Healthcare AI specialist, Clinithink, delivers ‘hours to minutes’ ground-breaking analysis to save vital time in the care of sick newborns with rare disease

Healthcare AI specialist, Clinithink, delivers ‘hours to minutes’ ground-breaking analysis to save vital time in the care of sick newborns with rare disease 

Rapid diagnosis of a case at Rady Children’s Institute for Genomic Medicine (RCIGM) highlights the value of new advancements with AI in diagnostics 

Clinithink’s advanced AI technology has enabled clinicians at RCIGM, a world leader in the field of genomics, to perform the deep phenotyping of a critically ill five-week-old baby with an unknown condition within minutes to help identify his rare genetic disorder. 

The team at RCIGM have published a letter in the New England Journal of Medicine(NEJM) describing how this accelerated diagnosis allowed the child to be put on treatment and be discharged from hospital three days after he had been admitted with a potentially fatal undiagnosed disorder. Now at seven months of age the child is thriving. 

Clinithink, a market leading healthcare AI company, provides innovative software systems to enable hospitals to review millions of clinical documents at a rapid pace. Its CLiX technology, which harnesses natural language processing (NLP), was integral to achieving a remarkable end-to-end time of 13.5 hours from blood sample to diagnosis in the child’s case, cited in the New England Journal of Medicine. 

The team from RCIGM, which is pioneering the use of innovative technology to improve the diagnosis and treatment of children with rare disease, reported the use of a rapid, AI-enabled approach to Whole Genome Sequencing (WGS) that included the use of Clinithink’s CLiX focus solution.  

RCIGM describe how this approach enabled the successful diagnosis and treatment of the child, who had been previously healthy but became acutely unwell two hours prior to admission to the Neonatal Intensive Care Unit (NICU) at Rady Children’s Hospital-San Diego. Testing showed he had encephalopathy, but the underlying cause was not known.  

As the child’s condition deteriorated with multiple seizures, WGS was performed to evaluate whether he had an underpinning genetic disease, over 1,500 of which can cause encephalopathy and seizures. Each minute lost before a diagnosis and precise treatment is started increases the likelihood of permanent neurological damage or even death.  

Clinithink’s patented CLiX technology lies behind the ground-breaking clinical natural language processing (NLP) ability of its solutions. CLiX focus automates “deep phenotyping” to support diagnosis in rare disease. Deep phenotyping is the painstaking analysis of an individual patient’s characteristics and clinical findings to compare with over 12,000 phenotypes that are known to be associated with over 7000 rare diseases. This analysis complements genomic data and is essential to confirming a diagnosis. Conventionally, deep phenotyping is done manually and can take hours or longer, even when undertaken by highly trained geneticists.  

In the case reported in the NEJM, the team at RCIGM used CLiX focus to complete the deep phenotyping step in the process in one minute as part of their pioneering approach. This helped to achieve a remarkable end-to-end time of 13.5 hours from blood sample to diagnosis. The disease identified by WGS, thiamine metabolism dysfunction syndrome 2 (THMD2), can be effectively treated with two vitamin supplements if diagnosed early. 

This treatment was started promptly and the child was discharged from hospital three days later. He is thriving at seven months of age. The team also report that the child’s older sibling probably died of the same condition ten years earlier, aged 11 months but before rapid, diagnostic WGS was available.  

This illustrates the benefit which the modern AI-based approach can deliver in the enormously challenging field of rare disease diagnosis and management. A similar approach was used in another RCIGM paper published in the American Journal of Human Genetics describing how WGS was used successfully to identify rare genetic diseases among 184 babies in intensive care units at five children’s hospitals in California. The authors reported significant cost-savings by using this approach to diagnose rare disease.  

“Clinithink’s natural language processing technology can help speed time to diagnosis in critically ill children,” said Stephen Kingsmore, MD, CEO of Rady Children’s Institute for Genomic Medicine. He continued, “CLiX focus expedites deep phenotyping, cutting this step from hours to minutes, a key component of our rapid WGS pipeline.” 

“Naturally we are absolutely delighted that the team at RCIGM have been able to deliver such a profoundly important outcome for this patient using their pioneering approach to rapid rare disease diagnosis which includes CLiX focus. As healthcare technology specialists it is incredibly inspiring for us to know that the software we develop can help to make this kind of difference at the clinical sharp end. It’s why we come to work.”, said Chris Tackaberry, CEO and Co-founder, Clinithink.