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

Summary: 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-lear...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tuyana Boldanova, Geoffrey Fucile, Jan Vosshenrich, Aleksei Suslov, Caner Ercan, Mairene Coto-Llerena, Luigi M. Terracciano, Christoph J. Zech, Daniel T. Boll, Stefan Wieland, Markus H. Heim
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/24d4d9cd9de347eb9e55f10515c24c82
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:24d4d9cd9de347eb9e55f10515c24c82
record_format dspace
spelling oai:doaj.org-article:24d4d9cd9de347eb9e55f10515c24c822021-11-18T04:52:12ZSupervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization2666-379110.1016/j.xcrm.2021.100444https://doaj.org/article/24d4d9cd9de347eb9e55f10515c24c822021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666379121003128https://doaj.org/toc/2666-3791Summary: 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.Tuyana BoldanovaGeoffrey FucileJan VosshenrichAleksei SuslovCaner ErcanMairene Coto-LlerenaLuigi M. TerraccianoChristoph J. ZechDaniel T. BollStefan WielandMarkus H. HeimElsevierarticleliver cancerlocoregional treatmenthepatocellular carcinomatransarterial chemoembolisationbiomarkerMedicine (General)R5-920ENCell Reports Medicine, Vol 2, Iss 11, Pp 100444- (2021)
institution DOAJ
collection DOAJ
language EN
topic liver cancer
locoregional treatment
hepatocellular carcinoma
transarterial chemoembolisation
biomarker
Medicine (General)
R5-920
spellingShingle liver cancer
locoregional treatment
hepatocellular carcinoma
transarterial chemoembolisation
biomarker
Medicine (General)
R5-920
Tuyana Boldanova
Geoffrey Fucile
Jan Vosshenrich
Aleksei Suslov
Caner Ercan
Mairene Coto-Llerena
Luigi M. Terracciano
Christoph J. Zech
Daniel T. Boll
Stefan Wieland
Markus H. Heim
Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
description Summary: 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.
format article
author Tuyana Boldanova
Geoffrey Fucile
Jan Vosshenrich
Aleksei Suslov
Caner Ercan
Mairene Coto-Llerena
Luigi M. Terracciano
Christoph J. Zech
Daniel T. Boll
Stefan Wieland
Markus H. Heim
author_facet Tuyana Boldanova
Geoffrey Fucile
Jan Vosshenrich
Aleksei Suslov
Caner Ercan
Mairene Coto-Llerena
Luigi M. Terracciano
Christoph J. Zech
Daniel T. Boll
Stefan Wieland
Markus H. Heim
author_sort Tuyana Boldanova
title Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
title_short Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
title_full Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
title_fullStr Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
title_full_unstemmed Supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
title_sort supervised learning based on tumor imaging and biopsy transcriptomics predicts response of hepatocellular carcinoma to transarterial chemoembolization
publisher Elsevier
publishDate 2021
url https://doaj.org/article/24d4d9cd9de347eb9e55f10515c24c82
work_keys_str_mv AT tuyanaboldanova supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT geoffreyfucile supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT janvosshenrich supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT alekseisuslov supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT canerercan supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT mairenecotollerena supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT luigimterracciano supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT christophjzech supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT danieltboll supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT stefanwieland supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
AT markushheim supervisedlearningbasedontumorimagingandbiopsytranscriptomicspredictsresponseofhepatocellularcarcinomatotransarterialchemoembolization
_version_ 1718424962566455296