Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes

Abstract

Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on a cohort of 49 individuals harbouring causative variants in known CdLS genes in order to evaluate Face2Gene utility and sensitivity in the clinical diagnosis of CdLS. Based on the profile images of patients, a diagnosis of CdLS was within the top five predicted syndromes for 97.9% of our cases and even listed as first prediction for 83.7%. The age of patients did not seem to affect the prediction accuracy, whereas our results indicate a correlation between the clinical score and affected genes. Furthermore, each gene presents a different pattern recognition that may be used to develop new neural networks with the goal of separating different genetic subtypes in CdLS. Overall, we conclude that computer-assisted image analysis based on deep learning could support the clinical diagnosis of CdLS.

ANKRD11 variants: KBG syndrome and beyond

“…Photographic material was submitted to Face2Gene for an additional clinical evaluation. This database includes an unprecedented amount of phenotypic and genotypic information associated with more than 10 000 diseases and has proven to be a valuable tool for the interpretation of facial features 36,43,44 . Face2Gene assigned a diagnosis of KBGS with high/medium similarity scores to 17 out of 21 individuals for whom photographs were available.…”

“…The remaining four individuals (Individuals 5, 15, 20, and 23) were not associated to any syndrome with a high probability. Previous studies have proven that the Facial Dysmorphology Novel Analysis technology could match the capabilities of expert clinicians and in some cases also outperform them 36,43,44 . Diagnosis‐aiding tools are particularly important for syndromes like KBGS, for which some of the typical and most recognizable clinical features (i.e., macrodontia, delayed bone age, and a bulbous nasal tip/broad nasal bridge) might appear only later in life.…”

Pitt-Hopkins Syndrome: Clinical and Molecular Findings of a 5-Year-Old Patient

“…Face2Gene uses deep-learning algorithms and it has been reported to be a useful technology for some rare diseases, mainly for pediatricians, general practitioners, but also for the young geneticist. The results may be interpreted with caution because more studies are needed to understand the genotype-phenotype correlations [13,14]. In the case of our patient, based on gestalt comparison, the score was high and suggested the possibility of a patient with PTHS ( Figure 3).…”

Craniofacial features of 3q29 deletion syndrome: application of next generation phenotyping technology

“…By following this tiered testing schema and recognizing the dysmorphic features of 3q29 deletion carriers, it may be possible for patients to obtain a molecular diagnosis in a timely manner and prior to the onset of some of the more severe neuropsychiatric phenotypes (Sanchez Russo et al, 2020). Since the phenotype may be too subtle and too variable for clinicians to easily recognize 3q29 deletion syndrome as may be the case for other syndromes with characteristic facial phenotypes such as Cornelia-de-Lange or Down syndrome, using next-generation phenotyping in primary care clinics may aid in the recognition of this rare disorder (Latorre-Pellicer et al, 2020).…”