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.

The involvement of the hepatic artery is a risk factor for unresectability after neoadjuvant treatment in borderline pancreatic adenocarcinoma.

INTRODUCTION: Borderline Resectable Pancreatic Ductal Adenocarcinoma (BR-PDAC) benefits from neoadjuvant treatment (NAT) with the intent of surgical salvage in the absence of disease progression during chemotherapy (CT) or chemoradiotherapy (CRT). Scarce literature exists about prognostic factors of resectability at the time of diagnosis or during neoadjuvant treatment, especially regarding vascular relationships. MATERIALS: We reviewed our prospective BR-PDAC cohort to determine resectability predictors. We collected data about clinical baseline characteristics, vessels' involvement, type of NAT, CA19-9 evolution, and radiological outcome. We performed a descriptive analysis and a logistic regression model to define resectability predictors; we finally compared overall survival (OS) and progression-free survival (PFS) for those predictors. RESULTS: One hundred patients started NAT, with a resection rate of 44 % (40 pancreaticoduodenectomies, 4 distal pancreatectomies). The most frequent vessel relationship was the abutment of the superior mesenteric artery (44 %), and 26 patients had ≥2 vessels involved. Prognostic factors of resectability were CA19-9 response >10 % (OR 3.07, p = 0.016) and Hepatic Artery involvement (OR 0.21, p = 0.026). Median overall survival was better for CA19-9 responders than for non-responders (20.9 months and 11.8 months respectively, p < 0.001), and similar to normalized CA19-9 (25.0 months, p = 0.48). There were no differences in terms of OS or PFS with the involvement of the HA (17.7 vs 17.1 months, p = 0.367; and 8.7 vs 12.0 months, p = 0.267). CONCLUSION: The involvement of the Hepatic Artery seems to confer a worse prognosis regarding resectability. A decrease of only >10 % of CA19-9 is a predictive factor for resectability and better overall and progression-free survival.

Prognostic risk factors in 113 patients undergoing cephalic duodenopancreatectomy for distal cholangiocarcinoma. / Factores de mal pronóstico en 113 pacientes sometidos a duodenopancreatectomía cefálica por colangiocarcinoma distal.

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.

Predictive factors for resection and survival in type A borderline resectable pancreatic ductal adenocarcinoma patients after neoadjuvant therapy: A retrospective cohort study.

INTRODUCTION: Pancreatic cancer is the seventh leading cause of cancer-related death worldwide, and surgical resection with radical intent remains the only potentially curative treatment option today. However, borderline resectable pancreatic ductal adenocarcinomas (BR-PDAC) stand in the gray area between the resectable and unresectable disease since they are technically resectable but have a high probability of incomplete exeresis. Neoadjuvant treatment (NAT) plays an important role in ensuring resection success.Different survival prognostic factors for BR-PDAC have been well described, but evidence on the predictive factors associated with resection after NAT is scarce. This study aims to study if CA 19-9 plasmatic levels and the tumor anatomical relationship with neighboring vascular structures are prognostic factors for resection and survival (both Overall Survival and Progression-Free Survival) in patients with type A BR-PDAC. METHODS: This will be a retrospective cohort study using data from type A BR-PDAC patients who received NAT in the Bellvitge University Hospital. The observation period is from January 2010 until December 2019; patients must have a minimum 12-month follow-up. Patients will be classified according to the MD Anderson Cancer Center criteria for BR-PDAC. DISCUSSION: Patients with BR-PDAC have a high risk for a margin-positive resection. Serum Carbohydrate Antigen 19-9 plasmatic levels and vascular involvement stand out as disease-related prognostic factors.This study will provide valuable information on the prognostic factors associated with resection. We will exclude locally advanced tumors and expect this approach to provide more realistic resection rates without selecting those patients that undergo surgical exploration. However, focusing on an anatomical definition may limit the results' generalizability.

Initial Experience in the Treatment of "Borderline Resectable" Pancreatic Adenocarcinoma. / Experiencia inicial en el tratamiento del adenocarcinoma de páncreas borderline resectable.

INTRODUCTION: A borderline resectable group (APBR) has recently been defined in adenocarcinoma of the pancreas. The objective of the study is to evaluate the results in the surgical treatment after neoadjuvancy of the APBR. METHOD: Between 2010 and 2014, we included patients with APBR in a neoadjuvant and surgery protocol, staged by multidetector computed tomography (MDCT). Treatment with chemotherapy was based on gemcitabine and oxaliplatin. Subsequently, MDCT was performed to rule out progression, and 5-FU infusion and concomitant radiotherapy were given. MDCT and resection were performed in absence of progression. A descriptive statistical study was performed, dividing the series into: surgery group (GR group) and progression group (PROG group). RESULTS: We indicated neoadjuvant treatment to 22 patients, 11 of them were operated, 9 pancreatoduodenectomies, and 2 distal pancreatectomies. Of the 11 patients, 7 required some type of vascular resection; 5 venous resections, one arterial and one both. No postoperative mortality was recorded, 7 (63%) had any complications, and 4 were reoperated. The median postoperative stay was 17 (7-75) days. The pathological study showed complete response (ypT0) in 27%, and free microscopic margins (R0) in 63%. At study clossure, all patients had died, with a median actuarial survival of 13 months (9,6-16,3). The median actuarial survival of the GR group was higher than the PROG group (25 vs. 9 months; p < 0.0001). CONCLUSION: The neoadjuvant treatment of APBR allows us to select a group of patients in whom resection achieves a longer survival to the group in which progression is observed. Post-adjuvant pancreatic resection requires vascular resection in most cases.

Surgical treatment of non-functioning pancreatic neuroendocrine tumours based on three clinical scenarios. / Tratamiento quirúrgico de los tumores neuroendocrinos no funcionantes de páncreas basado en 3 escenarios clínicos.

INTRODUCTION: The treatment of patients with non-functioning pancreatic neuroendocrine tumours (NFPNET) is resection in locally pancreatic disease, or with resectable liver metastases. There is controversy about unresectable liver disease. METHODS: We analysed the perioperative data and survival outcome of 63 patients who underwent resection of NFPNET between 1993 and 2012. They were divided into 3 scenarios: A, pancreatic resection (44patients); B, pancreatic and liver resection in synchronous resectable liver metastases (12patients); and C, pancreatic resection in synchronous unresectable liver metastases (6patients). The prognostic factors for survival and recurrence were studied. RESULTS: Distal pancreatectomy (51%) and pancreaticoduodenectomy (38%) were more frequently performed. Associated surgery was required in 44% of patients, including synchronous liver resections in 9patients. Two patients received a liver transplant during follow-up. According to the WHO classification they were distributed into G1: 10 (16%), G2: 45 (71%), and G3: 8 (13%). The median hospital stay was 11days. Postoperative morbidity and mortality were 49% and 1.6%, respectively. At the closure of the study, 43 (68%) patients were still alive, with a mean actuarial survival of 9.6years. The WHO classification and tumour recurrence were risk factors of mortality in the multivariate analysis. The median actuarial survival by scenarios was 131months (A), 102months (B), and 75months (C) without statistically significant differences. CONCLUSIONS: Surgical resection is the treatment for NFPNET without distant disease. Resectable liver metastases in well-differentiated tumours must be resected. The resection of the pancreatic tumour with unresectable synchronous liver metastasis must be considered in well-differentiated NFPNET. The WHO classification grade and recurrence are risk factors of long-term mortality.

Factors influencing mortality in patients undergoing surgery for acute pancreatitis: importance of peripancreatic tissue and fluid infection.

OBJECTIVES: The aims of present study were to analyze the mortality risk factors in patients who had surgery for acute pancreatitis and to assess the importance of culturing peripancreatic tissue or fluid infection to ascertain the infection status. METHODS: Surgery was indicated both in patients with infected severe acute pancreatitis and in those with sterile pancreatitis with an unfavorable course. During surgery, cultures were taken of tissues (pancreatic necrosis and peripancreatic fat), intra-abdominal fluid, and bile. RESULTS: Of 107 patients operated on, fluid culture was analyzed in 94 patients, pancreatic necrosis in 61 patients, peripancreatic fat in 39 patients, and bile in 38 patients. Sterile pancreatitis with sterile ascites was found in 17 patients, sterile pancreatitis with infected ascites in 22, and pancreatic tissue infection in 60. Multivariate analysis demonstrated that sterile tissue cultures, age over 65 years, and fewer than 12 days between the beginning of pain and surgery were risk factors for mortality. Sterile pancreatitis with sterile ascites and sterile pancreatitis with infected ascites had similar postoperative mortality (41% and 50%, respectively); the group with pancreatic tissue infection had a lower mortality (20%). CONCLUSIONS: Early surgery, advanced age, and sterility of tissue cultures have been demonstrated as mortality factors for acute pancreatitis. Intra-abdominal fluid may be infected in the presence of sterile necrosis.