Dataset Information

Deep Learning Predicts Overall Survival of Patients With Unresectable Hepatocellular Carcinoma Treated by Transarterial Chemoembolization Plus Sorafenib.

ABSTRACT: Objectives:To develop and validate a deep learning-based overall survival (OS) prediction model in patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization (TACE) plus sorafenib. Methods:This retrospective multicenter study consisted of 201 patients with treatment-naïve, unresectable HCC who were treated with TACE plus sorafenib. Data from 120 patients were used as the training set for model development. A deep learning signature was constructed using the deep image features from preoperative contrast-enhanced computed tomography images. An integrated nomogram was built using Cox regression by combining the deep learning signature and clinical features. The deep learning signature and nomograms were also externally validated in an independent validation set of 81 patients. C-index was used to evaluate the performance of OS prediction. Results:The median OS of the entire set was 19.2 months and no significant difference was found between the training and validation cohort (18.6 months vs. 19.5 months, P = 0.45). The deep learning signature achieved good prediction performance with a C-index of 0.717 in the training set and 0.714 in the validation set. The integrated nomogram showed significantly better prediction performance than the clinical nomogram in the training set (0.739 vs. 0.664, P = 0.002) and validation set (0.730 vs. 0.679, P = 0.023). Conclusion:The deep learning signature provided significant added value to clinical features in the development of an integrated nomogram which may act as a potential tool for individual prognosis prediction and identifying HCC patients who may benefit from the combination therapy of TACE plus sorafenib.

SUBMITTER: Zhang L

PROVIDER: S-EPMC7556271 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning Predicts Overall Survival of Patients With Unresectable Hepatocellular Carcinoma Treated by Transarterial Chemoembolization Plus Sorafenib.

Zhang Lei L Xia Wei W Yan Zhi-Ping ZP Sun Jun-Hui JH Zhong Bin-Yan BY Hou Zhong-Heng ZH Yang Min-Jie MJ Zhou Guan-Hui GH Wang Wan-Sheng WS Zhao Xing-Yu XY Jian Jun-Ming JM Huang Peng P Zhang Rui R Zhang Shen S Zhang Jia-Yi JY Li Zhi Z Zhu Xiao-Li XL Gao Xin X Ni Cai-Fang CF

Frontiers in oncology 20200930

<h4>Objectives</h4>To develop and validate a deep learning-based overall survival (OS) prediction model in patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization (TACE) plus sorafenib.<h4>Methods</h4>This retrospective multicenter study consisted of 201 patients with treatment-naïve, unresectable HCC who were treated with TACE plus sorafenib. Data from 120 patients were used as the training set for model development. A deep learning signature was constructed us ...[more]

PMID: 33102242

Similar Datasets

Project description:BACKGROUND:Transarterial chemoembolization (TACE) is the recommended treatment for hepatocellular carcinoma (HCC) patients at Barcelona Clinic Liver Cancer (BCLC) B-stage, whereas sorafenib is an orally administered small molecule target drug for BCLC C-stage. This updated systemic review and meta-analysis focuses on identifying the efficacy of the combination of TACE with sorafenib, which remains controversial despite years of exploration. METHODS:PubMed, EMBASE, Scopus and the Cochrane Library were systematically reviewed to search for studies published from January 1990 to May 2017. Studies focusing on the efficacy of combination therapy for unresectable HCC were eligible. The hazard ratio (HR) with 95% confidence intervals (95% CIs) for time to progression (TTP), overall survival (OS), disease control rate (DCR) and aetiology were collected. The data were then analysed through fixed/random effects meta-analysis models with STATA 13.0. The incidence and severity of treatment-related adverse events (AEs) were also evaluated. RESULTS:Twenty-seven studies were included. Thirteen non-comparative studies reported median OS (ranging from 18.5 to 20.4 months), median TTP (ranging from 7 to 13.9 months) and DCR (ranging from 18.4 to 95%). Fourteen comparative studies provided median OS (ranging from 7.0 to 29.7 months) and median TTP (ranging from 2.6 to 10.2 months). Five comparative studies provided DCR (ranging from 32 to 97.2%). Forest plots showed that combination therapy significantly improved TTP (HR?=?0.66, 95% CI 0.50-0.81, P?=?0.002) rather than OS (HR?=?0.63, 95% CI 0.55-0.71, P?=?0.058), compared to TACE alone. DCR increased significantly in the combination therapy group (OR?=?2.93, 95% CI 1.59-5.41, P?=?0.005). Additional forest plots were drawn and no significant differences were observed with regard to survival outcome among various aetiologies. Forest plots for separate analysis of regions showed the HR for TTP was 0.62 (95% CI 0.45-0.79, P?=?0.002) in the Asian countries group, and 0.82 (95% CI 0.59-1.05, P?=?0.504)) in western countries. The HR for OS was 0.61 (95% CI 0.48-0.75, P?=?0.050) in the Asian countries group and was 0.88 (95% CI 0.56-1.20, P?=?0.845) in western countries. These data may indicate positive TTP outcome in Asian patients but not in European patients while no positive findings regarding OS were observed in either region. The most common AEs included fatigue, hand-foot skin reaction, diarrhoea and hypertension. CONCLUSIONS:Combination therapy may benefit unresectable HCC patients in terms of prolonged TTP and DCR. More well-designed studies are needed to investigate its superiority for OS.

Project description:AimsThe purpose of the present study was to compare the efficacies of transarterial chemoembolization (TACE) combined with sorafenib versus TACE monotherapy for treating patients with advanced hepatocellular carcinoma (HCC).MethodsWe enrolled 321 patients and selected 280 with advanced HCC (Barcelona Clinic Liver Cancer stage C) who underwent TACE therapy between February 2009 and February 2013. TACE alone (monotherapy group) was administered to 198 patients (70.7%), and the remaining 82 (29.3%) underwent repeat combined TACE and sorafenib therapy (combined group). To minimize selection bias, these latter 82 patients were matched using propensity-score matching at a 1∶2 ratio with 164 patients who received TACE monotherapy. The primary endpoints were overall survival (OS) and related subgroup analysis. The secondary endpoints were time to progression (TTP) and treatment-related adverse events.ResultsOf the respective patients in the combined and monotherapy groups, 64.6% and 49.2% had vascular invasion, 87.8% and 91.1% had extrahepatic metastasis, and 54.3% and 47.1% had both. In the propensity-score-matched cohort, the OS survival of the combined group was significantly higher compared with the monotherapy group (7.0 months vs. 4.9 months, respectively, P = 0.003). The TTP was significantly longer in the combined group (2.6 months vs. 1.9 months, respectively, P = 0.001). Subgroup analysis showed that the outcomes of patients with advanced HCC without main portal vein invasion who were treated with combined therapy were significantly better compared with those who received monotherapy (P<0.05). Univariate and subsequent multivariate analyses revealed that the addition of sorafenib was an independent predictor of favorable OS and TTP (adjusted hazard ratios, 0.63 and 0.62, respectively; P<0.05 for both).ConclusionSorafenib plus TACE was more effective than TACE monotherapy for treating patients with advanced HCC without main portal vein invasion. Future trials with larger samples are required to validate these preliminary findings.

Project description:BackgroundSorafenib and transarterial chemoembolization (TACE) might both provide survival benefit for advanced hepatocellular carcinoma (HCC). Adopting either as a first-line therapy carries major cost and resource implications. We aimed to estimate the cost-effectiveness of sorafenib and TACE in advanced HCC.MethodsA Markov model was constructed in a hypothetical cohort of patients aged 60 years with advanced HCC and Child-Pugh A/B cirrhosis over a 2-year time frame. Three strategies (full or dose-adjusted sorafenib and TACE) were compared in two cost settings: China and the USA. Transition probabilities, utility and costs were extracted from systematic review of 27 articles. Sensitivity analysis and Monte Carlo analysis were conducted.ResultsFull and dose-adjusted sorafenib respectively produced 0.435 and 0.482 quality-adjusted life years (QALYs) while TACE produced 0.375 QALYs. The incremental cost-effectiveness ratio (ICER) of full-dose sorafenib versus TACE was $101,028.83/QALY in China whereas full-dose sorafenib is a dominant strategy (ICER of -$1,014,507.20/ QALY) compared with TACE in the USA. Compared to full-dose sorafenib, dose-adjusted sorafenib was the dominant strategy with the negative ICERs in both China (-$132,238.94/QALY) and the USA (-$230,058.09/QALY). However, dose-adjusted sorafenib is not available currently, so full-dose sorafenib should be compared with TACE. As the acceptability curves shown, full-dose sorafenib was the optimal strategy at the accepted thresholds of WTP in these two countries. Specifically, full-dose sorafenib was the cost-effective treatment compared with TACE if a WTP was set above $21,670 in the USA, whereas in China, TACE could be more favorable than full-dose sorafenib if a WTP was set below $10,473.ConclusionsDose-adjusted sorafenib may be cost-effective compared to full-dose sorafenib or TACE for advanced HCC patients. However, when confining the comparisons between full-dose sorafenib and TACE, full-dose sorafenib was cost-effective for these patients, under the accepted thresholds of WTP.

Dataset Information

Deep Learning Predicts Overall Survival of Patients With Unresectable Hepatocellular Carcinoma Treated by Transarterial Chemoembolization Plus Sorafenib.

Publications

Deep Learning Predicts Overall Survival of Patients With Unresectable Hepatocellular Carcinoma Treated by Transarterial Chemoembolization Plus Sorafenib.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure