Dataset Information

Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization.

ABSTRACT: Although transarterial chemoembolization (TACE) is the most widely used treatment for intermediate-stage, unresectable hepatocellular carcinoma (HCC), it is only effective in a subset of patients. In this study, we combine clinical, radiological, and genomics data in supervised machine-learning models toward the development of a clinically applicable predictive classifier of response to TACE in HCC patients. Our study consists of a discovery cohort of 33 tumors through which we identify predictive biomarkers, which are confirmed in a validation cohort. We find that radiological assessment of tumor area and several transcriptomic signatures, primarily the expression of FAM111B and HPRT1, are most predictive of response to TACE. Logistic regression decision support models consisting of tumor area and RNA-seq gene expression estimates for FAM111B and HPRT1 yield a predictive accuracy of ∼90%. Reverse transcription droplet digital PCR (RT-ddPCR) confirms these genes in combination with tumor area as a predictive classifier for response to TACE.

SUBMITTER: Boldanova T

PROVIDER: S-EPMC8606904 | biostudies-literature | 2021 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization.

Boldanova Tuyana T Fucile Geoffrey G Vosshenrich Jan J Suslov Aleksei A Ercan Caner C Coto-Llerena Mairene M Terracciano Luigi M LM Zech Christoph J CJ Boll Daniel T DT Wieland Stefan S Heim Markus H MH

Cell reports. Medicine 20211116 11

Although transarterial chemoembolization (TACE) is the most widely used treatment for intermediate-stage, unresectable hepatocellular carcinoma (HCC), it is only effective in a subset of patients. In this study, we combine clinical, radiological, and genomics data in supervised machine-learning models toward the development of a clinically applicable predictive classifier of response to TACE in HCC patients. Our study consists of a discovery cohort of 33 tumors through which we identify predicti ...[more]

PMID: 34841291

Similar Datasets

Project description:Transarterial chemoembolization (TACE) is the mainstay of treatment for patients with intermediate/advanced stage or unresectable hepatocellular carcinoma (HCC). Despite the palliative nature of TACE treatment, embolizing the tumor feeding vessels and leading to progressive tumor necrosis, complete response (CR) after TACE could still be observed in a certain population. Thus, this study aimed to investigate both the predictors for CR and the long-term prognosis of the patients with CR after TACE. The study recruited new diagnosed HCC patients initially treated with TACE from 2010 to 2013. Post TACE response was assessed by scheduled image studies according to the modified Response Evaluation Criteria in Solid Tumors (mRECIST). Then, pre-TACE factors were compared between patients with and without CR. After the first session of TACE, 22.3% of the 669 TACE treated patients achieved CR. During a median of 26.6 months follow-up, patients with CR had better overall survival than those without (median: 35.8 vs. 24.0 months, P<0.001). By multivariate logistic regression analysis, Child-Turcotte-Pugh class B (OR: 0.419, P=0.005), tumor burden beyond up-to-7 criteria (OR: 0.118, P<0.001), bilobar tumor extent (OR: 0.236, P<0.001), higher alpha-fetoprotein (AFP) level (≥20 ng/ml, OR: 0.614, P=0.039) and higher platelet counts (>150 k/μl, OR: 0.482, P=0.002) were unfavorable predictors for CR after first TACE. In addition, macrovascular invasion (HR: 3.113, P=0.001) and higher AFP levels (≥15 ng/ml, HR: 2.601, P=0.007) were predictors for early HCC recurrence whereas diabetes mellitus (DM) (HR: 2.166, P=0.006) was the only significant predictor for late HCC recurrence in CR patients. In conclusion, more than one-fifth of HCC patients achieved CR after first TACE and these patients had favorable prognosis. Furthermore, tailored post-TACE follow-up strategies shall be considered in patients with different risk factors of early or late recurrence after CR.

Dataset Information

Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization.

Publications

Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets