A novel machine learning model has been developed by researchers to predict survival in metastatic pancreatic neuroendocrine tumors (PNETs), a condition traditionally associated with poor prognosis. Utilizing data from 1430 patients, the model employed the extreme gradient boosting (XGBoost) algorithm and integrated ten prognostic factors. It demonstrated strong predictive accuracy, achieving area under the receiver […]
Category: HPB & Spleen
New strategies identified to prevent complications from ERCP
In the past five years, research highlights advancements in avoiding complications from endoscopic retrograde cholangiopancreatography (ERCP), particularly post-ERCP pancreatitis (PEP). Key findings include identifying pancreatic steatosis as a novel risk factor and employing machine learning models for PEP prediction. Prophylactic measures have expanded to encompass rectal NSAIDs, aggressive fluid hydration, and pancreatic duct stents. These […]
Machine-learning model accurately predicts gallbladder polyp malignancy
A novel machine-learning model, particularly the random forest algorithm, distinguishes between benign and malignant gallbladder polyps, utilizing clinical and ultrasound data from 1,050 patients. Key predictive factors identified include polyp size, age, fibrinogen levels, and presence of stones. The model achieved impressive performance metrics with area under the curve values ranging from 0.940 to 0.963 […]
Systemic indocyanine green lowers bilirubin levels post-liver surgery
A clinical trial involving 84 liver surgery patients revealed that systemic administration of indocyanine green (ICG) significantly reduced total bilirubin concentration in postoperative drainage fluid, compared to historical controls. On postoperative day three, the intervention group showed a mean difference of -1.11 mg/dl (p
Future liver remnant optimization improves surgical outcomes.
Enhancing the future liver remnant (FLR) before major hepatectomy significantly boosts patient outcomes, addressing post-operative liver failure risks. Various techniques such as portal vein embolization, ligation, and liver venous deprivation show distinct advantages and limitations for FLR hypertrophy. While comparative studies exist, controlled trials are scarce. The review highlights current methodologies and underscores the critical […]
Chen’s pancreaticojejunostomy shows low complication rates in surgery
A recent study evaluated the efficacy of Chen’s pancreaticojejunostomy in laparoscopic pancreaticoduodenectomy among 112 patients with soft pancreatic texture and small main pancreatic ducts. The procedure yielded a low postoperative pancreatic fistula rate of 7.1%, all classified as grade B, with no grade C occurrences. The median operation time was 300 minutes, and the perioperative […]
Global Consensus Established for Managing Perihilar Cholangiocarcinoma
A multidisciplinary jury of 71 international experts produced 71 recommendations for managing perihilar cholangiocarcinoma (pcca) after reviewing 570 studies. Their consensus emphasized the need for centralized care and multidisciplinary expertise to improve patient outcomes, focusing on curative resection and minimizing morbidity. Through a systematic evidence review, the panel addressed key areas, including diagnosis, preoperative assessment, […]
Angioembolization use increases but in-hospital mortality remains unchanged
A comprehensive analysis of severe liver injuries revealed a stable in-hospital mortality rate of 18.7% from 2017 to 2022, despite increasing utilization of angioembolization as a treatment strategy. Compared to laparotomy, angioembolization—either alone or combined with other methods—demonstrated improved survival rates. However, observation only led to worsening outcomes over time. Findings indicate the necessity for […]
New Index Predicts Liver Failure Risk After Hepatectomy
A new preoperative assessment index integrating liver-to-spleen signal intensity ratio of the remnant liver and future liver volume effectively predicts post-hepatectomy liver failure (PHLF). In a study of 333 patients, those with a volume-adjusted ratio below 0.147 were significantly linked to PHLF, with a particularly high risk among patients who had portal vein embolization. The […]
Machine learning predicts perineural invasion in cholangiocarcinoma patients
A novel machine learning model effectively predicts perineural invasion (PNI) in intrahepatic cholangiocarcinoma (ICC) patients preoperatively, offering new insights for clinical decision-making. The XGBoost algorithm demonstrated superior predictive performance, highlighting tumor size, number, and lymph node metastasis as key factors. Significant differences were observed in postoperative outcomes, with better progression-free survival and overall survival in […]