By Ilana Jacqueline for Rare Revolution Magazine What if the signs and symptoms of a rare disease were as easy to identify as they are for the common cold?
With all the knowledge being generated by doctors, researchers, patients, and their dedicated advocacy groups—we are entering an era where this is possible. That is the mission behind the newly launched Genomics Collaborative—to accelerate the possibility of an early and accurate diagnosis by advancing of technologies through collaboration with patient and medical communities. The new program was launched by FDNA with multiple collaborators. FDNA is the developer of Face2Gene (www.Face2gene.com), a cloud-based application that uses next-generation phenotyping technologies—such as facial analysis—to help doctors as they evaluate patients. FDNA uses artificial intelligence to detect physiological patterns that reveal disease-causing genetic variations. The free tool is available to health care providers and is already being used in exam rooms in 130 countries. The Genomics Collaborative (www.GenomicsCollaborative.com) seeks to increase the knowledgebase that doctors have to understand these complex diseases. Collaborators are using FDNA’s artificial intelligence and deep learning technologies to develop new precision medicine approaches for diagnosing and treating disease, and improving patients’ quality of life. As a part of the announcement, FDNA is holding an open call for collaboration with patient advocacy groups, clinicians, labs and life sciences stakeholders. Many projects were announced during the 2018 World Rare Diseases Day, including projects with major medical institutions like Seattle Children’s Hospital in Washington, Greenwood Genetics Center in South Carolina, and Lausanne University Hospital in Switzerland. These collaborators are all working with FDNA to research technologies that can provide health insights through analysis of phenotypes—such as metabolites, brain abnormalities, and bone structure. Multiple patient advocacy groups have also announced projects, including All Things Kabuki, working to improve facial analysis and understanding of Kabuki syndrome, as well as Bridge the Gap, working on Fragile X, Angelman syndrome, Rett syndrome, and Phelan-McDermid syndrome. Projects in the Genomics Collaborative are focused on using computational techniques that integrate phenotypic data—such as facial or voice data—into the analysis of human health. This process, known as “next- generation phenotyping,” or NGP, captures, structures and interprets complex physiological information. This NGP-generated data can then be used to interpret patient genomic data to help recognize current and future health risks, as well as identify therapeutic targets that will maximize quality and length of life. To accomplish these goals, FDNA has offered collaborators access to its technologies which use deep learning neural networks to de-identify and analyze patients’ phenotypic information captured in images, clinical notes, and voice and video recordings to discover correlations between patient data and disease. Collaborators will be able to set up secure online patient portals where researchers can ask targeted patient populations to share phenotypic and genomic data—including facial photos and other biometrics that will be de-identified and analyzed. Collaborators will have the opportunity to create specific studies and securely capture and analyze patient health data. FDNA will work with collaborators to design specific studies and securely capture and analyze patient health data that relates to the proposed research hypotheses. Data will be collected using secure portals and patient questionnaires, when applicable. Collaborators can gather and analyze a variety of data relating to the patient’s symptoms, signs, lifestyle, medical history, and genetic data. Interested advocacy groups, clinicians, patients and researchers can visit www.genomicscollaborative.com for more information.
0 Comments
Your comment will be posted after it is approved.
Leave a Reply. |
AuthorRare Revolution Editor Categories |