BACKGROUND: While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism.
OBJECTIVE: We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt.
METHODS: Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity.
RESULTS: DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88%, SD 18%) than for GestaltMatcher (76%, SD 26%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score\'s levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores.
CONCLUSIONS: If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face.

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.
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.
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.
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).
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.

UNASSIGNED: Noonan syndrome (NS) is a genetic disorder that is associated with social cognitive problems. While treatment aimed at the improvement of social cognition is available for other neuropsychiatric disorders, no such interventions yet exist for NS patients. In this study, the development of the first social cognitive training for NS patients is described and its applicability and feasibility evaluated.
UNASSIGNED: Eleven adult patients with NS participated in this controlled proof-of-principle study. Six patients were included in the treatment group and five in the control group. Neuropsychological testing was performed in both groups at baseline and posttreatment. Social cognition was a primary outcome measure and nonsocial cognition and psychopathology secondary outcome measures. Differences between pre- and posttest were investigated with Wilcoxon signed-rank tests, and a process evaluation was performed to aid interpretation of the results.
UNASSIGNED: Both groups were comparable with regard to age, estimated intelligence, and baseline performance. Although no significant differences were found between pre- and posttest scores on primary and secondary outcome measures in either group, a medium-large effect size was found on emotion recognition in the treatment group. Also, the process evaluation demonstrated the feasibility of the training.
UNASSIGNED: This first social cognitive training for adult patients with NS has proven to be feasible for this population and showed some encouraging results regarding emotion recognition, although the training protocol could be optimized. Further investigation is required using a randomized controlled design in a larger sample, in order to substantiate the overall effectiveness of the training.

The antenatal detection of facial dysmorphism using 3-dimensional ultrasound may raise the suspicion of an underlying genetic condition but infrequently leads to a definitive antenatal diagnosis. Despite advances in array and noninvasive prenatal testing, not all genetic conditions can be ascertained from such testing.
The aim of this study was to investigate the feasibility of quantitative assessment of fetal face features using prenatal 3-dimensional ultrasound volumes and statistical shape modeling. STUDY DESIGN: Thirteen normal and 7 abnormal stored 3-dimensional ultrasound fetal face volumes were analyzed, at a median gestation of 29+4 weeks (25+0 to 36+1). The 20 3-dimensional surface meshes generated were aligned and served as input for a statistical shape model, which computed the mean 3-dimensional face shape and 3-dimensional shape variations using principal component analysis.
Ten shape modes explained more than 90% of the total shape variability in the population. While the first mode accounted for overall size differences, the second highlighted shape feature changes from an overall proportionate toward a more asymmetric face shape with a wide prominent forehead and an undersized, posteriorly positioned chin. Analysis of the Mahalanobis distance in principal component analysis shape space suggested differences between normal and abnormal fetuses (median and interquartile range distance values, 7.31 ± 5.54 for the normal group vs 13.27 ± 9.82 for the abnormal group) (P = .056).
This feasibility study demonstrates that objective characterization and quantification of fetal facial morphology is possible from 3-dimensional ultrasound. This technique has the potential to assist in utero diagnosis, particularly of rare conditions in which facial dysmorphology is a feature.