A Machine Learning Algorithm Facilitates Prognosis Prediction and Treatment Selection for Barcelona Clinic Liver Cancer Stage C Hepatocellular Carcinoma.

PURPOSE: Given its heterogeneity and diverse clinical outcomes, precise subclassification of Barcelona Clinic Liver Cancer stage C (BCLC-C) hepatocellular carcinoma (HCC) is required for appropriately determining patient prognosis and selecting treatment. EXPERIMENTAL DESIGN: We recruited 2,626 patients with BCLC-C HCC from multiple centers, comprising training/test (n = 1,693) and validation cohorts (n = 933). The XGBoost model was chosen for maximum performance among the machine learning (ML) models. Patients were categorized into low-, intermediate-, high-, and very high-risk subgroups based on the estimated prognosis, and this subclassification was named the CLAssification via Machine learning of BCLC-C (CLAM-C). RESULTS: The areas under the receiver operating characteristic curve of the CLAM-C for predicting the 6-, 12-, and 24-month survival of patients with BCLC-C were 0.800, 0.831, and 0.715, respectively-significantly higher than those of the conventional models, which were consistent in the validation cohort. The four subgroups had significantly different median overall survivals, and this difference was maintained among various patient subgroups and treatment modalities. Immune-checkpoint inhibitors and transarterial therapies were associated with significantly better survival than tyrosine kinase inhibitors (TKI) in the low- and intermediate-risk subgroups. In cases with first-line systemic therapy, the CLAM-C identified atezolizumab-bevacizumab as the best therapy, particularly in the high-risk group. In cases with later-line systemic therapy, nivolumab had better survival than TKIs in the low-to-intermediate-risk subgroup, whereas TKIs had better survival in the high- to very high-risk subgroup. CONCLUSIONS: ML modeling effectively subclassified patients with BCLC-C HCC, potentially aiding treatment allocation. Our study underscores the potential utilization of ML modeling in terms of prognostication and treatment allocation in patients with BCLC-C HCC.

Early development of de novo hepatocellular carcinoma after direct-acting agent therapy: Comparison with pegylated interferon-based therapy in chronic hepatitis C patients.

Patients with chronic hepatitis C who achieve a sustained viral response after pegylated interferon therapy have a reduced risk of hepatocellular carcinoma, but the risk after treatment with direct-acting antivirals is unclear. We compared the rates of early development of hepatocellular carcinoma after direct-acting antivirals and after pegylated interferon therapy. We retrospectively analysed 785 patients with chronic hepatitis C who had no history of hepatocellular carcinoma (211 treated with pegylated interferon, 574 with direct-acting antivirals) and were followed up for at least 24 weeks after antiviral treatment. De novo hepatocellular carcinoma developed in 6 of 574 patients receiving direct-acting antivirals and in 1 of 211 patients receiving pegylated interferon. The cumulative incidence of early hepatocellular carcinoma development did not differ between the treatment groups either for the whole cohort (1.05% vs 0.47%, P = .298) or for those patients with Child-Pugh Class A cirrhosis (3.73% vs 2.94%, P = .827). Multivariate analysis indicated that alpha-fetoprotein level >9.5 ng/mL at the time of end-of-treatment response was the only independent risk factor for early development of hepatocellular carcinoma in all patients (P < .0001, hazard ratio 176.174, 95% confidence interval 10.768-2882.473) and in patients treated with direct-acting agents (P < .0001, hazard ratio 128.402, 95% confidence interval 8.417-1958.680). In conclusion, the rate of early development of hepatocellular carcinoma did not differ between patients treated with pegylated interferon and those treated with direct-acting antivirals and was associated with the serum alpha-fetoprotein level at the time of end-of-treatment response.

Effects of gentamicin monotherapy for the initial treatment of community-onset complicated non-obstructive acute pyelonephritis due to Enterobacteriaceae in elderly and non-elderly women.

Aminoglycosides may serve as fluoroquinolone-sparing or cephalosporin-sparing agents if the clinical effectiveness of aminoglycoside monotherapy is demonstrated. The purposes of this study were to investigate the clinical efficacy of gentamicin as an initial empirical antimicrobial agent and to evaluate the effects of gentamicin resistance on clinical outcomes in women with complicated non-obstructive acute pyelonephritis (APN). Medical records of 1066 women with a diagnosis of APN were reviewed retrospectively. We enrolled 275 women with community-onset complicated non-obstructive APN due to Enterobacteriaceae who received gentamicin as their initial antibiotic. Of these 275 patients, 43 had gentamicin-resistant (GM-R) Enterobacteriaceae APN, and 232 had gentamicin-susceptible (GM-S) Enterobacteriaceae APN. The early clinical success rates were 67.4% (29/43) versus 89.7% (208/232) at 72 h in the GM-R versus the GM-S groups (p 0.001). The overall clinical cure rate was 100% (43/43) and 98.7% (229/232) in the GM-R and GM-S groups, respectively. The duration of hospital stay was significantly longer in the elderly, although there were no significant differences in the rates of early clinical success, final clinical cure, mortality, and time to fever clearance between the elderly and non-elderly groups. Resistance of Enterobacteriaceae to gentamicin, haematuria and serum C-reactive protein level≥20 mg/dL were independently associated with early clinical failure. Gentamicin can be an effective initial antibiotic option for empirical therapy in women with community-onset complicated APN who do not need urological interventional procedures. The use of gentamicin may contribute to a reduction of fluoroquinolone or broad-spectrum cephalosporin use in the treatment of complicated APN.