Where portrait photos meet genetics and AI

Where portrait photos meet genetics and AI

Last Updated on June 13, 2019 by Joseph Gut – thasso

June 13, 2019 – This is simply fascinating stuff. Researchers are testing neural networks that automatically combine portrait photos with genetic and phenotypic patient data in order to obtain definitive diagnosis of hereditary rare diseases, all with the help of artificial intelligence (AI).  In a study published in the Journal of Genetics in Medicine of 679 patients with 105 rare diseases, a interdisciplinary team of scientists  has shown that AI can in fact diagnose rare diseases more efficiently and reliably.

Genetic portrait photos in the Journal of Design
Together with the international team of researchers, he has demonstrated how AI can be used to make comparatively quick and reliable diagnoses in facial analysis. The researchers used data of 679 patients with 105 different diseases caused by the change in a single gene. These include, for example, mucopolysaccharidosis (MPS), which leads to bone deformation, learning difficulties and stunted growth. Mabry syndrome (probably better known as Hyperphosphatasia with mental retardation syndrome (HPMRS) also results in intellectual disability. All these diseases have in common that the facial features of those affected show abnormalities. This is particularly characteristic of Kabuki syndrome (KMS), for example, in which facial features are reminiscent of the make-up of a traditional Japanese form of theatre. The eyebrows are arched, the eye-distance is wide and the spaces between the eyelids are long.

The used software can automatically detect these characteristic features from a photo. Together with the clinical symptoms of the patients and genetic data, it is possible to calculate with high accuracy which disease is most likely to be involved. The AI and digital health company FDNA  has developed the neural network DeepGestalt, which the researchers here used as a tool of artificial intelligence for their study. DeepGestalt ist also used in the Face2Gene suite of applications of the same company.

According to Mr. Gelbmann, the CEO of FDNA, is prioritization of exome data by image analysis (PEDIA), as performed in the present study, a unique example of next-generation phenotyping technologies. The integrating an advanced AI and facial analysis framework such as DeepGestalt into the variant analysis workflow will certainly result in a new paradigm for superior genetic testing.

The scientists trained this computer program with around 30,000 portrait pictures of people affected by rare syndromal diseases. “In combination with facial analysis, it is possible to filter out the decisive genetic factors and prioritize genes,” said Prof. Krawitz. “Merging data in the neuronal network reduces data analysis time and leads to a higher rate of diagnosis.” Prof. Kravitz has been working with FDNA for quite some time. “This is of great scientific interest to us and also enables us to find a cause in some unsolved cases,” said Prof. Krawitz. Many patients are currently still looking for an explanation for their symptoms.

The study was a extended team effort between computer science and medicine. This is illustrated through the shared first authorship of the computer scientist Tzung-Chien Hsieh, doctoral student at the institute of Professor Krawitz, and Dr. Martin Atta Mensah, physician at the Institute of Medical Genetics and Human Genetics of the Charité and Fellow of the Clinician Scientist Program of the Charité and Berlin Institute of Health (BIH). Prof. Mundlos, Director of the Institute of Medical Genetics and Human Genetics at the Charité, also participated in the study, as did over 90 other scientists.

“Patients want a prompt and accurate diagnosis. AI supports physicians and scientists in shortening the journey,” says Dr. Mundlos, Deputy Managing Director of Germanys alliance of patients with chronic rare diseases (ACHSE). “This also improves the quality of life of those affected to some extent.

Overall, this is a fascinating field in medicine, engaging everything from AI to genetics and overt human phenotypes to provide useful information for patients. One could easily imagine that therapy options as well as adverse events could easily be merged into these concepts of DeepGestalt to give rise in the future to something like “DeepHealing” in order to achieve the ultimate goal in medicine: Heal the patient. In any case, Thasso had already some previous posts in the context of using tools of facial recognition, AI and genetic big data within Face2Gene  (here) or to diagnose specific disorders such as a condition termed intellectual disability (ID) (here).

See here a sequence on a application of AI in portrait-based deep phenotyping:

Print Friendly, PDF & Email


Print Friendly, PDF & Email

Ph.D.; Professor in Pharmacology and Toxicology. Senior expert in theragenomic and personalized medicine and individualized drug safety. Senior expert in pharmaco- and toxicogenetics. Senior expert in human safety of drugs, chemicals, environmental pollutants, and dietary ingredients.

0 Comments on “Where portrait photos meet genetics and AI