Rare genetic diseases are usually hard to detect, and if they are, it could take years of diagnostic tests before physicians could come up with a definite diagnosis. Researchers from the University of Colorado, University of Calgary, and the University of California, San Francisco, have stepped up to address this problem. Combining 3D imaging and machine learning technology, the researchers created a prototype diagnostic tool to detect these rare conditions quickly.
Benedikt Hallgrímsson, Ph.D., a professor and head of the Department of Cell Biology & Anatomy, said that having a rare disease diagnosis for a child is life-changing. Also the scientific director at the Alberta Children's Hospital Research Institute in the Cumming School of Medicine at the University of Calgary, he shares that getting an accurate diagnosis is essential for getting access to the right treatments and allowing for connections with other children and families with the same situation.
Moreover, the majority of developmental genetic syndromes influence many organ systems, and clinical genetics have long depended on distinctive facial features as an essential basis for diagnosis.
In the analysis, the research team created a unique collection of 3D facial images of participants of diverse ages and ethnicities. The study included 3,327 children and adults with 396 different genetic syndromes. Furthermore, it also noted 727 of their unaffected relatives and 3,003 other unaffected individuals from the United States, Canada, and the United Kingdom.
The researchers used a protected database hosted by FaceBase, an international organization funded by the National Institute of Dental and Craniofacial Research, which is part of the U.S. National Institutes of Health (NIH).
Furthermore, the authors of the study used this secure database to instruct a machine-learning algorithm to recognize most of the genetic syndromes included in the dataset with moderate-to-high accuracy.
As a result, about 96 percent of the study subjects could be accurately classified as either unaffected or having a syndrome based on their facial features. Accordingly, the algorithm was able to provide a prioritized list of likely diagnoses with high accuracy. The paper was published online in the journal Genetics in Medicine on June 1, 2020.
Also Read: Viral Infection May Trigger Childhood Diabetes in Utero
Quick Result and Diagnosis Equals Immediate Treatment
According to Ophir Klein, MD, Ph.D., the Larry L. Hillblom Distinguished Professor in Craniofacial Anomalies, clinical genetics requires tremendous work. The Charles J. Epstein Professor of Human Genetics at UCSF and chief of the Division of Medical Genetics, adds that some clinics even have a two-year waiting list to get in.
Furthermore, Klein suggests that using 3D imaging could effectively enhance clinicians' capacity to diagnose children more expeditiously and inexpensively.
The authors emphasize that the current study embodies a shred of important evidence for facilitating genetic diagnoses. However, further endeavor is needed to release a clinically available and privacy-protected tool.
As of the present, the approach relies on costly 3D cameras. However, the researchers expected that this might change due to advances in smartphone camera technology.
Hope for All Types of People
The COVID-19 pandemic has sped up genetic clinics' rapid shift to telemedicine, including those at UCSF, University of Colorado, and the University of Calgary. Nevertheless, the study team says the field still lacks tools to take the place of many aspects of the face-to-face physical examination.
The automated diagnostic advancement developed in this study could enhance clinical geneticists' ability to diagnose patients without having them travel to a specialized clinic. Moreover, it could also help general practitioners without genetic training to focus on potential diagnoses. This would then allow them to connect patients with suitable specialty care and community support.
Richard Spritz, MD, a professor of Pediatrics and director of the Human Medical Genetics and Genomics Program at the University of Colorado School of Medicine hopes that one day soon, patients could resolutely take a photo of their face using a smartphone to be sent to their doctor for analysis in a confidential database.
In addition, low-income countries where genetic testing and medical geneticists are scarce could also benefit from this transformative new tool, Hallgrímsson said.
Read Also: More Kids at Higher Risk of Premature Heart Disease, Study Says
