At the European Society of Human Genetics annual meeting in Copenhagen this week, several groups presented studies involving automated facial analysis software.
FDNA's Face2Gene suite analyzes phenotypic data, including facial features, from rare disease patients.
The firm's first assay will be for Hodgkin lymphoma, but a liquid biopsy test for prostate cancer has also shown strong predictive power in initial validation data.
The new institute plans to use structured clinical information to inform targeted testing in order to cut down the time to diagnosis.
Following validation, the approach, which uses a deep convolutional neural network trained with almost 130,000 clinical images, could be developed into a smartphone app to detect skin cancer early.
In a recent study, researchers led by the NHGRI showed that the software could accurately diagnose Down syndrome in patients of different ethnic background.
Researchers at Tufts and their collaborators recently demonstrated that the approach, which uses multiphoton microscopy, can distinguish between normal and cancerous skin.