A study published in Science Translational Medicine documents the role played by Clinithink’s patented clinical natural language processing platform in delivering genetic diagnoses to neonatal and pediatric intensive care physicians in record breaking time
A new study, published today 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[i]. 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”.
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.
[i] Reference World Health Organisation publication
