[Benefit-risk assessment of three oral Chinese patent medicines for activating blood and eliminating mass in treating primary liver cancer based on network Meta-analysis and multi-criteria decision analysis].

Network Meta-analysis and multi-criteria decision analysis(MCDA) model were performed to evaluate the benefit-risk of Compound Cantharis Capsules, Huisheng Oral Solution, and Jinlong Capsules in the adjuvant treatment of primary liver cancer(PLC). The randomized controlled trial(RCT) of Compound Cantharis Capsules, Huisheng Oral Solution, and Jinlong Capsules in treating PLC were retrieved from CNKI, Wanfang, VIP, Web of Science, PubMed, and Cochrane Library. R 4.2 was employed to conduct a network Meta-analysis, on the basis of which the effect values of the three medicines were obtained by indirect comparison. MCDA was performed to establish the value tree based on the benefit-risk indexes. Hiview 3.2 was used to calculate the benefit values, risk values, and benefit-risk values of the three medicines in treating PLC, and a sensitivity analysis was carried out to evaluate the robustness of the results. Oracle Crystal Ball 11.1 was employed to optimize the evaluation results by Monte Carlo simulation. A total of 39 RCTs were included. The results showed that Compound Cantharis Capsules, Huisheng Oral Solution, and Jinlong Capsules combined with transcatheter arterial chemoembolization(TACE) had the benefit values of 45, 51 and 45, the risk values of 59, 47, and 41, and the benefit-risk values of 52, 49, and 43, respectively. The benefit-risk differences and [95%CI] of Compound Cantharis Capsules vs Huisheng Oral Solution, Compound Cantharis Capsules vs Jinlong Capsules, and Huisheng Oral Solution vs Jinlong Capsules were 3.00[-13.09, 21.82], 9.00[-4.39, 24.62], and 6.00[-8.84, 20.28], respectively. Based on the results of MCDA, Huisheng Oral Solution, Jinlong Capsules, and Compound Cantharis Capsules combined with TACE had the greatest benefit, the greatest risk, and the best overall benefit, respectively. Considering the efficacy and safety, the priority of the three oral Chinese patent medicines combined with TACE for treating PLC followed the trend of Compound Cantharis Capsules, Huisheng Oral Solution, and Jinlong Capsules.

P-CAB versus PPI in the eradication of Helicobacter pylori: a systematic review and network meta-analysis.

Background: The efficacy and safety of potassium-competitive acid blockers (P-CABs) in the eradication of Helicobacter pylori (Hp) remains controversial when compared with proton pump inhibitors (PPIs). Objectives: The current study set out to compare the differences in the eradication rate and adverse reactions between eradication regimens based on P-CAB or PPI drugs and the differences between the vonoprazan-based and the tegoprazan-based regimens to explore the efficacy and safety of different Hp eradication regimens. Data sources and methods: Databases including PubMed, EMBASE, Cochrane Library, and WOS were searched from the inception of these databases up to July 2023, and eligible randomized controlled trials (RCTs) were included. The outcome measures were the eradication rate and the incidence of adverse reactions of different regimens in treating Hp. The results were estimated as relative risk (RR) and its 95% confidence interval (CI), and R 4.2.1 software was used to perform the network meta-analysis (NMA). Results: A total of 20 studies were included in the analysis, involving 5815 patients with Hp. In terms of eradication rate, the 2-week vonoprazan-based triple regimen (V-Tri-2w) was the best, which was superior to the 2-week PPI-based quadruple regimen [P-Qua-2w, RR = 0.9, 95% CI: (0.85-0.95)] and the 1-week tegoprazan-based triple regimen [T-Tri-1w, RR = 0.79, 95% CI: (0.64-0.97)]; the 2-week tegoprazan-based quadruple regimen (T-Qua-2w) was superior to the 1-week PPI-based triple regimen [P-Tri-1w, RR = 0.82, 95% CI: (0.67-0.99)], and there was no difference between the remaining tegoprazan-based regimens and the PPI-based or vonoprazan-based regimens. In terms of the incidence of adverse reactions, the 2-week vonoprazan-based binary regimen (V-Bi-2w) was lower than that of the 2-week PPI-based quadruple regimen [P-Qua-2w, RR = 1.98, 95% CI: (1.57-2.52)]; there was no significant difference between 1 and 2 weeks for each regimen, such as the vonoprazan-based triple regimen [RR = 1.11, 95% CI: (0.82-1.52)]. Conclusion: In the eradication treatment of Hp, the efficacy and safety of vonoprazan-based regimens are generally better than those of PPI-based regimens. Among them, the V-Tri-2w regimen has the highest eradication rate and may be the preferred choice for Hp eradication.

Deep learning models for predicting the survival of patients with hepatocellular carcinoma based on a surveillance, epidemiology, and end results (SEER) database analysis.

Hepatocellular carcinoma (HCC) is a common malignancy with poor survival and requires long-term follow-up. Hence, we collected information on patients with Primary Hepatocellular Carcinoma in the United States from the Surveillance, Epidemiology, and EndResults (SEER) database. We used this information to establish a deep learning with a multilayer neural network (the NMTLR model) for predicting the survival rate of patients with Primary Hepatocellular Carcinoma. HCC patients pathologically diagnosed between January 2011 and December 2015 in the SEER (Surveillance, Epidemiology, and End Results) database of the National Cancer Institute of the United States were selected as study subjects. We utilized two deep learning-based algorithms (DeepSurv and Neural Multi-Task Logistic Regression [NMTLR]) and a machine learning-based algorithm (Random Survival Forest [RSF]) for model training. A multivariable Cox Proportional Hazards (CoxPH) model was also constructed for comparison. The dataset was randomly divided into a training set and a test set in a 7:3 ratio. The training dataset underwent hyperparameter tuning through 1000 iterations of random search and fivefold cross-validation. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). The accuracy of predicting 1-year, 3-year, and 5-year survival rates was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Area Under the Curve (AUC). The primary outcomes were the 1-year, 3-year, and 5-year overall survival rates. Models were developed using DeepSurv, NMTLR, RSF, and Cox Proportional Hazards regression. Model differentiation was evaluated using the C-index, calibration with concordance plots, and risk stratification capability with the log-rank test. The study included 2197 HCC patients, randomly divided into a training cohort (70%, n = 1537) and a testing cohort (30%, n = 660). Clinical characteristics between the two cohorts showed no significant statistical difference (p > 0.05). The deep learning models outperformed both RSF and CoxPH models, with C-indices of 0.735 (NMTLR) and 0.731 (DeepSurv) in the test dataset. The NMTLR model demonstrated enhanced accuracy and well-calibrated survival estimates, achieving an Area Under the Curve (AUC) of 0.824 for 1-year survival predictions, 0.813 for 3-year, and 0.803 for 5-year survival rates. This model's superior calibration and discriminative ability enhance its utility for clinical prognostication in Primary Hepatocellular Carcinoma. We deployed the NMTLR model as a web application for clinical practice. The NMTLR model have potential advantages over traditional linear models in prognostic assessment and treatment recommendations. This novel analytical approach may provide reliable information on individual survival and treatment recommendations for patients with primary liver cancer.