GestaltMatcher facilitates rare disease matching using facial phenotype descriptors

GestaltMatcher uses a deep convolutional neural network to improve recognition of rare disorders based on facial morphology. The framework detects similarities among patients with previously unseen syndromes, aiding discovery of new disease genes. Many monogenic disorders cause a characteristic facial morphology. Artificial intelligence can support physicians in recognizing these patterns by associating facial phenotypes with the underlying syndrome through training on thousands of patient photographs. However, this 'supervised' approach means that diagnoses are only possible if the disorder was part of the training set. To improve recognition of ultra-rare disorders, we developed GestaltMatcher, an encoder for portraits that is based on a deep convolutional neural network. Photographs of 17,560 patients with 1,115 rare disorders were used to define a Clinical Face Phenotype Space, in which distances between cases define syndromic similarity. Here we show that patients can be matched to others with the same molecular diagnosis even when the disorder was not included in the training set. Together with mutation data, GestaltMatcher could not only accelerate the clinical diagnosis of patients with ultra-rare disorders and facial dysmorphism but also enable the delineation of new phenotypes.

Automated summary

GestaltMatcher utilizes deep convolutional neural network to improve recognition of rare disorders based on facial morphology, aiding in discovery of new disease genes by detecting similarities among patients with previously unseen syndromes. This approach assists physicians in recognizing characteristic facial morphology associated with monogenic disorders through training on thousands of patient photographs. By developing an encoder based on deep convolutional neural network, GestaltMatcher allows matching of patients even with ultra-rare disorders that were not part of the training set. Combined with mutation data, it can accelerate clinical diagnosis and enable delineation of new phenotypes.