Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches

BackgroundThird molar extraction, a common dental procedure, often involves complications, such as alveolar nerve injury. Accurate preoperative assessment of the extraction difficulty and nerve injury risk is crucial for better surgical planning and patient outcomes. Recent advancements in deep lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamza Al Salieti, Hanan M. Qasem, Sakhr Alshwayyat, Noor Almasri, Mustafa Alshwayyat, Amira A. Aboali, Farah Alsarayrah, Lina Khasawneh, Mohammed Al-mahdi Al-kurdi
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Dental Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdmed.2025.1534406/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735768502697984
author Hamza Al Salieti
Hanan M. Qasem
Sakhr Alshwayyat
Sakhr Alshwayyat
Sakhr Alshwayyat
Noor Almasri
Mustafa Alshwayyat
Amira A. Aboali
Farah Alsarayrah
Lina Khasawneh
Mohammed Al-mahdi Al-kurdi
author_facet Hamza Al Salieti
Hanan M. Qasem
Sakhr Alshwayyat
Sakhr Alshwayyat
Sakhr Alshwayyat
Noor Almasri
Mustafa Alshwayyat
Amira A. Aboali
Farah Alsarayrah
Lina Khasawneh
Mohammed Al-mahdi Al-kurdi
author_sort Hamza Al Salieti
collection DOAJ
description BackgroundThird molar extraction, a common dental procedure, often involves complications, such as alveolar nerve injury. Accurate preoperative assessment of the extraction difficulty and nerve injury risk is crucial for better surgical planning and patient outcomes. Recent advancements in deep learning (DL) have shown the potential to enhance the predictive accuracy using panoramic radiographic (PR) images. This systematic review evaluated the accuracy and reliability of DL models for predicting third molar extraction difficulty and inferior alveolar nerve (IAN) injury risk.MethodsA systematic search was conducted across PubMed, Scopus, Web of Science, and Embase until September 2024, focusing on studies assessing DL models for predicting extraction complexity and IAN injury using PR images. The inclusion criteria required studies to report predictive performance metrics. Study selection, data extraction, and quality assessment were independently performed by two authors using the PRISMA and QUADAS-2 guidelines.ResultsSix studies involving 12,419 PR images met the inclusion criteria. DL models demonstrated high accuracy in predicting extraction difficulty (up to 96%) and IAN injury (up to 92.9%), with notable sensitivity (up to 97.5%) for specific classifications, such as horizontal impactions. Geographically, three studies originated in South Korea and one each from Turkey and Thailand, limiting generalizability. Despite high accuracy, demographic data were sparsely reported, with only two studies providing patient sex distribution.ConclusionDL models show promise in improving the preoperative assessment of third molar extraction. However, further validation in diverse populations and integration with clinical workflows are necessary to establish its real-world utility, as limitations such as limited generalizability, potential selection bias and lack of long-term follow up remain challenges.
format Article
id doaj-art-ca81d86a689f4a28a8b2a06f00936433
institution DOAJ
issn 2673-4915
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Dental Medicine
spelling doaj-art-ca81d86a689f4a28a8b2a06f009364332025-08-20T03:07:27ZengFrontiers Media S.A.Frontiers in Dental Medicine2673-49152025-05-01610.3389/fdmed.2025.15344061534406Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approachesHamza Al Salieti0Hanan M. Qasem1Sakhr Alshwayyat2Sakhr Alshwayyat3Sakhr Alshwayyat4Noor Almasri5Mustafa Alshwayyat6Amira A. Aboali7Farah Alsarayrah8Lina Khasawneh9Mohammed Al-mahdi Al-kurdi10Faculty of Dentistry, Applied Science Private University, Amman, JordanFaculty of Dentistry, Jordan University of Science and Technology, Irbid, JordanResearch Associate, King Hussein Cancer Center, Amman, JordanInternship, Princess Basma Teaching Hospital, Irbid, JordanApplied Science Research Center, Applied Science Private University, Amman, JordanFaculty of Medicine, University of Jordan, Amman, JordanFaculty of Medicine, Jordan University of Science and Technology, Irbid, JordanDamanhour Teaching Hospital, General Organization for Teaching Hospitals and Institutes, Damanhour, EgyptFaculty of Dentistry, Jordan University of Science and Technology, Irbid, JordanDepartment of Prosthodontics, Faculty of Dentistry, Jordan University of Science and Technology, Irbid, Jordan0Faculty of Medicine, University of Aleppo, Aleppo, Syrian Arab RepublicBackgroundThird molar extraction, a common dental procedure, often involves complications, such as alveolar nerve injury. Accurate preoperative assessment of the extraction difficulty and nerve injury risk is crucial for better surgical planning and patient outcomes. Recent advancements in deep learning (DL) have shown the potential to enhance the predictive accuracy using panoramic radiographic (PR) images. This systematic review evaluated the accuracy and reliability of DL models for predicting third molar extraction difficulty and inferior alveolar nerve (IAN) injury risk.MethodsA systematic search was conducted across PubMed, Scopus, Web of Science, and Embase until September 2024, focusing on studies assessing DL models for predicting extraction complexity and IAN injury using PR images. The inclusion criteria required studies to report predictive performance metrics. Study selection, data extraction, and quality assessment were independently performed by two authors using the PRISMA and QUADAS-2 guidelines.ResultsSix studies involving 12,419 PR images met the inclusion criteria. DL models demonstrated high accuracy in predicting extraction difficulty (up to 96%) and IAN injury (up to 92.9%), with notable sensitivity (up to 97.5%) for specific classifications, such as horizontal impactions. Geographically, three studies originated in South Korea and one each from Turkey and Thailand, limiting generalizability. Despite high accuracy, demographic data were sparsely reported, with only two studies providing patient sex distribution.ConclusionDL models show promise in improving the preoperative assessment of third molar extraction. However, further validation in diverse populations and integration with clinical workflows are necessary to establish its real-world utility, as limitations such as limited generalizability, potential selection bias and lack of long-term follow up remain challenges.https://www.frontiersin.org/articles/10.3389/fdmed.2025.1534406/fullalveolar nervedeep learningmandibular nervepanoramic radiographicthird molar
spellingShingle Hamza Al Salieti
Hanan M. Qasem
Sakhr Alshwayyat
Sakhr Alshwayyat
Sakhr Alshwayyat
Noor Almasri
Mustafa Alshwayyat
Amira A. Aboali
Farah Alsarayrah
Lina Khasawneh
Mohammed Al-mahdi Al-kurdi
Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
Frontiers in Dental Medicine
alveolar nerve
deep learning
mandibular nerve
panoramic radiographic
third molar
title Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
title_full Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
title_fullStr Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
title_full_unstemmed Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
title_short Predicting alveolar nerve injury and the difficulty level of extraction impacted third molars: a systematic review of deep learning approaches
title_sort predicting alveolar nerve injury and the difficulty level of extraction impacted third molars a systematic review of deep learning approaches
topic alveolar nerve
deep learning
mandibular nerve
panoramic radiographic
third molar
url https://www.frontiersin.org/articles/10.3389/fdmed.2025.1534406/full
work_keys_str_mv AT hamzaalsalieti predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT hananmqasem predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT sakhralshwayyat predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT sakhralshwayyat predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT sakhralshwayyat predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT nooralmasri predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT mustafaalshwayyat predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT amiraaaboali predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT farahalsarayrah predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT linakhasawneh predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches
AT mohammedalmahdialkurdi predictingalveolarnerveinjuryandthedifficultylevelofextractionimpactedthirdmolarsasystematicreviewofdeeplearningapproaches