The Covid-19 pandemic has forced changes and developments to the way the life science and healthcare industries, from vaccines being developed at record speed, to diagnostics taking centre stage. These advances wouldn’t have been possible without the implementation of technology. For this level of innovation to continue in a post-pandemic world, there must be a sustained focus on applying emerging technologies such as AI and data analytics to scientific research in life sciences and healthcare.
Here, four experts from the medical, life sciences and diagnostics sectors share their thoughts on the pivotal role that technology is playing in advancing science, and how it can continue to be applied to improve patient care and clinical breakthroughs.
The role of AI in diagnostics
Over the past 18 months, we’ve seen the diagnostics industry taking centre stage as it has enabled the quick and safe diagnosis of Covid-19. According to Adrian Smith, general manager, Hologic UK and Ireland, “Covid-19 has not only brought more focus to the role of new diagnostic technologies and solutions, but also on their rapid adoption so they can be fully leveraged in the fight against the pandemic.”
To help diagnose patients at speed and ensure diagnosis is highly accurate, AI technology can play an important role across a number of diseases. For example, Smith says: “AI-guided imaging has the potential to remove the current requirement for breast images to be reviewed by two radiologists. Together with increasing the numbers of screening units and mammographers, this can increase breast cancer screening capacity. When used as part of a screening programme, AI could effectively and accurately highlight the areas that are of particular interest for the reader, streamlining workflow and improving efficiencies within the breast screening programme.
Another example of where AI can support diagnostics is in cervical cancer screening. “For digital cytology in cervical cancer screening, the system is able to evaluate tens of thousands of cells from a single patient in around 30 seconds and present the most relevant diagnostic material to a trained medical professional for the final diagnosis,” says Smith.
Deep learning algorithms, in the form of AI, can also be applied in heart disease care, to help reduce the backlog of appointments created by the pandemic by significantly reducing diagnostic times. Charles Taylor, founder and chief technology officer, Heartflow, explains "Technology has been essential to treat coronary heart disease and drive down diagnosis times. By taking data from CT scans, our technology leverages algorithms trained with AI and highly trained analysts to create a personalised, digital 3D model of a patient’s coronary arteries. Its algorithms then solve millions of equations to simulate blood flow through the arteries to help clinicians assess the impact of any blockages. This technology helps clinicians diagnose CHD without the need for more invasive investigations such as an angiogram, which can carry its own risks of complication.”
The importance of patient data analysis
The pandemic has also brought the importance of patient data analysis to the fore. According to Dr Nick Scott-Ram, chief of Data Analytics, Partnerships & Delivery and commercial director, Sensyne Health, “Covid-19 has driven the healthcare and life sciences industries to improve patient care and dramatically speed up more inclusive and targeted drug development. During the pandemic, we have seen a collective clinical trials process, prompting global cooperation for vaccine research and distribution for the Covid-19 virus in under a year – a pace never before possible.”
These advances in drug and treatment development are only achievable at the speed and scale we’ve seen with the Covid-19 vaccine if scientists and researchers have access to real-world patient data, which can be analysed and insights can be garnered from it.
Scott-Ram says: “Access to large, anonymised patient datasets means that synthetic control arms can be generated, drug targets can be identified, clinical researchers can gather insights faster into their research questions, and they can even analyse the performance of drugs after regulatory approval. In turn, this is helping to reduce the time and cost associated with trials, minimise the burden on patients, and ultimately get new drugs to market faster.”
This is echoed by Taylor, who underlines the importance of applying AI algorithms to model coronary arteries in providing doctors data and insights on a level that wasn’t previously possible without an invasive procedure. “This information enables physicians to effectively triage patients to identify those with severe disease who are in urgent need of intervention such as stenting, while also being able to identify patients who can safely manage their condition with medication alone and don’t need to stay on waiting lists for further investigations. Being able to streamline diagnosis time and prioritise those most in need of intervention can make a considerable difference when working to reduce backlogs.”
Streamlining life sciences R&D
As a result of vaccines being developed at pace during the pandemic, the expectations on the life sciences industry have increased, and the standard has been set for how future scientific research is carried out. Sajith Wickramasekar, co-founder and CEO, Benchling, explains that to ensure that this impressive pace of scientific discovery continues, the way research and development in the industry is carried out must change. “Currently, barriers exist that prevent teams from efficiently collaborating, and despite a close connection between the research and development, there’s often a disconnect between the two functions when it comes to how they actually work – and how data is stored and shared is a big factor.”
Access to data was critical when developing the Covid-19 vaccines, and Wickramasekara adds, “As scientific data is often recorded, analysed and shared in disparate systems and databases, handoffs from research to development are complex and time consuming, and it isn’t possible to make cross connections that lead to such breakthroughs. The vaccine development really highlighted that this inability to access data has severely stifled innovation in the industry previously.”
To overcome this challenge, digital transformation needs to be carried out to suit the complexity of today’s modern scientific research. “By overhauling the way insights are documented, it is possible to both significantly improve productivity, and accelerate timelines for both research and development teams,” says Wickramasekara.
Technology is playing a critical role in advancing science. It is supporting drugs to be developed faster, diagnostics to be made more accurately and efficiently, and can underpin better collaboration between scientists as they research and develop new treatments.
Going forward, the momentum around life sciences and healthcare generated by the pandemic must continue, and investments into technology such as AI and the cloud will be critical.