Predicting Textbook Oncological Outcomes with Machine Learning: A Retrospective Review of Patients Who Underwent Resection for Malignant Tumours
- 1Faculty of Medicine and Health, The University of Sydney, Camperdown, NSW 2050, Australia
- 2Upper Gastrointestinal Surgical Unit, Royal North Shore Hospital, St Leonards, NSW 2065, Australia
- 3Faculty of Health and Medical Sciences, University of Adelaide, Adelaide SA 5000, Australia
Abstract
Introduction: Textbook oncological outcome (TOO) is a composite measure used to assess the quality of care in surgical oncology. Specifically, in liver surgery, it assesses several domains including intraoperative events, postoperative recovery, liver-specific complications, early mortality, and resection margins. Historically, one-third of patients undergoing liver resection have had a non-ideal outcome that has been difficult to predict. The aim of this study is to predict the risk of achieving textbook oncological outcome (TOO) using machine learning (ML) models for patients undergoing liver resection for malignant tumours. Methods: A retrospective cohort study of patients undergoing liver resection for malignant tumours was undertaken between 1999 and 2023 from a prospectively collected database. ML models were developed using preoperative variables as candidate predictors of TOO. Feature selection was performed using stability selection with LASSO regularisation. Model performance was evaluated using discrimination and calibration metrics. Model interpretability was assessed using SHapley Additive exPlanations. Predicted probabilities were stratified into tertiles to form risk groups (low, moderate, and high). Results: From the training cohort (n = 583), the RF model demonstrated the highest discrimination (AUROC = 0.813, 95% confidence interval [CI]= 0.731–0.877) for predicting TOO in the test cohort (n = 146). Post-recalibration, the Brier score was 0.162, calibration intercept was 0.06 and calibration slope was 0.92. The top three features were the extent of the resection, the site of the tumour, and the size of the largest tumour. TOO rates decreased in low-, moderate-, and high-risk groups (91%, 80% and 38% respectively, p < 0.001). Conclusions: An ML-based model for predicting TOO following liver resection demonstrated good discrimination and calibration metrics after recalibration. Risk stratification showed a clear gradient in TOO achievement, supporting its potential use in preoperative risk assessment and patient counselling. The current exploratory nature of this study necessitates further external validation before clinical application.
Related
- Association of steatotic liver disease with long-term oncological outcomes after hepatic resection for hepatocellular carcinoma
- Development and validation of a nomogram for predicting catheter-related complications after percutaneous transhepatic cholangial drainage in malignant obstructive jaundice patients: A retrospective study
- Development and internal validation of a nomogram for predicting high-risk postoperative status after thoracoscopic pulmonary wedge resection: a single-center retrospective cohort study.
- Local Recurrence and Oncological Outcomes After Transanal Total Mesorectal Excision With Intersphincteric Resection for Lower Rectal Cancer: A Nationwide Multicenter Cohort Study (Ta‐Ta‐Mi Study)
- Neurodevelopmental Outcomes of Very Preterm Infants Who Underwent Neonatal Gastrointestinal Surgery: A Single-Center Retrospective Cohort Study
BibTeX
@article{patel2026predicting,
title = {{Predicting Textbook Oncological Outcomes with Machine Learning: A Retrospective Review of Patients Who Underwent Resection for Malignant Tumours}},
author = {Meet Patel and Jonathan Ben Daniel and Nazim Bhimani and Joshua G. Kovoor and Arjun Fadia and Kai Brown and Anthony R. Glover and Thomas J. Hugh},
journal = {Journal of Clinical Medicine},
year = {2026},
month = nov,
doi = {10.3390/jcm15218527},
url = {https://www.mdpi.com/2077-0383/15/21/8527},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Predicting Textbook Oncological Outcomes with Machine Learning: A Retrospective Review of Patients Who Underwent Resection for Malignant Tumours
AU - Meet Patel
AU - Jonathan Ben Daniel
AU - Nazim Bhimani
AU - Joshua G. Kovoor
AU - Arjun Fadia
AU - Kai Brown
AU - Anthony R. Glover
AU - Thomas J. Hugh
PY - 2026
DA - 2026/11/02
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218527
UR - https://www.mdpi.com/2077-0383/15/21/8527
AB - Introduction: Textbook oncological outcome (TOO) is a composite measure used to assess the quality of care in surgical oncology. Specifically, in liver surgery, it assesses several domains including intraoperative events, postoperative recovery, liver-specific complications, early mortality, and resection margins. Historically, one-third of patients undergoing liver resection have had a non-ideal outcome that has been difficult to predict. The aim of this study is to predict the risk of achieving textbook oncological outcome (TOO) using machine learning (ML) models for patients undergoing liver resection for malignant tumours. Methods: A retrospective cohort study of patients undergoing liver resection for malignant tumours was undertaken between 1999 and 2023 from a prospectively collected database. ML models were developed using preoperative variables as candidate predictors of TOO. Feature selection was performed using stability selection with LASSO regularisation. Model performance was evaluated using discrimination and calibration metrics. Model interpretability was assessed using SHapley Additive exPlanations. Predicted probabilities were stratified into tertiles to form risk groups (low, moderate, and high). Results: From the training cohort (n = 583), the RF model demonstrated the highest discrimination (AUROC = 0.813, 95% confidence interval [CI]= 0.731–0.877) for predicting TOO in the test cohort (n = 146). Post-recalibration, the Brier score was 0.162, calibration intercept was 0.06 and calibration slope was 0.92. The top three features were the extent of the resection, the site of the tumour, and the size of the largest tumour. TOO rates decreased in low-, moderate-, and high-risk groups (91%, 80% and 38% respectively, p < 0.001). Conclusions: An ML-based model for predicting TOO following liver resection demonstrated good discrimination and calibration metrics after recalibration. Risk stratification showed a clear gradient in TOO achievement, supporting its potential use in preoperative risk assessment and patient counselling. The current exploratory nature of this study necessitates further external validation before clinical application.
SN - 2077-0383
ER -