for recurrent lesions was 83.0 (0.0-185.6) and 34 months (19.0-49.0), respectively. Therefore, patients who had undergone surgery for recurrent lesions had a significantly better prognosis (p = 0.022). Multivariate analyses of recurrent distal cholangiocarcinoma revealed that recurrence within one year was an independent predictor of poor survival. Resection of recurrent lesions improved prognosis.

CONCLUSIONS

Radical resection in recurrent distal cholangiocarcinoma may improve the prognosis in selected patients. Although time to recurrence is considered an important factor, the small number of cases of recurrence and resection of recurrent lesions in this study makes it difficult to conclude which patients are best suited for resection of recurrent lesions. This issue requires clarification in a multicentre prospective study, considering patients' background, such as the recurrence site and number of metastases.

Preoperative peripheral blood inflammatory markers especially the fibrinogen-to-lymphocyte ratio and novel FLR-N score predict the prognosis of patients with early-stage resectable extrahepatic cholangiocarcinoma

Background

Systemic inflammation is important in the development of extrahepatic cholangiocarcinoma (ECC). The aim of this study was to compare the prognostic power of preoperative peripheral blood inflammatory markers and the novel FLR-N score in patients with resectable ECC.

Methods

A total of 140 patients with resectable ECC and 140 healthy controls (HCs) were recruited for the study. The Mann−Whitney U test was used to evaluate the differences in inflammatory markers between groups. Kaplan−Meier and Cox regression analyses were used to evaluate the prognostic power of preoperative fibrinogen, albumin, prealbumin, bilirubin, neutrophils, lymphocytes, monocytes, platelets, fibrinogen-to-lymphocyte ratio (FLR), fibrinogen-to-albumin ratio (FAR), fibrinogen-to-prealbumin ratio (FPR), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), FLR-neutrophil (FLR-N) score, and CA19-9 in patients with resectable ECC. Nomogram was developed based on the results of multivariate Cox analyses.

Results

Patients with resectable ECC had significantly higher levels of neutrophils, monocytes, fibrinogen, FLR, FAR, FPR, NLR, PLR, and MLR and lower levels of lymphocytes, albumin, and prealbumin than HCs (all P < 0.01). Albumin, prealbumin, and FPR had a good ability to distinguish between ECC patients with total bilirubin < 34 µmol/L and HCs (AUCs of 0.820, 0.827, and 0.836, respectively). Kaplan−Meier analysis showed that high neutrophil, fibrinogen, FLR, FAR, PLR, MLR, and FLR-N score values were associated with poor survival in patients with resectable ECC. Multivariate analyses indicated that neutrophils (P = 0.022), FLR (P = 0.040), FLR-N score (P < 0.0001), and positive lymph node metastasis (P = 0.016) were independent factors for overall survival (OS). Nomogram were developed to predict OS for patients with ECC.

Conclusion

The prognostic roles of inflammatory markers in patients with resectable ECC were different. The preoperative neutrophil count, FLR and FLR-N score could serve as noninvasive markers for predicting the prognosis of resectable ECC.

Anatomical Resection Improved the Outcome of Intrahepatic Cholangiocarcinoma: A Propensity Score Matching Analysis of a Retrospective Cohort

Background

Intrahepatic cholangiocarcinoma (ICC) is the second most common liver malignancy after hepatocellular carcinoma (HCC), with a dismal prognosis and high heterogeneity. The oncological advantages of anatomical resection (AR) and nonanatomical resection (NAR) in HCC have been studied, but surgical strategies for ICC remain controversial with insufficient investigations.

Materials and Methods

From Jan 2013 to Dec 2016, 3880 consecutive patients were retrospectively reviewed from a single center. Patients with ICC undergoing AR or NAR have been enrolled according to inclusion and exclusion criteria. Propensity score matching (PSM) analysis was performed between two groups with a 1 : 1 ratio. The primary endpoint was overall survival (OS), and the secondary endpoints included disease-free survival (DFS), intraoperative patterns, postoperative morbidity, mortality, complications and recurrence. A prognostic nomogram was developed by a multivariate Cox proportion hazard model.

Results

After PSM, 99 paired cases were selected from 276 patients enrolled in this study. Patients in the AR group achieved better 1-, 3-, and 5-year OS (70%, 46%, and 34%, respectively) and DFS (61%, 21%, and 10%, respectively) than patients in the NAR group with statistical significance after PSM analysis. The postoperative complications and recurrence patterns were comparable between the two groups. Multivariate analysis identified NAR, tumor size >5 cm, multiple tumors, and poor differentiation as independent risk factors for OS (p < 0.05). Selected patients can benefit most from AR, according to subgroup analysis. A prognostic nomogram based on six independent risk factors for OS and factors with clinical significance was constructed to predict OS in ICC patients.

Conclusion

AR improved the long-term survival of ICC with comparable postoperative complications and similar recurrence patterns. AR is suggested in ICC patients with sufficient remnant liver volume. In addition to surgery strategy, malignant characteristics of tumors are risk factors for ICC prognosis.

Prognostic role of the systemic immune-inflammation index in biliary tract cancers: a meta-analysis of 3,515 patients

Background

The systemic immune-inflammation index (SII) is an inflammatory parameter calculated as platelet count × neutrophil count/lymphocyte count in the peripheral blood. In recent years, the prognostic role of the SII in patients with biliary tract cancer (BTC) has been gradually investigated. However, the results were controversial. This meta-analysis aimed to illustrate the prognostic value of the SII in BTC.

Methods

The electronic databases of PubMed, the Web of Science, Embase, and the Cochrane Library were thoroughly retrieved up to April 15, 2022. Pooled hazard ratios (HRs) with 95% confidence intervals (CIs) were used to evaluate the prognostic value of the SII for clinical outcomes. The association between the SII and overall survival (OS) and recurrence-free survival (RFS)/progression-free survival (PFS) was evaluated.

Results

Thirteen studies involving 3515 patients were included in this meta-analysis. The pooled results indicated that an elevated SII was significantly associated with poor OS (HR, 1.77; 95% CI, 1.47–2.14; p<0.001) and RFS/PFS (HR, 1.66; 95% CI, 1.38–1.99; p<0.001) in patients with BTC. Subgroup analysis stratified by country, sample size, and cutoff value showed similar results. The sensitivity analysis and publication bias test confirmed the reliability of our results.

Conclusions

An elevated pretreatment SII was significantly associated with worse OS and RFS/PFS in patients with BTC. Our results suggest that the SII is a valuable and cost-effective prognostic parameter for the treatment of patients with BTC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12957-022-02783-z.