EXCITING POSSIBILITIES AS AI REVOLUTIONISES HEALTHCARE CHALLENGES
High-performance computing (HPC), which has traditionally been dominated by physicists, chemists and astrophysicists, also offers the computing power needed to help humanity solve some of its greatest healthcare challenges. In combination with artificial intelligence (AI), these technologies will transform the future of healthcare.
This is according to Noam Rosen, EMEA Director, HPC & AI at Lenovo ISG, who explains: “High-performance computing and artificial intelligence have the potential to revolutionise healthcare, improving everything from drug research to cancer treatments. Using HPC in healthcare is relatively new, and extremely exciting. AI also presents tremendous possibilities with regards to the public health domain, the administration of healthcare and the clinical setting, particularly when it comes to the automation of diagnosis processes.”
Rosen clarifies that HPC is a perfect fit for healthcare because of the large data sets generated by public health systems, much of which is in the form of images, for example from scans. “These data sets constitute a vast body of knowledge which has been largely unexplored until now,” he says.
“Most of their value comes from interpretations by experts, which has been done manually and is a hugely limiting factor when it comes to getting value from this data. HPC enables researchers and clinicians to ask bigger and more complex questions, and get the answers much faster. It leads directly to better research results and more precise treatment decisions.
Alaa Bawab, General Manager, Lenovo Infrastructure Solutions Group, adds: “AI refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. It encompasses the automation of activities associated with human thinking such as decision-making, problem-solving, and learning.
“Against this background, current technology trends in healthcare include remote health monitoring, using technology to monitor a patient’s health outside the clinical environment through data exchange between devices that connect patients and providers; as well as the use of AI and predictive analytics to build industry insights with the aim of proactively improving preventative care. Added to this, genomics – the molecular biology study of the structure, function and mapping of genomes – is providing us with a far more detailed understanding today of what causes illness and infectious diseases. This is supporting the development of new innovations, enabled by HPC and AI.”
Bioinformatics speeds up diagnosis and treatment
In life sciences, the time it takes to answer crucial questions is incredibly important, says Rosen. “For instance, when it comes to seeing how a cancer patient will respond to a specific treatment, time matters a great deal. Speed is also imperative when spotting the signs of a new infection in society and stopping it before it spreads widely. The urgent need to create quick answers requires more powerful and sophisticated computing resources.”
In this regard, Rosen clarifies that HPC is particularly useful in bioinformatics, a multidisciplinary field that integrates the principles of mathematics, statistics, computer science and biological science. “The role of bioinformatics in medical research is to extract knowledge from biomedical data,” he explains. “HPC systems are now evolving to meet bioinformaticians’ needs, with new hardware and software products allowing more sophisticated uses of data.”
Understanding our genes
Bawaab notes that HPC facilities speed as well as accuracy, allowing a greater focus on individual data. At the same time, this also facilitates an understanding of future pandemic threats.
“Rapidly decreasing DNA sequencing costs, combined with increasing computing power, means that we are able to understand the human genetic code better than before. Genomics is providing us with far more detailed understanding of what causes illness and infectious diseases,” he clarifies, “and this in turn is allowing a shift in the life sciences industry from the development of ‘blockbusters’, which addresses the needs of the masses, to developing more niche, personalised solutions for patients. At the same time, we can harness genomics to respond quickly to evolving threats, such as COVID-19, as well as potential future pandemics.”
Rosen adds: “Lenovo Infrastructure Solutions Group has created a solution named GOAST, or in other words the Genomics Optimisation and Scalability Tool. GOAST is a great example of how much faster HPC can deliver scientific data. It allows integrators of HPC to break into the genomics space faster, without having to hire vertical technical expertise.
“GOAST has the capability to reduce the time to scientific insights by turning genomics analytics, a process that used to take days, down to minutes. Pre-GOAST, it took between 60 to over 150 hours to process a single human genome – now, however, it would take just 48 minutes. Excessive time taken to analyse data causes a delay in time to scientific insights, and also has a negative effect on company profits and growth.”
The role of AI
Artificial intelligence will also be important in everything from drug discovery to public health to the clinical setting, says Rosen. He clarifies: “Drug manufacturers frequently apply machine learning techniques to extract chemical information from large compound data sets and use this to design new drugs for clinical trials. AI models can be trained to better select the study participants with advanced statistical methods and to assess the results of the studies.
“In the clinical setting, the potential of AI is enormous, ranging from the automation of diagnosis processes to therapeutic decision making and clinical research. Among the most promising applications of AI is for the automated processing of cardiac imaging data, which is necessary for the assessment of cardiac structure and function. Generation of more accurate and automated echocardiograms with the use of AI is expected to reveal unrecognised imaging features that will facilitate the diagnosis of cardiovascular disease. It will also minimise the limitations associated with human interpretation of these scans.”
Bawaab adds that AI can also assist in the public health domain, in promoting health, preventing disease and prolonging life: “AI can help identify locations with a prevalence of disease or high-risk behaviours among its community members, allowing healthcare workers to intensify contact with patients as well as to offer targeted services to the people in the area.”
The last application of AI is in the administration of healthcare. Bawaab notes that the improved flow of data across the organisation allows for more efficient coordination between departments. “This can, for example, reduce the waiting time of patients, or provide accurate information on the availability of hospital beds. A lack of bed availability is an important cause of surgical cancellations and applying AI to optimise the availability of beds can help to decrease these,” he explains.
“Healthcare systems are characterised by significant administrative functions. AI can perform different types of routines related to this administrative requirement more efficiently and accurately, and without bias.”
HPC and AI in healthcare – the future
Looking ahead to the future, society must make it easier for healthcare organisations to use these important technological tools, says Rosen.
“Rather than research institutions taking the components and starting from scratch, we need to integrate these tools in a way that makes it easier for organisations in the healthcare space to make the most of them. HPC can offer answers to many of the greatest problems we face and can herald a new era of personalised medicine in combination with AI. It is therefore crucial that medical experts have the access they need to these game-changing technologies,” he concludes.