Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach
Abstract Introduction Machine learning (ML)‐based facial nerve injury (FNI) forecasting grounded on multicentric data has not been released up to now. Three distinct ML models, random forest (RF), K‐nearest neighbor, and artificial neural network (ANN), for the prediction of FNI were evaluated in th...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-12-01
|
Series: | World Journal of Otorhinolaryngology-Head and Neck Surgery |
Subjects: | |
Online Access: | https://doi.org/10.1002/wjo2.94 |
_version_ | 1797404531428950016 |
---|---|
author | Carlos M. Chiesa‐Estomba Jose A. González‐García Ekhiñe Larruscain Jon A. Sistiaga Suarez Miquel Quer Xavier León Paula Martínez‐Ruiz de Apodaca Celia López‐Mollá Miguel Mayo‐Yanez Alfonso Medela |
author_facet | Carlos M. Chiesa‐Estomba Jose A. González‐García Ekhiñe Larruscain Jon A. Sistiaga Suarez Miquel Quer Xavier León Paula Martínez‐Ruiz de Apodaca Celia López‐Mollá Miguel Mayo‐Yanez Alfonso Medela |
author_sort | Carlos M. Chiesa‐Estomba |
collection | DOAJ |
description | Abstract Introduction Machine learning (ML)‐based facial nerve injury (FNI) forecasting grounded on multicentric data has not been released up to now. Three distinct ML models, random forest (RF), K‐nearest neighbor, and artificial neural network (ANN), for the prediction of FNI were evaluated in this mode. Methods A retrospective, longitudinal, multicentric study was performed, including patients who went through parotid gland surgery for benign tumors at three different university hospitals. Results Seven hundred and thirty‐six patients were included. The most compelling aspects related to risk escalation of FNI were as follows: (1) location, in the mid‐portion of the gland, near to or above the main trunk of the facial nerve and at the top part, over the frontal or the orbital branch of the facial nerve; (2) tumor volume in the anteroposterior axis; (3) the necessity to simultaneously dissect more than one level; and (4) the requirement of an extended resection compared to a lesser extended resection. By contrast, in accordance with the ML analysis, the size of the tumor (>3 cm), as well as gender and age did not result in a determining favor in relation to the risk of FNI. Discussion The findings of this research conclude that ML models such as RF and ANN may serve evidence‐based predictions from multicentric data regarding the risk of FNI. Conclusion Along with the advent of ML technology, an improvement of the information regarding the potential risks of FNI associated with patients before each procedure may be achieved with the implementation of clinical, radiological, histological, and/or cytological data. |
first_indexed | 2024-03-09T02:56:21Z |
format | Article |
id | doaj.art-b0f26b31d85d42599e1189f377af5d53 |
institution | Directory Open Access Journal |
issn | 2095-8811 2589-1081 |
language | English |
last_indexed | 2024-03-09T02:56:21Z |
publishDate | 2023-12-01 |
publisher | Wiley |
record_format | Article |
series | World Journal of Otorhinolaryngology-Head and Neck Surgery |
spelling | doaj.art-b0f26b31d85d42599e1189f377af5d532023-12-05T06:26:41ZengWileyWorld Journal of Otorhinolaryngology-Head and Neck Surgery2095-88112589-10812023-12-019427127910.1002/wjo2.94Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approachCarlos M. Chiesa‐Estomba0Jose A. González‐García1Ekhiñe Larruscain2Jon A. Sistiaga Suarez3Miquel Quer4Xavier León5Paula Martínez‐Ruiz de Apodaca6Celia López‐Mollá7Miguel Mayo‐Yanez8Alfonso Medela9Department of Otorhinolaryngology—Head and Neck Surgery Donostia University Hospital Donosti‐San Sebastián SpainDepartment of Otorhinolaryngology—Head and Neck Surgery Donostia University Hospital Donosti‐San Sebastián SpainDepartment of Otorhinolaryngology—Head and Neck Surgery Donostia University Hospital Donosti‐San Sebastián SpainDepartment of Otorhinolaryngology—Head and Neck Surgery Donostia University Hospital Donosti‐San Sebastián SpainDepartment of Otorhinolaryngology, Hospital Santa Creu I Sant Pau Universitat Autònoma de Barcelona Barcelona SpainDepartment of Otorhinolaryngology, Hospital Santa Creu I Sant Pau Universitat Autònoma de Barcelona Barcelona SpainHead & Neck Study Group of Young‐Otolaryngologists of the International Federations of Oto‐rhino‐laryngological Societies (YO‐IFOS) Paris FranceDepartment of Otorhinolaryngology Doctor Peset University Hospital Valencia SpainHead & Neck Study Group of Young‐Otolaryngologists of the International Federations of Oto‐rhino‐laryngological Societies (YO‐IFOS) Paris FranceLEGIT Health Bilbao SpainAbstract Introduction Machine learning (ML)‐based facial nerve injury (FNI) forecasting grounded on multicentric data has not been released up to now. Three distinct ML models, random forest (RF), K‐nearest neighbor, and artificial neural network (ANN), for the prediction of FNI were evaluated in this mode. Methods A retrospective, longitudinal, multicentric study was performed, including patients who went through parotid gland surgery for benign tumors at three different university hospitals. Results Seven hundred and thirty‐six patients were included. The most compelling aspects related to risk escalation of FNI were as follows: (1) location, in the mid‐portion of the gland, near to or above the main trunk of the facial nerve and at the top part, over the frontal or the orbital branch of the facial nerve; (2) tumor volume in the anteroposterior axis; (3) the necessity to simultaneously dissect more than one level; and (4) the requirement of an extended resection compared to a lesser extended resection. By contrast, in accordance with the ML analysis, the size of the tumor (>3 cm), as well as gender and age did not result in a determining favor in relation to the risk of FNI. Discussion The findings of this research conclude that ML models such as RF and ANN may serve evidence‐based predictions from multicentric data regarding the risk of FNI. Conclusion Along with the advent of ML technology, an improvement of the information regarding the potential risks of FNI associated with patients before each procedure may be achieved with the implementation of clinical, radiological, histological, and/or cytological data.https://doi.org/10.1002/wjo2.94glandmachine learningparotidpersonalized medicinesurgery |
spellingShingle | Carlos M. Chiesa‐Estomba Jose A. González‐García Ekhiñe Larruscain Jon A. Sistiaga Suarez Miquel Quer Xavier León Paula Martínez‐Ruiz de Apodaca Celia López‐Mollá Miguel Mayo‐Yanez Alfonso Medela Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach World Journal of Otorhinolaryngology-Head and Neck Surgery gland machine learning parotid personalized medicine surgery |
title | Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach |
title_full | Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach |
title_fullStr | Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach |
title_full_unstemmed | Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach |
title_short | Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach |
title_sort | facial nerve palsy following parotid gland surgery a machine learning prediction outcome approach |
topic | gland machine learning parotid personalized medicine surgery |
url | https://doi.org/10.1002/wjo2.94 |
work_keys_str_mv | AT carlosmchiesaestomba facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT joseagonzalezgarcia facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT ekhinelarruscain facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT jonasistiagasuarez facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT miquelquer facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT xavierleon facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT paulamartinezruizdeapodaca facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT celialopezmolla facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT miguelmayoyanez facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach AT alfonsomedela facialnervepalsyfollowingparotidglandsurgeryamachinelearningpredictionoutcomeapproach |