Cargando…

Development and external validation of clinical prediction models for pituitary surgery

INTRODUCTION: Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available dat...

Descripción completa

Detalles Bibliográficos
Autores principales: Zanier, Olivier, Zoli, Matteo, Staartjes, Victor E., Alalfi, Mohammed O., Guaraldi, Federica, Asioli, Sofia, Rustici, Arianna, Pasquini, Ernesto, Faustini-Fustini, Marco, Erlic, Zoran, Hugelshofer, Michael, Voglis, Stefanos, Regli, Luca, Mazzatenta, Diego, Serra, Carlo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10668061/
https://www.ncbi.nlm.nih.gov/pubmed/38020983
http://dx.doi.org/10.1016/j.bas.2023.102668
_version_ 1785139389637066752
author Zanier, Olivier
Zoli, Matteo
Staartjes, Victor E.
Alalfi, Mohammed O.
Guaraldi, Federica
Asioli, Sofia
Rustici, Arianna
Pasquini, Ernesto
Faustini-Fustini, Marco
Erlic, Zoran
Hugelshofer, Michael
Voglis, Stefanos
Regli, Luca
Mazzatenta, Diego
Serra, Carlo
author_facet Zanier, Olivier
Zoli, Matteo
Staartjes, Victor E.
Alalfi, Mohammed O.
Guaraldi, Federica
Asioli, Sofia
Rustici, Arianna
Pasquini, Ernesto
Faustini-Fustini, Marco
Erlic, Zoran
Hugelshofer, Michael
Voglis, Stefanos
Regli, Luca
Mazzatenta, Diego
Serra, Carlo
author_sort Zanier, Olivier
collection PubMed
description INTRODUCTION: Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available data might help improve patient care and contribute to a more personalized medicine. RESEARCH QUESTION: This study aims to develop machine learning models predicting GTR, BR, and IMP in PA resection surgery, using preoperatively available data. MATERIAL AND METHODS: With data from patients undergoing endoscopic transsphenoidal surgery for PAs machine learning models for prediction of GTR, BR and IMP were developed and externally validated. Development was carried out on a registry from Bologna, Italy while external validation was conducted using patient data from Zurich, Switzerland. RESULTS: The model development cohort consisted of 1203 patients. GTR was achieved in 207 (17.2%, 945 (78.6%) missing), BR in 173 (14.4%, 992 (82.5%) missing) and IMP in 208 (17.3%, 167 (13.9%) missing) cases. In the external validation cohort 206 patients were included and GTR was achieved in 121 (58.7%, 32 (15.5%) missing), BR in 46 (22.3%, 145 (70.4%) missing) and IMP in 42 (20.4%, 7 (3.4%) missing) cases. The AUC at external validation amounted to 0.72 (95% CI: 0.63–0.80) for GTR, 0.69 (0.52–0.83) for BR, as well as 0.82 (0.76–0.89) for IMP. DISCUSSION AND CONCLUSION: All models showed adequate generalizability, performing similarly in training and external validation, confirming the possible potentials of machine learning in helping to adapt surgical therapy to the individual patient.
format Online
Article
Text
id pubmed-10668061
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-106680612023-08-28 Development and external validation of clinical prediction models for pituitary surgery Zanier, Olivier Zoli, Matteo Staartjes, Victor E. Alalfi, Mohammed O. Guaraldi, Federica Asioli, Sofia Rustici, Arianna Pasquini, Ernesto Faustini-Fustini, Marco Erlic, Zoran Hugelshofer, Michael Voglis, Stefanos Regli, Luca Mazzatenta, Diego Serra, Carlo Brain Spine Article INTRODUCTION: Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available data might help improve patient care and contribute to a more personalized medicine. RESEARCH QUESTION: This study aims to develop machine learning models predicting GTR, BR, and IMP in PA resection surgery, using preoperatively available data. MATERIAL AND METHODS: With data from patients undergoing endoscopic transsphenoidal surgery for PAs machine learning models for prediction of GTR, BR and IMP were developed and externally validated. Development was carried out on a registry from Bologna, Italy while external validation was conducted using patient data from Zurich, Switzerland. RESULTS: The model development cohort consisted of 1203 patients. GTR was achieved in 207 (17.2%, 945 (78.6%) missing), BR in 173 (14.4%, 992 (82.5%) missing) and IMP in 208 (17.3%, 167 (13.9%) missing) cases. In the external validation cohort 206 patients were included and GTR was achieved in 121 (58.7%, 32 (15.5%) missing), BR in 46 (22.3%, 145 (70.4%) missing) and IMP in 42 (20.4%, 7 (3.4%) missing) cases. The AUC at external validation amounted to 0.72 (95% CI: 0.63–0.80) for GTR, 0.69 (0.52–0.83) for BR, as well as 0.82 (0.76–0.89) for IMP. DISCUSSION AND CONCLUSION: All models showed adequate generalizability, performing similarly in training and external validation, confirming the possible potentials of machine learning in helping to adapt surgical therapy to the individual patient. Elsevier 2023-08-28 /pmc/articles/PMC10668061/ /pubmed/38020983 http://dx.doi.org/10.1016/j.bas.2023.102668 Text en © 2023 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zanier, Olivier
Zoli, Matteo
Staartjes, Victor E.
Alalfi, Mohammed O.
Guaraldi, Federica
Asioli, Sofia
Rustici, Arianna
Pasquini, Ernesto
Faustini-Fustini, Marco
Erlic, Zoran
Hugelshofer, Michael
Voglis, Stefanos
Regli, Luca
Mazzatenta, Diego
Serra, Carlo
Development and external validation of clinical prediction models for pituitary surgery
title Development and external validation of clinical prediction models for pituitary surgery
title_full Development and external validation of clinical prediction models for pituitary surgery
title_fullStr Development and external validation of clinical prediction models for pituitary surgery
title_full_unstemmed Development and external validation of clinical prediction models for pituitary surgery
title_short Development and external validation of clinical prediction models for pituitary surgery
title_sort development and external validation of clinical prediction models for pituitary surgery
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10668061/
https://www.ncbi.nlm.nih.gov/pubmed/38020983
http://dx.doi.org/10.1016/j.bas.2023.102668
work_keys_str_mv AT zanierolivier developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT zolimatteo developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT staartjesvictore developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT alalfimohammedo developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT guaraldifederica developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT asiolisofia developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT rusticiarianna developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT pasquiniernesto developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT faustinifustinimarco developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT erliczoran developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT hugelshofermichael developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT voglisstefanos developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT regliluca developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT mazzatentadiego developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery
AT serracarlo developmentandexternalvalidationofclinicalpredictionmodelsforpituitarysurgery