AI and Advanced Technology Revolutionize Diagnosis of Rare Diseases and Genetic Conditions

Advanced technology and AI used to diagnose rare diseases and birth abnormalities

Lawson Health Research InstituteJul 31 2024 Researchers at London Health Sciences Centre (LHSC) and Lawson Health Research Institute are using advanced technology and artificial intelligence (AI) to diagnose rare diseases and prenatal exposure-related birth abnormalities in two studies published today in American Journal of Human Genetics and Genetics in Medicine. The research uses technology called EpiSign™, which was developed by Dr. Bekim Sadikovic, Lawson Scientist at LHSC. EpiSign leverages AI to measure a patient's epigenome - a unique chemical fingerprint that every person has on top of their DNA that is responsible for turning genes on or off. EpiSign can currently be used to help diagnose more than 100 genetic diseases that were previously difficult to diagnose. In one of two newly published studies, Dr. Sadikovic's team has found that EpiSign can be used to accurately identify patients affected by birth disorders called recurrent constellation of embryonic malformations (RCEMs). Since their discovery more than 70 years ago, attempts to identify the cause and specific diagnostic markers for RCEMs have been unsuccessful, making it challenging to provide patients and families with accurate diagnoses. EpiSign can now be used to accurately identify RCEMs for the first time using a blood test. "Reaching an early and accurate diagnosis can be lifechanging. This is a major breakthrough that allows physicians to provide earlier and more accurate diagnosis, resulting in improved disease management," said Dr. Sadikovic, who is also Research Chair in Clinical Genomics and Epigenomics at the Archie and Irene Verspeeten Clinical Genome Centre at LHSC. "It also has the potential to lead to health system cost savings since many patients spend years and even decades being tested to rule out other potential diseases with similar symptoms." In a second study, Dr. Sadikovic's team used EpiSign technology for the first time to develop an accurate biomarker for a group of disorders called fetal valproate syndrome, which is caused by prenatal exposure to toxic levels of medication that may be used to treat bipolar disorder and migraines, or to control seizures in the treatment of epilepsy. It can result in neurodevelopmental disorders in infants, including learning, communication and motor disorders, autism, and intellectual disabilities. This is a significant breakthrough as it's the first time the technology has been used to aid in diagnosis of a disease caused by environmental factors rather than genetics. It highlights how epigenetics can be influenced by environmental and lifestyle factors, including diet, exercise and exposure to toxins." Dr. Bekim Sadikovic, Lawson Scientist at LHSC The research is ongoing as Dr. Sadikovic and his team, in collaboration with the global EpiSign Discovery Research network, are currently studying and developing biomarkers for more than 700 rare disorders. He noted the potential of this research is endless, showing promise for use in the diagnosis, prognosis and treatment of many other diseases and disorders, including cancer. "One in 20 people have a rare disease that could present at any point in their lives and can be caused by genes, environmental exposures, or their combined effects," he noted. "We can help diagnose a growing number of genetic diseases and, now for the first time, we can look beyond the genome and accurately measure the impact of the environment." These studies are a collaborative effort involving multidisciplinary teams in Canada, the United States, the United Kingdom and Europe. The first study, titled "Identification of a DNA methylation episignature biomarker for recurrent constellations of embryonic malformations," is published in American Journal of Human Genetics. The second study, titled "Discovery of DNA methylation signature of teratogenic exposure to valproic acid," is published in Genetics in Medicine. Funding for the research was provided by Genome Canada and Ontario Genomics, as well as in-kind support from EpiSign Inc. Lawson Health Research Institute Journal reference: Haghshenas, S., et al. (2024) Identification of a DNA methylation episignature for recurrent constellations of embryonic malformations. American Journal of Human Genetics. doi.org/10.1016/j.ajhg.2024.07.005.

World first discoveries allow researchers to accurately diagnose prenatal exposure syndromes and birth disorders

Researchers at London Health Sciences Centre (LHSC) and Lawson Health Research Institute are using advanced technology and artificial intelligence (AI) to diagnose rare diseases and prenatal exposure-related birth abnormalities in two studies published today, one study in American Journal of Human Genetics and the other in Genetics in Medicine. The research uses technology called EpiSign, which was developed by Dr. Bekim Sadikovic, Lawson Scientist at LHSC. EpiSign leverages AI to measure a patient's epigenome -- a unique chemical fingerprint that every person has on top of their DNA that is responsible for turning genes on or off. EpiSign can currently be used to help diagnose more than 100 genetic diseases that were previously difficult to diagnose. In one of two newly published studies, Dr. Sadikovic's team has found that EpiSign can be used to accurately identify patients affected by birth disorders called recurrent constellation of embryonic malformations (RCEMs). Since their discovery more than 70 years ago, attempts to identify the cause and specific diagnostic markers for RCEMs have been unsuccessful, making it challenging to provide patients and families with accurate diagnoses. EpiSign can now be used to accurately identify RCEMs for the first time using a blood test. "Reaching an early and accurate diagnosis can be life-changing. This is a major breakthrough that allows physicians to provide earlier and more accurate diagnosis, resulting in improved disease management," said Dr. Sadikovic, who is also Research Chair in Clinical Genomics and Epigenomics at the Archie and Irene Verspeeten Clinical Genome Centre at LHSC. "It also has the potential to lead to health system cost savings since many patients spend years and even decades being tested to rule out other potential diseases with similar symptoms." In the other study, Dr. Sadikovic's team used EpiSign technology for the first time to develop an accurate biomarker for a group of disorders called fetal valproate syndrome, which is caused by prenatal exposure to toxic levels of medication that may be used to treat bipolar disorder and migraines, or to control seizures in the treatment of epilepsy. It can result in neurodevelopmental disorders in infants, including learning, communication and motor disorders, autism, and intellectual disabilities. "This is a significant breakthrough as it's the first time the technology has been used to aid in diagnosis of a disease caused by environmental factors rather than genetics," explained Dr. Sadikovic. "It highlights how epigenetics can be influenced by environmental and lifestyle factors, including diet, exercise and exposure to toxins." The research is ongoing as Dr. Sadikovic and his team, in collaboration with the global EpiSign Discovery Research network, are currently studying and developing biomarkers for more than 700 rare disorders. He noted the potential of this research is endless, showing promise for use in the diagnosis, prognosis and treatment of many other diseases and disorders, including cancer. "One in 20 people have a rare disease that could present at any point in their lives and can be caused by genes, environmental exposures, or their combined effects," he noted. "We can help diagnose a growing number of genetic diseases and, now for the first time, we can look beyond the genome and accurately measure the impact of the environment." These studies are a collaborative effort involving multidisciplinary teams in Canada, the United States, the United Kingdom and Europe.

Researchers use AI-powered method to identify genetic epilepsies earlier than current genetic diagnosis

Diagnosing the genetic cause of a disease can aid in finding therapies and directing treatment, but often these diagnoses occur long after the disease has impacted a patient's life. In a new study, researchers from Children's Hospital of Philadelphia (CHOP) used machine learning and artificial intelligence to comb through medical records and use clinical notes to match symptoms with specific genetic epilepsies. The results of their study could significantly improve the time to diagnosis and treatment. The findings were recently published in the journal Genetics in Medicine. More than 100 epilepsies caused by a single gene mutation have been identified, with several therapies being designed to target the genes responsible for these epilepsies. However, genetic testing can take a long time to confirm a particular genetic epilepsy. For example, in Dravet Syndrome, one of the most common genetic epilepsies, symptoms can be observed between the ages of 6 to 9 months, yet the average age for diagnosis is 4.2 years. Cost and access barriers continue to be an issue, meaning that researchers must develop methods for making diagnoses more timely and more widely accessible. Prior studies from the Epilepsy Genetics Initiative (ENGIN) at CHOP--one of the largest epilepsy genetics programs in the country, with more than 5,000 individuals assessed for epilepsy genetics evaluations so far--have demonstrated that standardized data from Electronic Medical Records can be used to study clinical data at very large scales and better predict onset of epilepsy based on symptoms instead of relying solely on a confirmed genetic diagnosis. Building upon these previously developed techniques, researchers in this study aimed to identify early clinical features that could suggest a genetic diagnosis of epilepsy. "We wanted to determine whether the type of information captured in electronic medical records prior to genetic testing could provide clinicians with clues for a later diagnosis," said first study author Peter D. Galer, MSc, a Ph.D. student with ENGIN at CHOP and the Center for Neuroengineering and Therapeutics at the University of Pennsylvania. "In this instance, we found that a wide range of genetic epilepsies have key clinical features that present prior to genetic testing and diagnosis." Using Natural Language Processing, an AI-driven standardized method for processing clinical information from text in Electronic Medical Records, the researchers extracted 89 million timestamped clinical annotations from 4,572,783 clinical notes from 32,112 individuals with childhood epilepsy, including 1,925 individuals with known or presumed genetic epilepsies. The researchers identified 47,774 age-dependent associations of clinical features with genetic epilepsies a median of 3.6 years prior to when those diagnoses were confirmed with a genetic test. A total of 710 genetic etiologies were identified in the cohort, and in that group, neurodevelopmental differences observed between the ages of 6 and 9 months increased the likelihood of a later genetic diagnosis fivefold. "By examining a very large dataset of individuals with childhood epilepsies, we believe that our results could be used prospectively for new diagnoses. Since most clinicians use Electronic Medical Records, we believe this system could be widely adapted and utilized even in patient populations where genetic testing is not immediately available after symptom onset," said senior study author Ingo Helbig, MD, pediatric neurologist in the Division of Neurology, co-director of ENGIN, and Clinical Director of the CHOP/Penn Center for Epilepsy and Neurodevelopmental Disorders (ENDD). Helbig also serves as the Scientific Director of Arcus Omics, an institution-wide initiative that allows for genomics and clinical data at CHOP to be analyzed jointly. The analysis of the combined dataset was only made possible through the resources of the Arcus Omics team. "In the era of precision medicine, quicker, more accurate prognoses could make an enormous difference in the lives of individuals living with genetic epilepsies," said Helbig.