Search News Archives
Conferences | Events
Helping To Diagnose Rare Disease In Record Time
A new study, published in Science Translational Medicine, details the pioneering work undertaken by a collaboration led by Stephen Kingsmore, MD, DSc, President and CEO of Rady Children’s Institute for Genomic Medicine (RGIGM)
The team, which includes British company Clinithink, utilized a machine learning process and clinical natural language processing to diagnose rare genetic diseases in record time. This revolutionary method is providing speedy answers to physicians caring for infants in intensive care and opens the door to increased use of genome sequencing as a first-line diagnostic test for babies with rare genetic disorders.
There are between 5000 and 8000 rare diseases affecting around 400 million people worldwide. (source) The diagnosis of rare disease is a significant challenge as many physicians may have never encountered the symptoms before. As a result it can take, on average, 4.8 years for an accurate diagnosis of a rare disease to be made, with patients seeing an average of 7.3 physicians on this diagnostic odyssey. In February 2018 the same team achieved a GUINNESS WORLD RECORDS™ title for the Fastest genetic diagnosis, successfully reducing diagnosis time to just 19 hours. This is particularly significant as delays in diagnosis can lead to inappropriate management and disease progression, with misdiagnosis leading to additional interventions later deemed to be inappropriate given the underlying disorder.
Providing a key element of the diagnostic pipeline was Clinithink’s patented clinical natural language processing platform, CLiX ENRICH. This ground-breaking solution quickly combs through a patient’s electronic medical record to 1) automatically extract all of the clinical information that has been documented about that patient and 2) compare this information to the many thousands of phenotypes and synonyms which are critical to the diagnosis of thousands of rare diseases. CLiX ENRICH can perform both of these tasks in a fraction of the time it would take a highly skilled physician – potentially saving lives in critical care situations.
Dr Richard Gain, senior clinical terminologist at Clinithink and one of the authors on the Science Translational Medicine paper said: “The team at Clinithink thrive on the knowledge that we are crossing new frontiers within the research community in the diagnosis and management of rare diseases. The fact that the results of this study have been published in one of the most prominent scientific journals further certifies the incredibly exciting value of our technology. Most importantly, it is very humbling to know that the results of our work can go towards helping save the lives of critically ill children. It is prospects such as these – the chance to make a real difference - that drives everyone at Clinithink to continue innovating and honing our software”.
Stephen Kingsmore said of the technology: “Some people call this artificial intelligence, we call it augmented intelligence. Patient care will always begin and end with the doctor and by harnessing the power of technology, we can quickly and accurately determine the root cause of genetic diseases. We rapidly provide this critical information to intensive care physicians so that they can focus on personalizing care for babies who are struggling to survive.”
This important work represents the first time that rare diseases have been diagnosed using a supervised machine-learning system to analyse and interpret genetic disease testing results.
Eric Topol, MD, Professor of Molecular Medicine at Scripps Research and author of the new book Deep Medicine said: “This is truly pioneering work by the RCIGM team – saving the lives of very sick newborn babies by using AI to rapidly and accurately analyse their whole genome sequence”.
Dr Calum Yacoubian, Partner Success Lead, Life Sciences at Clinithink added: “The goal for the future is to scale this solution up for use in the clinical setting to expand access to life-changing genomic medicine. By reducing the time spent on less critical manual data review, we believe CLiX has the potential to augment the capabilities of the highly-trained human experts who work in this field, thereby offering life changing diagnostics, research and treatments to a breadth of patients that would not otherwise be possible”