Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study

Abstract

Background Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls. Objective The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images. Methods Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists. Results We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; P<.001). Conclusions DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.

A survey of U.S. public perspectives on facial recognition technology and facial imaging data practices in health and research contexts

“…The emergence of new facial recognition technologies (FRT) intensifies the availability of and interest in facial imaging for precision health research purposes. Several healthcare applications of FRT have been identified, including assisting in the diagnosis of certain medical conditions (such as melanoma and certain craniofacial anomalies), detecting pain and pain relief, and accurately matching patients to their medical records [ 16 – 17 , 31 , 32 ]. Other applications focus more squarely on FRT’s uses for identification and authentication, including securing access to physical spaces or computer workstations, enabling touch-free appointment check-in for patients, and even detecting or deterring healthcare fraud [ 33 – 35 ].…”

Genetic syndromes screening by facial recognition technology: VGG-16 screening model construction and evaluation

“…Hence, developing a facial recognition model for screening GSs is necessary. In 2020, Pantel et al [ 15 ] analysed a total of 646 images of 323 patients with 17 different genetic syndromes and matched individuals without a genetic syndrome. A face recognition model, which is driven by support vector machine running on the top of DeepGestalt framework, was introduced in this study.…”

Multi-Scale Part-Based Syndrome Classification of 3D Facial Images

“…Further, it can be difficult for a clinician to keep pace with the everexpanding catalog of clinical and molecular diagnoses and their associated phenotypes. Therefore, objective facial phenotyping for syndrome identification is needed to assist in clinical diagnosis [1]- [5]. Previous work has mostly focused on 2D facial images [6], with large-scale deep convolutional neural networks being developed for and implemented in the clinic [1].…”