Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care
Abstract Facial palsy (FP) can lead to significant psychological and physical burdens such as facial synkinesis. This involuntary simultaneous movement of facial musculature remains challenging to diagnose and treat. This study aimed to develop a cost-effective, rapid, and accurate artificial intell...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-08548-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766147733323776 |
|---|---|
| author | Leonard Knoedler Christian Festbaum Jillian Dean Helena Baecher Grégoire de Lambertye Maximilian Maul Thomas Schaschinger Tobias Niederegger Alexandra Scheiflinger Michael Alfertshofer Khalil Sherwani Claudius Steffen Max Heiland Steffen Koerdt Samuel Knoedler Andreas Kehrer |
| author_facet | Leonard Knoedler Christian Festbaum Jillian Dean Helena Baecher Grégoire de Lambertye Maximilian Maul Thomas Schaschinger Tobias Niederegger Alexandra Scheiflinger Michael Alfertshofer Khalil Sherwani Claudius Steffen Max Heiland Steffen Koerdt Samuel Knoedler Andreas Kehrer |
| author_sort | Leonard Knoedler |
| collection | DOAJ |
| description | Abstract Facial palsy (FP) can lead to significant psychological and physical burdens such as facial synkinesis. This involuntary simultaneous movement of facial musculature remains challenging to diagnose and treat. This study aimed to develop a cost-effective, rapid, and accurate artificial intelligence (AI)-based algorithm to screen FP patients for facial synkinesis. Data from 70 FP patients were collected at the University Hospital Regensburg and compared to healthy controls from an online platform. The standardized patient image series included 9 images, of which 3 were used to train the algorithm. The control images were single images. A total of 385 images were used to train and evaluate a convolutional neural network (CNN). The dataset was divided into training (285 images), validation (29 images), and test sets (71 images). The model was trained over 18 epochs. A web application was developed for practical use. The model achieved an accuracy of 98.6% on the test set, correctly identifying 31 of 32 synkinesis cases and all 39 images of healthy individuals. Performance metrics included an F1-score of 98.4%, precision of 100%, and recall of 96.9%. The web application allowed for image upload and rapid synkinesis prediction. The CNN-based model demonstrated high accuracy in detecting synkinesis in FP patients, offering potential for improved diagnostic accuracy and expedited treatment. Further validation with larger datasets is necessary to ensure robustness and generalizability. |
| format | Article |
| id | doaj-art-e941e14e90984bfa953d577d9b85e322 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e941e14e90984bfa953d577d9b85e3222025-08-20T03:04:39ZengNature PortfolioScientific Reports2045-23222025-07-011511710.1038/s41598-025-08548-4Diagnosing facial synkinesis using artificial intelligence to advance facial palsy careLeonard Knoedler0Christian Festbaum1Jillian Dean2Helena Baecher3Grégoire de Lambertye4Maximilian Maul5Thomas Schaschinger6Tobias Niederegger7Alexandra Scheiflinger8Michael Alfertshofer9Khalil Sherwani10Claudius Steffen11Max Heiland12Steffen Koerdt13Samuel Knoedler14Andreas Kehrer15Department of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Plastic, Hand and Reconstructive Surgery, Hospital IngolstadtSchool of Medicine, University of PittsburghDepartment of Oral and Maxillofacial Surgery, University Hospital RegensburgDepartment of Informatics, Vienna Technical UniversityDepartment of Informatics, Vienna Technical UniversityDepartment of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Surgery, Beth Israel Deaconess Medical Center, Harvard Medical SchoolDepartment of Plastic, Hand and Reconstructive Surgery, University Hospital RegensburgMedical University of ViennaDepartment of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charité – Universitätsmedizin BerlinDepartment of Plastic, Hand and Reconstructive Surgery, University Hospital RegensburgDepartment of Plastic, Hand and Reconstructive Surgery, Hospital IngolstadtAbstract Facial palsy (FP) can lead to significant psychological and physical burdens such as facial synkinesis. This involuntary simultaneous movement of facial musculature remains challenging to diagnose and treat. This study aimed to develop a cost-effective, rapid, and accurate artificial intelligence (AI)-based algorithm to screen FP patients for facial synkinesis. Data from 70 FP patients were collected at the University Hospital Regensburg and compared to healthy controls from an online platform. The standardized patient image series included 9 images, of which 3 were used to train the algorithm. The control images were single images. A total of 385 images were used to train and evaluate a convolutional neural network (CNN). The dataset was divided into training (285 images), validation (29 images), and test sets (71 images). The model was trained over 18 epochs. A web application was developed for practical use. The model achieved an accuracy of 98.6% on the test set, correctly identifying 31 of 32 synkinesis cases and all 39 images of healthy individuals. Performance metrics included an F1-score of 98.4%, precision of 100%, and recall of 96.9%. The web application allowed for image upload and rapid synkinesis prediction. The CNN-based model demonstrated high accuracy in detecting synkinesis in FP patients, offering potential for improved diagnostic accuracy and expedited treatment. Further validation with larger datasets is necessary to ensure robustness and generalizability.https://doi.org/10.1038/s41598-025-08548-4SynkinesisArtificial intelligenceAIFacial palsyFacial paralysisConvolutional neural network |
| spellingShingle | Leonard Knoedler Christian Festbaum Jillian Dean Helena Baecher Grégoire de Lambertye Maximilian Maul Thomas Schaschinger Tobias Niederegger Alexandra Scheiflinger Michael Alfertshofer Khalil Sherwani Claudius Steffen Max Heiland Steffen Koerdt Samuel Knoedler Andreas Kehrer Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care Scientific Reports Synkinesis Artificial intelligence AI Facial palsy Facial paralysis Convolutional neural network |
| title | Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| title_full | Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| title_fullStr | Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| title_full_unstemmed | Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| title_short | Diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| title_sort | diagnosing facial synkinesis using artificial intelligence to advance facial palsy care |
| topic | Synkinesis Artificial intelligence AI Facial palsy Facial paralysis Convolutional neural network |
| url | https://doi.org/10.1038/s41598-025-08548-4 |
| work_keys_str_mv | AT leonardknoedler diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT christianfestbaum diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT jilliandean diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT helenabaecher diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT gregoiredelambertye diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT maximilianmaul diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT thomasschaschinger diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT tobiasniederegger diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT alexandrascheiflinger diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT michaelalfertshofer diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT khalilsherwani diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT claudiussteffen diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT maxheiland diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT steffenkoerdt diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT samuelknoedler diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare AT andreaskehrer diagnosingfacialsynkinesisusingartificialintelligencetoadvancefacialpalsycare |