Predictive Value of Preoperative Neutrophil-to-Lymphocyte Ratio in Patients with Hepatocellular Carcinoma after Transarterial Chemoembolization Combined With Radiofrequency Ablation.

PURPOSE: To determine the predictive value of preoperative inflammatory markers in hepatocellular carcinoma (HCC) prognosis after transarterial chemoembolization (TACE) combined with radiofrequency ablation (RFA). MATERIALS AND METHODS: A total of 161 patients with HCC who underwent TACE combined with RFA were enrolled in this retrospective study. Receiver operating characteristic (ROC) curve analysis was used to decide the cutoff value of the neutrophil-to-lymphocyte ratio (NLR), the lymphocyte-to-monocyte ratio (LMR), the platelet-to-lymphocyte ratio (PLR), and the prognostic nutritional index (PNI). The relationship between preoperative NLR, LMR, PLR, PNI, and survival outcomes was analyzed using Kaplan-Meier curves and multivariate Cox regression analyses. RESULTS: The cutoff value of NLR for the best discrimination of HCC prognosis was 2.95. The median recurrence-free survival (RFS) of the low NLR (≤2.95) group was longer than that of the high NLR (>2.95) group (29 months vs. 20 months, p = 0.013). The median overall survival (OS) of the low NLR group was longer than that of the high NLR group (60 months vs. 38 months, p = 0.006). Multivariate analysis showed that the tumor size (≤3 cm vs. >3cm), tumor number (single vs. multiple), and NLR (≤2.95 vs. >2.95) were independent predictors of the PFS and OS. LMR, PLR, and PNI did not have any prognostic significance. CONCLUSION: NLR was confirmed as an independent predictive biomarker for hepatocellular carcinoma prognosis after TACE combined with RFA.

Efficacy and Safety of Drug-Eluting Beads Transarterial Chemoembolization Combining Immune Checkpoint Inhibitors in Unresectable Intrahepatic Cholangiocarcinoma: A Propensity Score Matching Analysis.

Purpose: To assess the effectiveness and safety of drug-eluting beads transarterial chemoembolization plus immune checkpoint inhibitors (DEB-TACE+ICIs) versus chemotherapy (gemcitabine+cisplatin) for patients with unresectable intrahepatic cholangiocarcinoma (iCCA). Materials and Methods: This retrospective study included unresectable iCCA patients treated with DEB-TACE+ICIs or chemotherapy between May, 2019 and August, 2021. The differences in tumor responses, progression-free survival (PFS), overall survival (OS), and treatment-related adverse events (TRAEs) were compared between the 2 groups. Patient baseline characteristics, PFS, and OS were compared among 2 groups before and after propensity score-matching (PSM). Factors affecting PFS and OS were analyzed by Cox's proportional hazards regression model. Results: The study included 49 patients with unresectable iCCA patients, 20 in the DEB-TACE+ICIs group and 29 in the chemotherapy group. PSM analysis created 20 pairs of patients in 2 groups. The patients in the DEB-TACE+ICIs group had a higher objective response rate (55.0% vs. 20.0%, P=0.022), higher PFS (median, 7.2 vs. 5.7 months, P=0.036), and higher OS (median, 13.2 vs. 7.6 months, P=0.015) than those in the chemotherapy group. Multivariate analyses suggested that chemotherapy, tumor size >5cm, and multiple tumors were the independent risk factors for PFS and OS. The incidence of TRAEs was similar between the 2 groups. Conclusion: Compared to chemotherapy, DEB-TACE plus ICIs improved survival and was well-tolerated in patients with unresectable iCCA.

Efficacy and safety of transarterial chemoembolization combining sorafenib with or without immune checkpoint inhibitors in previously treated patients with advanced hepatocellular carcinoma: A propensity score matching analysis.

Purpose: To compare the efficacy and safety of transarterial chemoembolization (TACE) plus sorafenib and immune checkpoint inhibitors (T+S+ICIs) and TACE plus sorafenib (T+S) when treating patients with advanced hepatocellular carcinoma (HCC) who have previously received locoregional treatment. Materials and methods: A retrospective analysis was performed on the patients with Barcelona Clinic Liver Cancer (BCLC) stage C HCC from May 2019 to December 2020. These patients were treated with locoregional therapy and showed radiographic progression after the treatment. Patients received either T+S+ICIs or T+S. The outcomes, including disease control rate (DCR), progression-free survival (PFS), overall survival (OS), and safety, were compared. The propensity score matching (PSM) methodology was used to reduce the influence of confounding factors on the outcomes. Results: Forty-three patients were included in the T+S group and 33 in the T+S+ICI group. After PSM (n = 29 in each group), patients who received T+S+ICIs had a higher DCR (82.8% vs. 58.6%, p = 0.043), longer median PFS (6.9 vs. 3.8 months, p = 0.003), and longer median OS (12.3 vs. 6.3 months, p = 0.008) than those who underwent T+S. Eastern Cooperative Oncology Group performance status was an independent predictor of PFS, and age was an independent predictor of OS. The incidence of treatment-related adverse events in T+S+ICIs was well controlled. Conclusions: Compared with TACE combined with sorafenib, TACE combined with sorafenib plus ICIs is a potentially safe and effective treatment regimen for patients with advanced HCC who previously received locoregional treatment.

In silico prediction and screening of gamma-secretase inhibitors by molecular descriptors and machine learning methods.

Gamma-secretase inhibitors have been explored for the prevention and treatment of Alzheimer's disease (AD). Methods for prediction and screening of gamma-secretase inhibitors are highly desired for facilitating the design of novel therapeutic agents against AD, especially when incomplete knowledge about the mechanism and three-dimensional structure of gamma-secretase. We explored two machine learning methods, support vector machine (SVM) and random forest (RF), to develop models for predicting gamma-secretase inhibitors of diverse structures. Quantitative analysis of the receiver operating characteristic (ROC) curve was performed to further examine and optimize the models. Especially, the Youden index (YI) was initially introduced into the ROC curve of RF so as to obtain an optimal threshold of probability for prediction. The developed models were validated by an external testing set with the prediction accuracies of SVM and RF 96.48 and 98.83% for gamma-secretase inhibitors and 98.18 and 99.27% for noninhibitors, respectively. The different feature selection methods were used to extract the physicochemical features most relevant to gamma-secretase inhibition. To the best of our knowledge, the RF model developed in this work is the first model with a broad applicability domain, based on which the virtual screening of gamma-secretase inhibitors against the ZINC database was performed, resulting in 368 potential hit candidates.

Vesselplasty using the Mesh-Hold™ bone-filling container for the treatment of pathological vertebral fractures due to osteolytic metastases: A retrospective study.

PURPOSE: To evaluate the clinical benefits and complications of vesselplasty using the Mesh-Hold™ bone-filling container in the treatment of vertebral osteolytic fractures. METHODS: This was a retrospective study of patients with vertebral osteolytic pathological fractures treated by vesselplasty at Sichuan Cancer Hospital between 09/2014 and 01/2018. VAS1 (Visual analog scale) scores and ODI2 (Oswestry disability index) were recorded routinely 1 day preoperative, at 1 day, 1 month, 3 months, 6 months, and 1 year postoperation, and at the last follow-up. V13 (The of bone cement injection volume) and V24 (vertebral body osteolytic volume) were evaluated, and the R5 (ratio) of bone cement filling was obtained according to the V1/V2. RESULTS: Sixty-three patients were included (105 segments with osteolytic fractures). The amount of bone cement for each vertebra was 2.4-5.2 ml (3.1 ± 0.7 ml). The ratio (R) of bone cement filling was not related to pain relief or functional recovery (all P > 0.05).The VAS scores and ODI at different time points after surgery were decreased compared with before surgery (all P < 0.05). The bone cement leakage rate was 16.2 % (17/105). The follow-up was 4-30 months (mean of 13 ± 6 months). Thirty patients had died by the last follow-up, all from their cancer. CONCLUSIONS: The Mesh-Hold™ bone-filling container in the treatment of vertebral fractures induced by osteolytic metastases could reduce pain, improve function, and reduce the bone cement leakage rate in the process of vesselplasty.

Prediction of antibacterial compounds by machine learning approaches.

The machine learning (ML) as well as quantitative structure activity relationship (QSAR) method has been explored for predicting compounds with antibacterial activities at impressive performance. It is desirable to test additional ML methods, select most representative sets of molecular descriptors, and subject the developed prediction models to rigorous evaluations. This work evaluated three ML methods, support vector classification (SVC), k-nearest neighbor (k-NN), and C4.5 decision tree, which were trained and tested by 230 antibacterial and 381 nonantibacterial compounds. A well-established feature selection method was used to select representative molecular descriptors from a larger pool than that used in reported studies. The performance of the developed prediction models was tested by 5-fold cross-validation and independent evaluation set. SVC produced the best prediction accuracies of 96.66 and 98.15% for antibacterial compounds, and 99.50 and 98.02% for nonantibacterial compounds respectively, which are slightly improved against those of the reported ML as well as QSAR models and outperform the k-NN and C4.5 decision tree models developed in this work. Our study suggests that ML methods, particularly SVC, are potentially useful for facilitating the discovery of antibacterial agents.

In silico prediction of spleen tyrosine kinase inhibitors using machine learning approaches and an optimized molecular descriptor subset generated by recursive feature elimination method.

We tested four machine learning methods, support vector machine (SVM), k-nearest neighbor, back-propagation neural network and C4.5 decision tree for their capability in predicting spleen tyrosine kinase (Syk) inhibitors by using 2592 compounds which are more diverse than those in other studies. The recursive feature elimination method was used for improving prediction performance and selecting molecular descriptors responsible for distinguishing Syk inhibitors and non-inhibitors. Among four machine learning models, SVM produces the best performance at 99.18% for inhibitors and 98.82% for non-inhibitors, respectively, indicating that the SVM is potentially useful for facilitating the discovery of Syk inhibitors.

Prediction of novel and selective TNF-alpha converting enzyme (TACE) inhibitors and characterization of correlative molecular descriptors by machine learning approaches.

The inhibition of TNF-alpha converting enzyme (TACE) has been explored as a feasible therapy for the treatment of rheumatoid arthritis (RA) and Crohn's disease (CD). Recently, large numbers of novel and selective TACE inhibitors have been reported. It is desirable to develop machine learning (ML) models for identifying the inhibitors of TACE in the early drug design phase and test the prediction capabilities of these ML models. This work evaluated four ML methods, support vector machine (SVM), k-nearest neighbor (k-NN), back-propagation neural network (BPNN) and C4.5 decision tree (C4.5 DT), which were trained and tested by using a diverse set of 443 TACE inhibitors and 759 non-inhibitors. A well-established feature selection method, the recursive feature elimination (RFE) method, was used to select the most appropriate descriptors for classification from a large pool of descriptors, and two evaluation methods, 5-fold cross-validation and independent evaluation, were used to assess the performances of these developed models. In this study, all these ML models have already achieved promising prediction accuracies. By using the RFE method, the prediction accuracies are further improved. In k-NN, the model gives the best prediction for TACE inhibitors (98.32%), and the SVM bears the best prediction for non-inhibitors (99.51%). Both the k-NN and SVM model give the best overall prediction accuracy (98.45%). To the best of our knowledge, the SVM model developed in this work is the first one for the classification prediction of TACE inhibitors with a broad applicability domain. Our study suggests that ML methods, particularly SVM, are potentially useful for facilitating the discovery of TACE inhibitors and for exhibiting the molecular descriptors associated with TACE inhibitors.