AUTHOR=Hennocq Quentin , Bongibault Thomas , Marlin Sandrine , Amiel Jeanne , Attie-Bitach Tania , Baujat Geneviève , Boutaud Lucile , Carpentier Georges , Corre Pierre , Denoyelle Françoise , Djate Delbrah François , Douillet Maxime , Galliani Eva , Kamolvisit Wuttichart , Lyonnet Stanislas , Milea Dan , Pingault Véronique , Porntaveetus Thantrira , Touzet-Roumazeille Sandrine , Willems Marjolaine , Picard Arnaud , Rio Marlène , Garcelon Nicolas , Khonsari Roman H. TITLE=AI-based diagnosis in mandibulofacial dysostosis with microcephaly using external ear shapes JOURNAL=Frontiers in Pediatrics VOLUME=11 YEAR=2023 URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2023.1171277 DOI=10.3389/fped.2023.1171277 ISSN=2296-2360 ABSTRACT=Introduction

Mandibulo-Facial Dysostosis with Microcephaly (MFDM) is a rare disease with a broad spectrum of symptoms, characterized by zygomatic and mandibular hypoplasia, microcephaly, and ear abnormalities. Here, we aimed at describing the external ear phenotype of MFDM patients, and train an Artificial Intelligence (AI)-based model to differentiate MFDM ears from non-syndromic control ears (binary classification), and from ears of the main differential diagnoses of this condition (multi-class classification): Treacher Collins (TC), Nager (NAFD) and CHARGE syndromes.

Methods

The training set contained 1,592 ear photographs, corresponding to 550 patients. We extracted 48 patients completely independent of the training set, with only one photograph per ear per patient. After a CNN-(Convolutional Neural Network) based ear detection, the images were automatically landmarked. Generalized Procrustes Analysis was then performed, along with a dimension reduction using PCA (Principal Component Analysis). The principal components were used as inputs in an eXtreme Gradient Boosting (XGBoost) model, optimized using a 5-fold cross-validation. Finally, the model was tested on an independent validation set.

Results

We trained the model on 1,592 ear photographs, corresponding to 1,296 control ears, 105 MFDM, 33 NAFD, 70 TC and 88 CHARGE syndrome ears. The model detected MFDM with an accuracy of 0.969 [0.838–0.999] (p < 0.001) and an AUC (Area Under the Curve) of 0.975 within controls (binary classification). Balanced accuracies were 0.811 [0.648–0.920] (p = 0.002) in a first multiclass design (MFDM vs. controls and differential diagnoses) and 0.813 [0.544–0.960] (p = 0.003) in a second multiclass design (MFDM vs. differential diagnoses).

Conclusion

This is the first AI-based syndrome detection model in dysmorphology based on the external ear, opening promising clinical applications both for local care and referral, and for expert centers.