Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery

Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to p...

Full description

Saved in:
Bibliographic Details
Main Authors: Benoit Schmauch, Sarah S. Elsoukkary, Amika Moro, Roma Raj, Chase J. Wehrle, Kazunari Sasaki, Julien Calderaro, Patrick Sin-Chan, Federico Aucejo, Daniel E. Roberts
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Journal of Pathology Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2153353923001748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119349327626240
author Benoit Schmauch
Sarah S. Elsoukkary
Amika Moro
Roma Raj
Chase J. Wehrle
Kazunari Sasaki
Julien Calderaro
Patrick Sin-Chan
Federico Aucejo
Daniel E. Roberts
author_facet Benoit Schmauch
Sarah S. Elsoukkary
Amika Moro
Roma Raj
Chase J. Wehrle
Kazunari Sasaki
Julien Calderaro
Patrick Sin-Chan
Federico Aucejo
Daniel E. Roberts
author_sort Benoit Schmauch
collection DOAJ
description Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.
format Article
id doaj-art-9df2723580f74a68805a47b36e4ecca2
institution OA Journals
issn 2153-3539
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Journal of Pathology Informatics
spelling doaj-art-9df2723580f74a68805a47b36e4ecca22025-08-20T02:35:39ZengElsevierJournal of Pathology Informatics2153-35392024-12-011510036010.1016/j.jpi.2023.100360Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgeryBenoit Schmauch0Sarah S. Elsoukkary1Amika Moro2Roma Raj3Chase J. Wehrle4Kazunari Sasaki5Julien Calderaro6Patrick Sin-Chan7Federico Aucejo8Daniel E. Roberts9Owkin Lab, Owkin, Inc., New York, NY, USAOwkin Lab, Owkin, Inc., New York, NY, USA; Department of Pathology, Cleveland Clinic, Cleveland, OH, USADepartment of Surgery, Cleveland Clinic, Cleveland, OH, USADepartment of Surgery, Cleveland Clinic, Cleveland, OH, USADepartment of Surgery, Cleveland Clinic, Cleveland, OH, USADepartment of Surgery, Stanford University, Palo Alto, CA, USADepartment of Pathology, Henri Mondor University Hospital, Créteil, FranceOwkin Lab, Owkin, Inc., New York, NY, USADepartment of Surgery, Cleveland Clinic, Cleveland, OH, USADepartment of Pathology, Cleveland Clinic, Cleveland, OH, USA; Corresponding author at: Cleveland Clinic, Department of Pathology, 2119 E 93rd St, Cleveland, OH 44106, USA.Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.http://www.sciencedirect.com/science/article/pii/S2153353923001748Hepatocellular carcinomaArtificial intelligenceMachine learningDeep learningPrognostic modeling
spellingShingle Benoit Schmauch
Sarah S. Elsoukkary
Amika Moro
Roma Raj
Chase J. Wehrle
Kazunari Sasaki
Julien Calderaro
Patrick Sin-Chan
Federico Aucejo
Daniel E. Roberts
Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
Journal of Pathology Informatics
Hepatocellular carcinoma
Artificial intelligence
Machine learning
Deep learning
Prognostic modeling
title Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
title_full Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
title_fullStr Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
title_full_unstemmed Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
title_short Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
title_sort combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
topic Hepatocellular carcinoma
Artificial intelligence
Machine learning
Deep learning
Prognostic modeling
url http://www.sciencedirect.com/science/article/pii/S2153353923001748
work_keys_str_mv AT benoitschmauch combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT sarahselsoukkary combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT amikamoro combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT romaraj combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT chasejwehrle combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT kazunarisasaki combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT juliencalderaro combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT patricksinchan combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT federicoaucejo combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery
AT danieleroberts combiningadeeplearningmodelwithclinicaldatabetterpredictshepatocellularcarcinomabehaviorfollowingsurgery