We look at how scientists in Ireland and beyond are using artificial intelligence to enhance their research and improve health outcomes for patients.
Artificial intelligence is disrupting all walks of human life, from business and science to education and even entertainment. While the jury is still out on whether it is mostly positive, and to what extent it should be regulated, health research stands out as one area that AI is sure to change for the better.
According to the World Economic Forum, healthcare accounts for 11pc of global GDP or $9trn annually. This presents a significant opportunity for AI and machine learning to aid in research and development of everything from drugs and vaccines to better medical diagnostics and treatment.
“We’ve had this real spike in the last couple of decades,” Aaron Quigley told SiliconRepublic.com recently. He is the science director and deputy director of CSIRO’s Data 61, the digital specialist arm of Australia’s national science agency.
“It’s a human capital solution as much as a research, innovation solution, there’s just a lot of people who have the skills now to do this kind of advanced AI research.”
Reducing false positives in colorectal cancer
In February, Northern Ireland’s Sonrai Analytics entered a partnership to deploy its AI tech in the United Arab Emirates to improve cancer patient outcomes. A year ago, health-tech start-up xWave Technologies teamed up with CeADAR, Ireland’s centre for applied AI research, to make medical testing more predictive and personalised using AI.
Now, Irish scientists are increasingly teaming up with European and international researchers on projects that will see the deployment of AI in healthcare research.
Take, for instance, APC Mircobiome, a world-leading Science Foundation Ireland research centre based at University College Cork. Scientists from the centre have joined forces with BowelScreen, the national colorectal cancer (CRC) screening service, and the Mater Misericordiae University Hospital, to reduce ‘false-positive’ rates in CRC screening.
According to the World Health Organization, CRC is the third most common cancer globally. Early identification of the disease can dramatically improve patient outcomes, but, according to APC Microbiome, traditional screening is based on a faecal immunological test which typically have false-positive rate of more than 37pc – which can result in unnecessary invasive patient colonoscopy treatments.
Funded by Horizon Europe, the new project will leverage AI to conduct a more detailed and thorough analysis of stool microbiome data and aim to significantly reduce the false-positive rate while also enhancing the sensitivity for early detection of colon cancer.
The innovative European project, led in Ireland by Prof Paul O’Toole of APC Microbiome Ireland and Prof Padraic MacMathuna of BowelScreen, can significantly reduce the volume of colonoscopy procedures required with significant cost savings and harm reduction.
O’Toole said the so-called ‘Microb-AI-ome’ project will respect privacy regulations by integrating isolated, national databases into one international and privacy-preserving federated database network.
“Crucially this ensures that all personal data remains safely on the local databases without infringing privacy regulations, and at the same time will be able to feed and train the AI models,” he said.
The project will integrate microbiome data collected during its runtime for more than 4,000 individuals from Ireland and France.
“This ground-breaking project combining international expertise in CRC, AI and microbiomics is a significant development in medical research and leverages the established scientific and clinical expertise available in Ireland,” added MacMathuna.
“Outcomes from this Horizon Europe project have the potential to significantly enhance CRC early detection with consequent increased survival.”
Using AI to search for novel antibiotics
These are just a few of many examples of how AI helping healthcare research in Ireland. Across the pond, researchers at MIT and McMaster University have identified a new antibiotic using an AI algorithm that can kill a type of bacteria that is responsible for many drug-resistant infections.
Acinetobacter baumannii is a dangerous bacterial species that lurks in many hospital settings and causes pneumonia, meningitis and other serious infections. It is also a leading cause of infections in wounded soldiers in Iraq and Afghanistan.
However, the biggest concern around A baumannii is that it is becoming increasingly resistant to antibiotics.
“Acinetobacter can survive on hospital doorknobs and equipment for long periods of time, and it can take up antibiotic resistance genes from its environment,” said Jonathan Stokes, a former MIT postdoc who is now an assistant professor at Canada’s McMaster University. “It’s really common now to find A baumannii isolates that are resistant to nearly every antibiotic.”
The researchers identified a new drug from a library of nearly 7,000 potential drug compounds using a machine learning model that they trained to evaluate whether a chemical compound will inhibit the growth of A baumannii.
“This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics,” added James Collins, a professor at MIT’s Institute for Medical Engineering and Science and Department of Biological Engineering. “I’m excited that this work shows that we can use AI to help combat problematic pathogens such as A baumannii.”
While AI is playing an increasingly important role in healthcare research, experts warn of the downsides of the emerging technology.
Prof Paula Petrone of the Barcelona Institute for Global Health, who is developing algorithms for the detection of pathology in non-invasive ultrasound imaging, told SiliconRepublic.com last month that AI is not without fault and models must be trained to avoid biases and encourage citizens’ trust in scientific research.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.