Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort

Objective:. This study aimed to (1) develop a machine learning (ML) model that predicts the textbook outcome in liver surgery (TOLS) using preoperative variables and (2) validate the TOLS criteria by determining whether TOLS is associated with long-term survival after hepatectomy. Background:. Textb...

Full description

Saved in:
Bibliographic Details
Main Authors: Jane Wang, MD, Amir Ashraf Ganjouei, MD, MPH, Taizo Hibi, MD, PhD, Nuria Lluis, MD, PhD, Camilla Gomes, MD, Fernanda Romero-Hernandez, MD, Han Yin, BA, Lucia Calthorpe, MD, Yukiyasu Okamura, MD, PhD, Yuta Abe, MD, PhD, Shogo Tanaka, MD, PhD, Minoru Tanabe, MD, PhD, Zeniche Morise, MD, PhD, Horacio Asbun, MD, PhD, David Geller, MD, Mohammed Abu Hilal, MD, PhD, Mohamed Adam, MD, Adnan Alseidi, MD, EdM, International Hepatectomy Study Group, Alison Baskin, Annie Wong-On-Wing, Annie Yang, Devesh Sharma, Taisuke Imamura, Masanori Nakamura, Yuya Miura, Koki Hayashi, Masatsugu Ishii, Keita Shimata, Kazuya Hirukawa, Hiroki Ueda, June S. Peng, Lucas Thornblade, Kenzo Hirose, Kimberly Kirkwood, Eric Nakakura, Carlos Corvera, Ajay Maker
Format: Article
Language:English
Published: Wolters Kluwer Health 2025-03-01
Series:Annals of Surgery Open
Online Access:http://journals.lww.com/10.1097/AS9.0000000000000539
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850092472933285888
author Jane Wang, MD
Amir Ashraf Ganjouei, MD, MPH
Taizo Hibi, MD, PhD
Nuria Lluis, MD, PhD
Camilla Gomes, MD
Fernanda Romero-Hernandez, MD
Han Yin, BA
Lucia Calthorpe, MD
Yukiyasu Okamura, MD, PhD
Yuta Abe, MD, PhD
Shogo Tanaka, MD, PhD
Minoru Tanabe, MD, PhD
Zeniche Morise, MD, PhD
Horacio Asbun, MD, PhD
David Geller, MD
Mohammed Abu Hilal, MD, PhD
Mohamed Adam, MD
Adnan Alseidi, MD, EdM
International Hepatectomy Study Group
Alison Baskin
Annie Wong-On-Wing
Annie Yang
Devesh Sharma
Taisuke Imamura
Masanori Nakamura
Yuya Miura
Koki Hayashi
Masatsugu Ishii
Keita Shimata
Kazuya Hirukawa
Hiroki Ueda
June S. Peng
Lucas Thornblade
Kenzo Hirose
Kimberly Kirkwood
Eric Nakakura
Carlos Corvera
Ajay Maker
author_facet Jane Wang, MD
Amir Ashraf Ganjouei, MD, MPH
Taizo Hibi, MD, PhD
Nuria Lluis, MD, PhD
Camilla Gomes, MD
Fernanda Romero-Hernandez, MD
Han Yin, BA
Lucia Calthorpe, MD
Yukiyasu Okamura, MD, PhD
Yuta Abe, MD, PhD
Shogo Tanaka, MD, PhD
Minoru Tanabe, MD, PhD
Zeniche Morise, MD, PhD
Horacio Asbun, MD, PhD
David Geller, MD
Mohammed Abu Hilal, MD, PhD
Mohamed Adam, MD
Adnan Alseidi, MD, EdM
International Hepatectomy Study Group
Alison Baskin
Annie Wong-On-Wing
Annie Yang
Devesh Sharma
Taisuke Imamura
Masanori Nakamura
Yuya Miura
Koki Hayashi
Masatsugu Ishii
Keita Shimata
Kazuya Hirukawa
Hiroki Ueda
June S. Peng
Lucas Thornblade
Kenzo Hirose
Kimberly Kirkwood
Eric Nakakura
Carlos Corvera
Ajay Maker
author_sort Jane Wang, MD
collection DOAJ
description Objective:. This study aimed to (1) develop a machine learning (ML) model that predicts the textbook outcome in liver surgery (TOLS) using preoperative variables and (2) validate the TOLS criteria by determining whether TOLS is associated with long-term survival after hepatectomy. Background:. Textbook outcome is a composite measure that combines several favorable outcomes into a single metric and represents the optimal postoperative course. Recently, an expert panel of surgeons proposed a Delphi consensus-based definition of TOLS. Methods:. Adult patients who underwent hepatectomies were identified from a multicenter, international cohort (2010–2022). After data preprocessing and train-test splitting (80:20), 4 models for predicting TOLS were trained and tested. Following model optimization, the performance of the models was evaluated using receiver operating characteristic curves, and a web-based calculator was developed. In addition, a multivariable Cox proportional hazards analysis was conducted to determine the association between TOLS and overall survival (OS). Results:. A total of 2059 patients were included, with 62.8% meeting the criteria for TOLS. The XGBoost model, which had the best performance with an area under the curve of 0.73, was chosen for the web-based calculator. The most predictive variables for having TOLS were a minimally invasive approach, fewer lesions, lower Charlson Comorbidity Index, lower preoperative creatinine levels, and smaller lesions. In the multivariable analysis, having TOLS was associated with improved OS (hazard ratio = 0.82, P = 0.015). Conclusions:. Our ML model can predict TOLS with acceptable discrimination. We validated the TOLS criteria by demonstrating a significant association with improved OS, thus supporting their use in informing patient care.
format Article
id doaj-art-02ffb26e4d3b4b6c84ef3f9aa528a2ec
institution DOAJ
issn 2691-3593
language English
publishDate 2025-03-01
publisher Wolters Kluwer Health
record_format Article
series Annals of Surgery Open
spelling doaj-art-02ffb26e4d3b4b6c84ef3f9aa528a2ec2025-08-20T02:42:08ZengWolters Kluwer HealthAnnals of Surgery Open2691-35932025-03-0161e53910.1097/AS9.0000000000000539202503000-00014Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International CohortJane Wang, MD0Amir Ashraf Ganjouei, MD, MPH1Taizo Hibi, MD, PhD2Nuria Lluis, MD, PhD3Camilla Gomes, MD4Fernanda Romero-Hernandez, MD5Han Yin, BA6Lucia Calthorpe, MD7Yukiyasu Okamura, MD, PhD8Yuta Abe, MD, PhD9Shogo Tanaka, MD, PhD10Minoru Tanabe, MD, PhD11Zeniche Morise, MD, PhD12Horacio Asbun, MD, PhD13David Geller, MD14Mohammed Abu Hilal, MD, PhD15Mohamed Adam, MD16Adnan Alseidi, MD, EdM17International Hepatectomy Study GroupAlison BaskinAnnie Wong-On-WingAnnie YangDevesh SharmaTaisuke ImamuraMasanori NakamuraYuya MiuraKoki HayashiMasatsugu IshiiKeita ShimataKazuya HirukawaHiroki UedaJune S. PengLucas ThornbladeKenzo HiroseKimberly KirkwoodEric NakakuraCarlos CorveraAjay MakerFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CAFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CA† Department of Pediatric Surgery and Transplantation, Kumamoto University Graduate School of Medical Sciences, Kumamoto, Japan‡ Hepato-Biliary and Pancreas Surgery, Miami Cancer Institute, Miami, FLFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CAFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CAFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CAFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CA§ Division of Hepato-Biliary-Pancreatic Surgery, Shizuoka Cancer Center, Shizuoka, Japan‖ Department of Surgery, Keio University School of Medicine, Tokyo, Japan¶ Department of Hepato-Biliary-Pancreatic Surgery, Osaka City University Graduate School of Medicine, Osaka, Japan# Department of Hepatobiliary and Pancreatic Surgery, Graduate School of Medicine, Tokyo Medical and Dental University, Tokyo, Japan** Department of Surgery, Okazaki Medical Center, Fujita Health University School of Medicine, Okazaki, Japan‡ Hepato-Biliary and Pancreas Surgery, Miami Cancer Institute, Miami, FL†† Department of Surgery, University of Pittsburgh Medical Center, Pittsburgh, PA‡‡ Department of General Surgery, Poliambulanza Foundation Hospital, Brescia, Italy.From the * Department of Surgery, University of California, San Francisco, San Francisco, CAFrom the * Department of Surgery, University of California, San Francisco, San Francisco, CAObjective:. This study aimed to (1) develop a machine learning (ML) model that predicts the textbook outcome in liver surgery (TOLS) using preoperative variables and (2) validate the TOLS criteria by determining whether TOLS is associated with long-term survival after hepatectomy. Background:. Textbook outcome is a composite measure that combines several favorable outcomes into a single metric and represents the optimal postoperative course. Recently, an expert panel of surgeons proposed a Delphi consensus-based definition of TOLS. Methods:. Adult patients who underwent hepatectomies were identified from a multicenter, international cohort (2010–2022). After data preprocessing and train-test splitting (80:20), 4 models for predicting TOLS were trained and tested. Following model optimization, the performance of the models was evaluated using receiver operating characteristic curves, and a web-based calculator was developed. In addition, a multivariable Cox proportional hazards analysis was conducted to determine the association between TOLS and overall survival (OS). Results:. A total of 2059 patients were included, with 62.8% meeting the criteria for TOLS. The XGBoost model, which had the best performance with an area under the curve of 0.73, was chosen for the web-based calculator. The most predictive variables for having TOLS were a minimally invasive approach, fewer lesions, lower Charlson Comorbidity Index, lower preoperative creatinine levels, and smaller lesions. In the multivariable analysis, having TOLS was associated with improved OS (hazard ratio = 0.82, P = 0.015). Conclusions:. Our ML model can predict TOLS with acceptable discrimination. We validated the TOLS criteria by demonstrating a significant association with improved OS, thus supporting their use in informing patient care.http://journals.lww.com/10.1097/AS9.0000000000000539
spellingShingle Jane Wang, MD
Amir Ashraf Ganjouei, MD, MPH
Taizo Hibi, MD, PhD
Nuria Lluis, MD, PhD
Camilla Gomes, MD
Fernanda Romero-Hernandez, MD
Han Yin, BA
Lucia Calthorpe, MD
Yukiyasu Okamura, MD, PhD
Yuta Abe, MD, PhD
Shogo Tanaka, MD, PhD
Minoru Tanabe, MD, PhD
Zeniche Morise, MD, PhD
Horacio Asbun, MD, PhD
David Geller, MD
Mohammed Abu Hilal, MD, PhD
Mohamed Adam, MD
Adnan Alseidi, MD, EdM
International Hepatectomy Study Group
Alison Baskin
Annie Wong-On-Wing
Annie Yang
Devesh Sharma
Taisuke Imamura
Masanori Nakamura
Yuya Miura
Koki Hayashi
Masatsugu Ishii
Keita Shimata
Kazuya Hirukawa
Hiroki Ueda
June S. Peng
Lucas Thornblade
Kenzo Hirose
Kimberly Kirkwood
Eric Nakakura
Carlos Corvera
Ajay Maker
Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
Annals of Surgery Open
title Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
title_full Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
title_fullStr Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
title_full_unstemmed Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
title_short Development and Validation of a Machine Learning Prediction Model for Textbook Outcome in Liver Surgery: Results From a Multicenter, International Cohort
title_sort development and validation of a machine learning prediction model for textbook outcome in liver surgery results from a multicenter international cohort
url http://journals.lww.com/10.1097/AS9.0000000000000539
work_keys_str_mv AT janewangmd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT amirashrafganjoueimdmph developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT taizohibimdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT nurialluismdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT camillagomesmd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT fernandaromerohernandezmd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT hanyinba developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT luciacalthorpemd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT yukiyasuokamuramdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT yutaabemdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT shogotanakamdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT minorutanabemdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT zenichemorisemdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT horacioasbunmdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT davidgellermd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT mohammedabuhilalmdphd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT mohamedadammd developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT adnanalseidimdedm developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT internationalhepatectomystudygroup developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT alisonbaskin developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT anniewongonwing developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT annieyang developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT deveshsharma developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT taisukeimamura developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT masanorinakamura developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT yuyamiura developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT kokihayashi developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT masatsuguishii developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT keitashimata developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT kazuyahirukawa developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT hirokiueda developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT junespeng developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT lucasthornblade developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT kenzohirose developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT kimberlykirkwood developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT ericnakakura developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT carloscorvera developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort
AT ajaymaker developmentandvalidationofamachinelearningpredictionmodelfortextbookoutcomeinliversurgeryresultsfromamulticenterinternationalcohort