This article will explore the biggest trends in data science in the healthcare industry, as identified by experts in the field.
From AI and DevOps to digital twins, data science has provided many beneficial features for healthcare organizations.
The healthcare industry has leveraged data science to speed up operations and help patients recover from a variety of ailments, including COVID-19. As the industry continues to navigate the post-pandemic landscape, this shows no signs of slowing down.
“There are so many areas where data science can help enable more efficient care, from managing capacity demand to predicting length of stay, aligning with discharge and reducing patient burden. care demands for patients discharging from acute care, ”said Rob O’Neill, director of analysis at Morecambe Bay University Hospitals NHS Foundation Trust (UHMBT).
“Since the pandemic, there has been an accelerated use of data. COVID-19 has increased the need for health officials to be able to make real-time decisions and forecast the resources they will need for future demand. For example, being able to understand the risk of readmission of our current patient population is crucial to effectively execute forecasts of unanticipated demand and potentially manage an influx of crisis-related patients, and limit the number of patients who need to return to the next level. hospital environments during a pandemic. “
In this article, we take a look at the biggest trends in data science happening in healthcare.
Evolving analytics platforms
NHS analytics leader O’Neill went on to explain how analytics platforms have evolved to help meet demand for services.
He said: “At UHMBT, we have combined data science and predictive analytics with Qlik, Snowflake and DataRobot. Companies have come together to create a modern analytics platform that enables the real-time analysis needed to predict patient readmission, which in turn has helped plan for COVID-19 surge capacity. . It’s a combination of a cloud data platform, enterprise AI, and machine learning for predictive modeling and actionable business intelligence.
“With Qlik reading live data from Snowflake and running DataRobot’s predictive model directly in the Qlik app, healthcare decision makers have an up-to-date window into their current state of care, while also gaining a sense of strategies. that they must perform to better serve their entire patient population.
“This allows UHMBT clinicians to explore specific modalities and services to clearly understand where, how and why readmissions occur. This helps us better understand current demand and forecast the resources we will need to provide comprehensive care to our entire patient population. “
Hot topics and emerging trends in data science
We evaluated the views of data science experts, asking them about the biggest emerging trends in data science. Read here
Increased use of AI
Artificial intelligence and machine learning deployments have proven to be critical in accelerating communication and data management in healthcare. According to Nick Mandella, management consultant at Harnham, this is expected to increase further, to make patient care even more efficient.
“AI and data science have enormous potential to have a significant positive impact on healthcare in the near future,” Mandella said.
“One example is using machine learning to optimize patient procedures, making sure they get in and out as efficiently as possible, freeing up bed space and allowing more operations to be done. – a currently problematic issue for the NHS.
“AI is also used to aid in the diagnosis of diseases. By using computer vision and deep learning to understand scan images, diseases that may be more difficult to detect, such as certain types of cancer, can be detected and treated much earlier, which means a rate of much higher survival for patients.
“In many cases and tests that have been done, AI has been more successful than using a doctor with many years of experience.”
Adopting DevOps for Cost Reduction
Additionally, Mandella believes DevOps has played a vital role, especially in the pharmaceuticals arena.
He said DevOps has helped businesses in the space reduce costs, comply faster, and maintain productivity: “The healthcare industry is heavily regulated to ensure that drugs created do not cause harm, and that includes monitoring its software and hardware components as much as anything else.
“Using computer system validation (CSV) is the most common way for companies to be regulated by the FDA, but there’s no denying that this system is time consuming and expensive. Using DevOps for this process enables businesses to autonomously reduce the risk of bugs, avoid bottlenecks without compromising productivity and reliability.
“Not only do all of these elements within DevOps mean that the regulatory process becomes much more streamlined, but regulations are more likely to be complied with and products can be brought to market much faster, which improves return on investment and income. “
How to drive impact and change through DevOps
Stephen Magennis, Managing Director of Expleo Technology (UK Technology), explains how impact and change can be driven through DevOps. Read here
Digital twins are another aspect of data science that has made advancements in healthcare, helping to drive the industry’s post-pandemic recovery. Technology enables organizations like the NHS to make decisions faster, using modeling and simulation.
“This technology, which is already in practice in everything from cancer patient journeys to GP surgeries, is one of the most effective ways to quickly advance different scenarios and produce the evidence needed to streamline processes and improve patient outcomes, ”said Frances Sneddon, CTO at Simul8.
‘NHS trusts were using this approach for critical care capacity planning during the pandemic, feeding real-time data from local and national government figures, internal resource planning systems and directly from the floor to the hospital. hospital in a digital twin so they knew exactly how many beds, ventilators and staff would be needed before the peak. It’s been so effective that now these hospitals are building new models to deepen patient journeys and find ways to tackle the much-talked-about challenge of expanding NHS waiting lists.
“Breaking down day-to-day processes into digital information – things like wait times, headcount, resource availability, floor plans, schedules typical of demand increases – is where the science of data contributes to the excellence of healthcare processes. This data provides the blocks on which to build a digital replica – or twin – and it is in this virtual playground that you can experiment and optimize by running simulations.
Towards preventive treatment
The healthcare industry has demonstrated its goal of moving from reactive measures to preventive measures for patients, and is leveraging the capabilities of data science to achieve this.
“The wealth of historical data on healthcare patients, coupled with the constant increase in home monitoring equipment, means that healthcare services have vast stores of structured data,” explained Andre Van Gils, Managing Director. Principal, Global Sales and Marketing at OMRON Healthcare.
“Yet, to date, the overwhelming majority of treatments are reactive, that is, managing an established disease or responding to medical emergencies.
“The mission to take this needle from reactive to preventive is why these growing data stores are so important. With the right data science tools and patient home equipment, we as an industry learn to spot trends and early indicators of conditions, enabling a more preventative approach to care.
“The NHS is currently testing a range of programs using AI and automation in this regard. And we at OMRON have just started a research project with Kyoto University, exploring how AI could predict early-stage cardiovascular disease. We hope that the results will be transferred directly to pre-existing care platforms within the NHS, platforms that we have already built and deployed across the country. “