In recent years,significant progress has been made in the radiological diagnosis,molecular profiling,and systemic therapy of cholangiocarcinoma(CCA).Nevertheless,there are still many challenges in early identification,precise classification,and effective management.Given the marked heterogeneity between CCA subtypes and the recent research advances,the European Association for the Study of the Liver has developed evidence-based management recommendations for extrahepatic CCA,covering both perihilar and distal subtypes.This guideline particularly emphasizes the need for precise classification systems,the integration of emerging molecular studies,and practical diagnostic and therapeutic strategies reflecting real-world clinical scenarios.

Objective:To investigate the efficacy of anatomical resection (AR) in the early stages of treating solitary hepatocellular carcinoma (HCC) combined with liver cirrhosis with a diameter of ≤5 cm in comparison to different surgical methods of preferential hepatic parenchymal preservation (non-anatomical liver resection, NAR).Methods:The clinical data of 1 390 cases with solitary HCC combined with liver cirrhosis at an early stage who underwent liver resection at Mengchao Hepatobiliary Hospital of Fujian Medical University and six other medical centers from September 2013 to May 2019 were retrospectively analyzed. Patients were divided into the AR group (486 cases) and the NAR group (904 cases) and the wide surgical margin (WSM) group (745 cases) and the narrow surgical margin (NSM) group (645 cases) according to whether they received AR and the width of the surgical margin (1 cm). The basic information of the patients, preoperative evaluation index data, and postoperative follow-up (follow-up every 3 months) were collected. The Kaplan-Meier method was used to plot the survival curve.The log-rank test was used to compare the difference in survival between the two groups. The Cox proportional hazards regression model was used to analyze the factors affecting the prognosis. Propensity score matching (PSM) was applied to reduce intergroup bias.Results:The overall survival (OS) rates for all patients at 1, 3, and 5 years were 95.5%, 79.9%, and 63.5%, respectively. The recurrence-free survival (RFS) rates were 81.5%, 59.0%, and 43.7%, respectively. There was a statistically significant difference in RFS rate between the AR group and the NAR group prior to PSM, but no statistically significant difference in OS rate (RFS rate: 47.0% vs. 41.9%, P<0.05; OS rate: 64.4% vs. 62.9%, P>0.05). The postoperative RFS rate and OS rate were significantly superior in the WSM group than those of the NSM group (RFS rate: 47.8% vs. 37.2%, P<0.001; OS rate: 69.0% vs. 57.3%, P<0.001). There was no statistically significant difference in OS rate and RFS rate between the AR group and the NAR group following PSM (RFS: 46.3% vs. 45.1%, P>0.05; OS rate: 64.0% vs. 64.3%, P>0.05).The 5-year OS and RFS rates in the WSM group were 66.8% and 60.2%, respectively. The 5-year OS and RFS rates for the NSM group were 48.7% and 41.4%, respectively, with a statistically significant difference ( P<0.05). Cox multivariate analysis indicated that serum albumin, tumor diameter, microvascular invasion, and surgical margin were independent prognostic factors affecting OS and RFS. The Child-Pugh grade and satellite lesions were independent prognostic factors affecting OS. Conclusion:Anatomical liver resection is not an independent risk factor for prognosis, but the state of the resection margin determines the prognosis of patients with solitary HCC combined with cirrhosis. Therefore, hepatic resection margins should be prioritized in such patients.

OBJECTIVE To provide a reference for optimizing and promoting the quality standards of Shechuan naolitong granules. METHODS Fifteen batches of Shechuan naolitong granules were used as samples to establish HPLC fingerprints using the Similarity Evaluation System for Chromatographic Fingerprint of Traditional Chinese Medicine （2012 edition）. Similarity evaluation and common peak identification were performed， and orthogonal partial least squares discriminant analysis （OPLS-DA） was used to assess quality differences among different batches and to screen quality differential components. Using salvianolic acid B（SAB） as the internal reference， quantitative analysis of multi-components by single-marker （QAMS） was developed to simultaneously determine geniposidic acid （GA）， chlorogenic acid （CA）， vaccarin （VA）， ferulic acid （FA） and senkyunolide I （SI）. The results were compared with those obtained by the external standard method. RESULTS A total of 13 common peaks were identified in the HPLC fingerprints of 15 batches of samples， and the similarities of the spectra were all above 0.96. Seven chromatographic peaks were identified as GA （peak 3）， CA （peak 6）， VA （peak 8）， FA （peak 9）， SI （peak 11）， SAB（peak 12） and TA（peak 13）. OPLS-DA indicated that the differential quality markers among 15 batches were peaks 5， 11 （SI）， and 12 （SAB）.Using SAB as the internal reference， the relative correction factors for GA， CA， VA， FA and SI were calculated as 1.058 4， 0.594 3， 0.643 3， 0.342 7 and 0.262 8， respectively. The mean content of GA， CA， VA， FA， SI and SAB across the 15 batches of samples were 0.155 0， 0.085 4， 0.140 3， 0.071 8， 0.072 7， 1.276 3 mg/g， respectively， showing no significant difference compared with the ESM （P＞0.05）. CONCLUSIONS The established HPLC fingerprint and QAMS are simple， efficient and economical， providing a reference for the quality control and further development of Shechuan naolitong granules.

In recent years,significant progress has been made in the radiological diagnosis,molecular profiling,and systemic therapy of cholangiocarcinoma(CCA).Nevertheless,there are still many challenges in early identification,precise classification,and effective management.Given the marked heterogeneity between CCA subtypes and the recent research advances,the European Association for the Study of the Liver has developed evidence-based management recommendations for extrahepatic CCA,covering both perihilar and distal subtypes.This guideline particularly emphasizes the need for precise classification systems,the integration of emerging molecular studies,and practical diagnostic and therapeutic strategies reflecting real-world clinical scenarios.

Objective:To investigate the efficacy of anatomical resection (AR) in the early stages of treating solitary hepatocellular carcinoma (HCC) combined with liver cirrhosis with a diameter of ≤5 cm in comparison to different surgical methods of preferential hepatic parenchymal preservation (non-anatomical liver resection, NAR).Methods:The clinical data of 1 390 cases with solitary HCC combined with liver cirrhosis at an early stage who underwent liver resection at Mengchao Hepatobiliary Hospital of Fujian Medical University and six other medical centers from September 2013 to May 2019 were retrospectively analyzed. Patients were divided into the AR group (486 cases) and the NAR group (904 cases) and the wide surgical margin (WSM) group (745 cases) and the narrow surgical margin (NSM) group (645 cases) according to whether they received AR and the width of the surgical margin (1 cm). The basic information of the patients, preoperative evaluation index data, and postoperative follow-up (follow-up every 3 months) were collected. The Kaplan-Meier method was used to plot the survival curve.The log-rank test was used to compare the difference in survival between the two groups. The Cox proportional hazards regression model was used to analyze the factors affecting the prognosis. Propensity score matching (PSM) was applied to reduce intergroup bias.Results:The overall survival (OS) rates for all patients at 1, 3, and 5 years were 95.5%, 79.9%, and 63.5%, respectively. The recurrence-free survival (RFS) rates were 81.5%, 59.0%, and 43.7%, respectively. There was a statistically significant difference in RFS rate between the AR group and the NAR group prior to PSM, but no statistically significant difference in OS rate (RFS rate: 47.0% vs. 41.9%, P<0.05; OS rate: 64.4% vs. 62.9%, P>0.05). The postoperative RFS rate and OS rate were significantly superior in the WSM group than those of the NSM group (RFS rate: 47.8% vs. 37.2%, P<0.001; OS rate: 69.0% vs. 57.3%, P<0.001). There was no statistically significant difference in OS rate and RFS rate between the AR group and the NAR group following PSM (RFS: 46.3% vs. 45.1%, P>0.05; OS rate: 64.0% vs. 64.3%, P>0.05).The 5-year OS and RFS rates in the WSM group were 66.8% and 60.2%, respectively. The 5-year OS and RFS rates for the NSM group were 48.7% and 41.4%, respectively, with a statistically significant difference ( P<0.05). Cox multivariate analysis indicated that serum albumin, tumor diameter, microvascular invasion, and surgical margin were independent prognostic factors affecting OS and RFS. The Child-Pugh grade and satellite lesions were independent prognostic factors affecting OS. Conclusion:Anatomical liver resection is not an independent risk factor for prognosis, but the state of the resection margin determines the prognosis of patients with solitary HCC combined with cirrhosis. Therefore, hepatic resection margins should be prioritized in such patients.

In recent years, the artificial intelligence machine learning and deep learning technology have made leap progress. Using clinical decision support system for auxiliary diagnosis and treatment is the inevitable developing trend of wisdom medical. Clinicians tend to ignore the interpretability of models while pursuing its high accuracy, which leads to the lack of trust of users and hamper the application of clinical decision support system. From the perspective of explainable artificial intelligence, the authors make some preliminary exploration on the construction of clinical decision support system in the field of liver disease. While pursuing high accuracy of the model, the data governance techniques, intrinsic interpretability models, post-hoc visualization of complex models, design of human-computer interactions, providing knowledge map based on clinical guidelines and data sources are used to endow the system with interpretability.

Objective:To investigate the application value of machine learning algorithms for preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).Methods:The retrospective and descriptive study was conducted. The clinicopathological data of 277 patients with HCC who were admitted to Mengchao Hepatobiliary Hospital of Fujian Medical University between May 2015 and December 2018 were collected. There were 235 males and 42 females, aged (56±10)years, with a range from 33 to 80 years. Patients underwent preoperative magnetic resonance imaging examination. According to the random numbers showed in the computer, all the 277 HCC patients were divided into training dataset consisting of 193 and validation dataset consisting of 84, with a ratio of 7∶3. Machine learning algorithms, including logistic regression nomogram, support vector machine (SVM), random forest (RF), artificial neutral network (ANN) and light gradient boosting machine (LightGBM), were used to develop models for preoperative prediction of MVI. Observation indicators: (1) analysis of clinicopathological data of patients in the training dataset and validation dataset; (2) analysis of risk factors for tumor MVI of the training dataset; (3) construction of machine learning algorithm prediction models and comparison of their accuracy of preoperative tumor MVI prediction. Measurement data with normal distribution were represented as Mean± SD, and comparison between groups was analyzed using the paired t test. Count data were described as absolute numbers, and comparison between groups was analyzed using the chi-square test. Univariate and multivariate analyses were performed using the Logistic regression model. Results:(1) Analysis of clinicopathological data of patients in the training dataset and validation dataset: there were 157 males and 36 females in the training dataset, 78 males and 6 females in the validation dataset, showing a significant difference in the sex between the training dataset and validation dataset ( χ2=6.028, P<0.05). (2) Analysis of risk factors for tumor MVI of the training dataset: of the 193 patients, 108 had positive MVI, and 85 had negative MVI. Results of univariate analysis showed that age, the number of tumors, tumor diameter, satellite lesions, tumor margin, alpha fetaprotein (AFP), alkaline phosphatase (ALP), fibrinogen were related factors for tumor MVI [ odds ratio ( OR)=0.971, 2.449, 1.368, 4.050, 2.956, 4.083, 2.532, 1.996, 95% confidence interval ( CI): 0.943-1.000, 1.169-5.130, 1.180-1.585, 1.316-12.465, 1.310-6.670, 2.214-7.532, 1.016-6.311, 1.323-3.012, P<0.05]. Results of multivariate analysis showed that AFP>20 μg/L, multiple tumors, larger tumor diameter, unsmooth tumor margin were independent risk factors for tumor MVI ( OR=3.680, 3.100, 1.438, 3.628, 95% CI: 1.842-7.351, 1.334-7.203, 1.201-1.721, 1.438-9.150, P<0.05). Larger age was associated with lower risk of preoperative tumor MVI ( OR=0.958, 95% CI: 0.923-0.994, P<0.05). (3) Construction of machine learning algorithm prediction models and comparison of their accuracy of preoperative tumor MVI prediction: ①machine learning algorithm prediction models involving logistic regression nomogram, SVM, RF, ANN and LightGBM were constructed based on results of multivariate analysis including age, AFP, the number of tumors, tumor diameter, tumor margin, and consistency analysis of the logistic regression nomogram prediction model showed a good stability. For the training dataset and validation dataset, the area under curve (AUC) of logistic regression nomogram model, SVM model, RF model, ANN model, LightGBM model was 0.812, 0.794, 0.807, 0.814, 0.810 and 0.784, 0.793, 0.783, 0.803, 0.815, respectively, showing no significant difference between SVM model and logistic regression nomogram model, between RF model and logistic regression nomogram model, between ANN model and logistic regression nomogram model, between LightGBM model and logistic regression nomogram model [(95% CI: 0.731-0.849, 0.744-0.860, 0.752-0.867, 0.747-0.862, Z=0.995, 0.245, 0.130, 0.102, P>0.05) and (95% CI: 0.690-0.873, 0.679-0.865, 0.702-0.882, 0.715-0.891, Z=0.325, 0.026, 0.744, 0.803, P>0.05)]. ② Clinicopathological factors were selected using RF, LightGBM machine learning algorithm to construct corresponding prediction models. According to importance scale of factors to prediction models, factors with importance scale>0.01 were selected to construct RF model, including age, tumor diameter, AFP, white blood cell, platelet, total bilirubin, aspartate transaminase, γ-glutamyl transpeptidase, ALP, and fibrinogen. Factors with importance scale>5.0 were selected to construct LightGBM model, including age, tumor diameter, AFP, white blood cell, ALP, and fibrinogen. Due to lack of factor selection ability, factors based on results of univariate analysis were secected to construct SVM model and ANN model, including age, the number of tumors, tumor diameter, satellite lesions, tumor margin, AFP, ALP, and fibrinogen. For the training dataset and validation dataset, the AUC of SVM model, RF model, ANN model, LightGBM model was 0.803, 0.838, 0.793, 0.847 and 0.810, 0.802, 0.802, 0.836, respectively, showing no significant difference between SVM model and logistic regression nomogram model, between RF model and logistic regression nomogram model, between ANN model and logistic regression nomogram model, between LightGBM model and logistic regression nomogram model [(95% CI: 0.740-0.857, 0.779-0.887, 0.729-0.848, 0.789-0.895, Z=0.421, 0.119, 0.689, 1.517, P>0.05) and (95% CI: 0.710-0.888, 0.700-0.881, 0.701-0.881, 0.740-0.908, Z=0.856, 0.458, 0.532, 1.306, P>0.05)]. Conclusion:Machine learning algorithms can predict MVI of HCC preoperatively, but its application value needs to be further verified by large sample data from multi centers.