As adoption of AI in health continues to accelerate, its range of applications, capacity and impact on patient outcomes is rapidly developing.
More and more healthcare professions across the world are adopting AI to improve patient care.
By putting users in control of their own health and wellbeing, AI technologies can increase the ability for clinicians to better understand the day-to-day routines and needs of patients they care for; therefore allowing them to provide better feedback, guidance and support.
As AI rises in popularity within the industry, we can also see an increase in the number of technologies on offer to clinicians.
Here, Health Tech World looks at some of the most exciting AI in health developments…
Dementia detection
Birmingham and Solihull Mental Health NHS Foundation Trust has partnered with Cognetivity to deliver an AI-powered tool – the Integrated Cognitive Assessment (ICA) – to detect dementia.
The ICA, which will be deployed across primary and secondary care services operating out of more than 40 sites, has the ability to detect dementia up to 15 years earlier than conventional methods, and even before memory symptoms present, according to the company.
The next generation assessment benefits from shorter testing duration, automatic marking and high classification accuracy, in comparison to pen and paper testing. Its founders also say it’s well placed to serve the UK’s diverse population as the artificial intelligence is free form learning effect and cultural biases.
Landmark creation of dedicated department
Located in New York City, The Icahn School of Medicine at Mount Sinai has announced the launch of a department dedicated wholly to AI.
The Department of Artificial Intelligence and Human Health, billed as the first of its kind, is aimed at enhancing opportunities for collaboration among medical and computer scientists and establishing an AI framework that’s integrated across all the health system’s hospitals and clinics.
Thomas J Fuchs, the school’s dean for artificial intelligence and human health, said: “The overarching goal for the Department for AI and Human Health is to impact patients’ health with AI.
“We will accomplish this by building AI systems at scale from data representing Mount Sinai’s diverse patient population. These systems will work seamlessly across all hospitals and care units to support physicians, foster research and, most importantly, help patients’ care and wellbeing.”
New drug combination for children with cancer
Scientists at The Institute of Cancer Research, London, and the Royal Marsden NHS Foundation Trust have used artificial intelligence to identify a new combination of drugs for use against incurable childhood brain cancer.
The approach allowed the scientists to explore ideas on how to target children with diffuse intrinsic pontine glioma (DIPG), who have mutations in a gene called ACVR1.
The initial hypothesis for the study came from BenevolentAI, a company that has built a leading AI drug discovery platform and its own in-house pipeline of drug discovery programmes. Researchers used BenevolentAI’s platform to identify drugs that could be used to target ACVR1 mutations in DIPG, with computational tools allowing scientists to explore information and uncover insights they would not have been able to find using human reasoning alone.
Diagnosing genetic causes of serious disease
An AI-based technology can rapidly diagnose rare disorders in critically ill children with high accuracy, according to a report by scientists from University of Utah Health and Fabric Genomics. The technology means clinicians can determine the root cause of a disease and recommend treatment much quicker.
Arriving at a diagnosis within the first 24 to 48 hours after birth gives the best chance to improve the newborns’ conditions. In order to utilise speed and accuracy of diagnosis, the scientists worked with creators of AI-based platform Fabric to develop the new Fabric GEM algorithm, which incorporates AI to find DNA errors that lead to disease.
In this study, the team tested GEM by analysing whole genomes from 179 previously diagnosed pediatric cases from Rady’s Children’s Hospital and five other medical centres across the world. GEM identified the causative gene as one of its top two candidates 92 per cent of the time, and in doing so, outperformed existing tools that accomplished the same task less than 60 per cent of the time.
AI for brain stimulation
A new algorithm to improve brain stimulation devices in treating disease is being developed by Mayo Clinic and Google Research.
Electrical stimulation of the brain is already widening treatment possibilities for millions of people with epilepsy and movement disorders – but it’s hoped that this stimulation can be utilised even further with new developments, supporting those with psychiatric illness and direct brain injuries, such as stroke.
In a remarkable step forward, Mayo Clinic researchers, working with Google Research Brain Team, have developed a set of paradigms that simplify comparisons between effects of electrical stimulation on the brain.
In the study, a patient with a brain tumour underwent placement of an electrocorticographic electrode array to locate seizures and map brain function before a tumour was removed, with results showing that every electrode interaction resulted in hundreds to thousands of time points to be studied using the new algorithm.
Dr Kai Miller, Mayo Clinic neurosurgeon and first author of the study, said: “Our findings show that this new type of algorithm may help us understand which brain regions directly interact with one another, which in turn may help guide placement of electrodes for stimulating devices to treat network brain diseases.”
