Overcoming the limits of rare disease matching using facial phenotypic descriptors


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.

What is GestaltMatcher?

GestaltMatcher enables clinicians to match patients with facial similarity and thus, possibly diagnose patients with an ultra-rare disorder, or delineate a new syndrome in similar patients. This new algorithm is available as a web service and more details about the method can be found in our Nature Genetics paper. Furthermore, we provide code snippets and data for reproducing our results. The data portal GestaltMatcher DB can also be used to query for any medical images by gene or disorder.

See also Hellen Lesmann's talk about GestaltMatcher Database.

To sign up to GestaltMatcher DB, please send us an e-mail.