Artificial Intelligence in Healthcare: Smarter Care Delivery

[ad_1]

Mike Wright, business partner for innovation, CW Innovation, Chelsea and Westminster Hospital NHS Foundation Trust, talks about the use of AI at the Trust and stresses the need for a step-by-step approach.

Most of us are already unknowingly interacting with AI on a daily basis; most commonly on our email and social media platforms and with chatbots and mobile banking. Artificial intelligence is increasingly being used to support the selection of candidates for job interviews, to detect fraud in the payment of insurance claims and to determine eligibility for financial products such as loans. In short, artificial intelligence is a factor in many aspects of our daily life.

In November 2018, then-Secretary of Health Matt Hancock said that artificial intelligence “will play a crucial role in the future of the NHS.” I think it will, over time, but not in the near future because, despite its already widespread use in other parts of society, AI is still in its infancy in the healthcare sector. At Chelsea and Westminster Hospital NHS Foundation Trust, a Global Digital Exemplar and emerging leader in innovation and discovery, we are carefully leveraging the benefits of AI.

AI often evokes ethical concerns about privacy and surveillance, bias and discrimination, and perhaps the deepest and most difficult area is the role of human judgment. With this front and center approach, our step-by-step approach is to identify the areas where we believe AI will have the greatest impact on patient outcomes and then work with the right partners to jointly develop and rigorously test the technology against. existing practices to ensure favorable results without prejudice.

We are currently exploring the use of AI in clinical and back-office functions. In the clinical setting, we are testing and scaling Skin Analytics’ innovative AI DERM (Deep Ensemble for Recognition of Malignancy) algorithm. This can identify skin cancers from dermoscopic images taken using a smartphone and attachment and has been shown to be more accurate than dermatologists at identifying some skin cancers. We have completed the recruitment of 700 patients for an exciting prospective study to evaluate the impact of DERM on the allocation of health care resources for the diagnosis of skin cancers, also evaluating patient acceptability. Pending these exciting results and a successful grant application, we hope to implement DERM as a decision support tool in our standard care pathway.

In the back office, we are investigating how AI can support the burden of handling routine requests to HR and Procurement functions, allowing staff to focus on higher value-added activities such as employee training and development at the Trust. . One of the benefits of this type of machine learning is that we can provide an always-on service, allowing both our staff and patients to access the information they need, regardless of shifts or time of day.

There is no doubt that the COVID-19 pandemic has rapidly accelerated the use of digital and AI solutions. One example is the algorithms we have developed, combining our clinical expertise with Sensyne Healths’ artificial intelligence and machine learning know-how, to process patient data incredibly quickly and provide clinicians with insights and predictions about which they can act immediately.

The first algorithm called SYNE-COV has recently gained UKCA brand status. SYNE-COV predicts what is likely to happen to a COVID positive patient; in particular, their risk of needing ICU care or invasive mechanical ventilation, based on vital signs, test results, and other useful data. This helps doctors intervene earlier and a patient who may have ended up in intensive care can be treated effectively before they deteriorate further.

The second algorithm, SYNE-OPS-1, predicts overall resource requirements, helping to maximize available resources by identifying problems, such as a shortage of beds or fans, before they become a problem.

Earlier this year, the UK Parliamentary Office for Science and Technology released its AI and Health Research Briefing on the use of AI in the UK’s healthcare system, acknowledging that although artificial intelligence is not yet widely used within the NHS, there are multiple artificial intelligence products at various stages of testing and evaluation. We are thrilled to be working on some of these pioneering applications and to play a leading role in establishing the UK as a champion of digital technology in the healthcare sector.

The opportunities are endless, but what is critical is the approach. Our data warehouse and our growing use of data mining tools and data science techniques are absolutely delivering smarter management and care delivery. They enable doctors and managers to get correct diagnoses the first time to first identify patients with deteriorating health.

By constantly evaluating and exploring new solutions in the use of AI with partners and staff, we will continue to lead our journey, being cautiously optimistic, while ensuring the best outcomes for patients both now and in the future.

[ad_2]