Can your face reveal a disease to a doctor?
This artificial intelligence app uses a facial recognition algorithm to help diagnose rare genetic diseases.
Facial recognition technology is all around us these days – from notifications on Facebook asking us if we want to tag recognized friends, to helping you choose a new dog and even to catch shoplifters.
It’s also possible to diagnose many diseases by analyzing a patient’s facial features – a process known as dysmorphology. Now FDNA – a startup founded in Israel and now based in Boston – is using dysmorphology to help doctors diagnose rare genetic diseases simply by uploading a patient’s photo to their phone.
Face2Gene’s smartphone app, powered by the company’s patented Facial Dysmorphology Novel Analysis solution, returns a list of possible diagnoses based on a patient’s picture uploaded by a doctor. A user can also add other general and clinical information and indicate features that should be included or excluded to further narrow results.
According to the U.S. National Institutes of Health Office of Rare Disease Research, there are about 7,000 rare diseases that range from the more recognizable cerebral palsy to obscure, hard-to-pronounce diseases like choroideremia hypopituitarism – an eye disease that involves a malfunctioning pituitary gland. Around 1 in 10 Americans suffer from a rare disease – that’s around 30 million people – about half of whom are children.
Diagnosing a rare disease is incredibly difficult simply because there are so many, and in the case of ultra-rare diseases there may be very few specialists familiar with the disease. Traditionally, the process was long and arduous of linking symptoms and ruling out diagnoses. Patients visited on average about seven physicians over a period of years in order to find out what was wrong with them so that they could finally receive treatment.
“Patients and their families suffer a great burden while trying to find answers to their symptoms, averaging seven years and seven doctors,” said FDNA CEO Dekel Gelbman, a graduate of Tel Aviv University in Israel.
The platform uses data crowdsourced from geneticists and cross-references that data with information from the London Medical Databases, which maintains a collection of images based on dysmorphology. According to Gelbman, some 60% of clinical geneticists and genetic counselors around the world have used the technology, and experienced researchers have found Face2Gene useful.
“You only recognize what you know. Face2Gene gets me to go down the list and say, ‘Hmm, did I consider everything?’” said Dr. Karen W. Gripp, chief of the Division of Medical Genetics at A.I. DuPont Hospital for Children in Wilmington, Del. Gripp added that the Face2Gene platform provides relevant, accurate data that is now an essential part of the diagnostic process.
The app is free, and available only to verified clinicians and doctors. It is also HIPPA compliant, which means it conforms to the highest level of personal privacy safeguards regarding health information.
“FDNA helps healthcare providers find answers faster in hopes of saving lives and improving patient quality of life,” Gelbman said. “We accomplish this through using the best technology in the world – based on a combination of facial analysis, deep learning, and artificial intelligence and partnering with clinicians, researchers, labs and ultimately with drug development companies that share our goal.”
The company is also working to integrate facial analysis with phenotyping, which is the process of describing a patient on a clinical level, to better pinpoint rare and ultra-rare genetic diseases.
“Phenotyping and facial analysis technologies are now being used to make progress in the genetics community to connect these dots, ultimately changing the lives of patients and the ways clinicians diagnose them. Marrying this data in a meaningful way will make significant strides in reducing the timeline of the diagnostic odyssey, giving families the crucial answers they need,” said Gelbman.
MORE FROM THE GRAPEVINE:
Related Topics: Science