A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly

Frailty in the elderly population is associated with increased vulnerability to stressors, including surgical interventions. This study compared machine learning (ML) models with a clinical bedside tool, the Gastrointestinal Surgery Frailty Index (GiS-FI), for predicting mortality and morbidity in e...

Full description

Saved in:
Bibliographic Details
Main Authors: Barbara Frezza, Mario Cesare Nurchis, Gabriella Teresa Capolupo, Filippo Carannante, Marco De Prizio, Fabio Rondelli, Danilo Alunni Fegatelli, Alessio Gili, Luca Lepre, Gianluca Costa
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/5/544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257451907022848
author Barbara Frezza
Mario Cesare Nurchis
Gabriella Teresa Capolupo
Filippo Carannante
Marco De Prizio
Fabio Rondelli
Danilo Alunni Fegatelli
Alessio Gili
Luca Lepre
Gianluca Costa
author_facet Barbara Frezza
Mario Cesare Nurchis
Gabriella Teresa Capolupo
Filippo Carannante
Marco De Prizio
Fabio Rondelli
Danilo Alunni Fegatelli
Alessio Gili
Luca Lepre
Gianluca Costa
author_sort Barbara Frezza
collection DOAJ
description Frailty in the elderly population is associated with increased vulnerability to stressors, including surgical interventions. This study compared machine learning (ML) models with a clinical bedside tool, the Gastrointestinal Surgery Frailty Index (GiS-FI), for predicting mortality and morbidity in elderly patients undergoing gastrointestinal cancer surgery. In a multicenter analysis of 937 patients aged ≥65 years, the performance of various predictive models including Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), Stepwise Regression, K-Nearest Neighbors, Neural Network, and Support Vector Machine algorithms were evaluated. The overall 30-day mortality and morbidity rates were 6.1% and 35.7%, respectively. For mortality prediction, the RF model demonstrated superior performance with an AUC of 0.822 (95% CI 0.714–0.931), outperforming the GiS-FI score (AUC = 0.772, 95% CI 0.675–0.868). For morbidity prediction, all models showed more modest discrimination, with stepwise regression and LASSO regression achieving the highest performance (AUCs of 0.652 and 0.647, respectively). Our findings suggest that ML approaches, particularly RF algorithm, offer enhanced predictive accuracy compared to traditional clinical scores for mortality risk assessment in elderly cancer patients undergoing gastrointestinal surgery. These advanced analytical tools could provide valuable decision support for surgical risk stratification in this vulnerable population.
format Article
id doaj-art-9799077e057144eebd74dc773cc2f438
institution OA Journals
issn 2306-5354
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-9799077e057144eebd74dc773cc2f4382025-08-20T01:56:25ZengMDPI AGBioengineering2306-53542025-05-0112554410.3390/bioengineering12050544A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the ElderlyBarbara Frezza0Mario Cesare Nurchis1Gabriella Teresa Capolupo2Filippo Carannante3Marco De Prizio4Fabio Rondelli5Danilo Alunni Fegatelli6Alessio Gili7Luca Lepre8Gianluca Costa9General Surgery Unit, San Donato Hospital, Azienda USL Toscana Sud-Est, 52100 Arezzo, ItalyDepartment of Life Sciences, Health and Health Professions, Link Campus University, 00165 Roma, ItalyOperative Research Unit of Colorectal Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Roma, ItalyOperative Research Unit of Colorectal Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Roma, ItalyGeneral Surgery Unit, San Donato Hospital, Azienda USL Toscana Sud-Est, 52100 Arezzo, ItalyGeneral Surgery and Surgical Specialties Unit, Santa Maria Hospital Terni, Teaching Hospital of Perugia University, 05100 Perugia, ItalyDepartment of Life Sciences, Health and Health Professions, Link Campus University, 00165 Roma, ItalyDepartment of Life Sciences, Health and Health Professions, Link Campus University, 00165 Roma, ItalyGeneral and Emergency Surgery Unit, Santo Spirito in Sassia Hospital, ASL RM1, 00193 Roma, ItalyDepartment of Life Sciences, Health and Health Professions, Link Campus University, 00165 Roma, ItalyFrailty in the elderly population is associated with increased vulnerability to stressors, including surgical interventions. This study compared machine learning (ML) models with a clinical bedside tool, the Gastrointestinal Surgery Frailty Index (GiS-FI), for predicting mortality and morbidity in elderly patients undergoing gastrointestinal cancer surgery. In a multicenter analysis of 937 patients aged ≥65 years, the performance of various predictive models including Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), Stepwise Regression, K-Nearest Neighbors, Neural Network, and Support Vector Machine algorithms were evaluated. The overall 30-day mortality and morbidity rates were 6.1% and 35.7%, respectively. For mortality prediction, the RF model demonstrated superior performance with an AUC of 0.822 (95% CI 0.714–0.931), outperforming the GiS-FI score (AUC = 0.772, 95% CI 0.675–0.868). For morbidity prediction, all models showed more modest discrimination, with stepwise regression and LASSO regression achieving the highest performance (AUCs of 0.652 and 0.647, respectively). Our findings suggest that ML approaches, particularly RF algorithm, offer enhanced predictive accuracy compared to traditional clinical scores for mortality risk assessment in elderly cancer patients undergoing gastrointestinal surgery. These advanced analytical tools could provide valuable decision support for surgical risk stratification in this vulnerable population.https://www.mdpi.com/2306-5354/12/5/544cancersurgeryelderlyfrailtyscoremachine learning
spellingShingle Barbara Frezza
Mario Cesare Nurchis
Gabriella Teresa Capolupo
Filippo Carannante
Marco De Prizio
Fabio Rondelli
Danilo Alunni Fegatelli
Alessio Gili
Luca Lepre
Gianluca Costa
A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
Bioengineering
cancer
surgery
elderly
frailty
score
machine learning
title A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
title_full A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
title_fullStr A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
title_full_unstemmed A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
title_short A Comparison of Machine Learning-Based Models and a Simple Clinical Bedside Tool to Predict Morbidity and Mortality After Gastrointestinal Cancer Surgery in the Elderly
title_sort comparison of machine learning based models and a simple clinical bedside tool to predict morbidity and mortality after gastrointestinal cancer surgery in the elderly
topic cancer
surgery
elderly
frailty
score
machine learning
url https://www.mdpi.com/2306-5354/12/5/544
work_keys_str_mv AT barbarafrezza acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT mariocesarenurchis acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT gabriellateresacapolupo acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT filippocarannante acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT marcodeprizio acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT fabiorondelli acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT daniloalunnifegatelli acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT alessiogili acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT lucalepre acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT gianlucacosta acomparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT barbarafrezza comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT mariocesarenurchis comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT gabriellateresacapolupo comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT filippocarannante comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT marcodeprizio comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT fabiorondelli comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT daniloalunnifegatelli comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT alessiogili comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT lucalepre comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly
AT gianlucacosta comparisonofmachinelearningbasedmodelsandasimpleclinicalbedsidetooltopredictmorbidityandmortalityaftergastrointestinalcancersurgeryintheelderly