Diaverum develops breakthrough AI model to deliver step-change in Vascular Access (VA) thrombosis prevention
Diaverum, a leading global renal care service provider, has developed an artificial intelligence model to support the company’s physicians and nurses predict with a high degree of accuracy, episodes of vascular access thrombosis among haemodialysed patients. Simulations using Diaverum’s historical patient data predicted an average of 75% of actual cases that were not detected by best-in-class clinical assessments and monitoring systems.
Vascular Access (VA) thrombosis is a major factor of suffering and increased mortality for chronic haemodialysis patients, with incidence ranging between 0.11 to 0.5 episodes per patient every year. It accounts for a significant increase of the total cost of care for these patients, contributing to the unsustainable trajectory of growing expenditure and disease burden impacting national healthcare systems around the world.
Dimitris Moulavasilis, Diaverum’s CEO, said: “VA management is central to our clinical strategy. We are delighted to be announcing today, a breakthrough innovation that will deliver a step-change in our ability to predict and take preventive measures to avoid VA thrombosis episodes among our dialysis patients. It’s a big win for everyone – better digital tools and predictive analytics insights for our healthcare professionals; improved medical outcomes for our patients; and lower cost of care for payors and national health systems.”
Diaverum’s VA model follows the principles of human-centric, explainable, and responsible AI. It uses personalised input variables comprising dialysis treatment data, lab tests results and demographics, predicting if the patient will suffer from a thrombotic event one week before the episode takes place. The AI prediction is presented to the nephrologists together with a set of explainable insights, empowering them to offer preventive personalised care to maintain the patient’s vascular access survival.
The new VA AI model is integrated into the company’s digitalised clinical workflows and interfaces with its digital infrastructure, including its proprietary renal information platform, d.CARE, and Treatment Guidance System (TGS).
Starting with its operations in Saudi Arabia, Portugal and Spain, which care for approximately 12.000 renal patients, the company’s ambition is to roll out the model to its entire network of 452 clinics in 24 countries, over the next 18 months.
Dr Fernando Macário, Diaverum’s Chief Medical Officer, commented: “Diaverum’s renal care model is built around safety-oriented policies and procedures, standardised holistic interventions, strong clinical governance and digitalised workflows to deliver medical outcomes that matter for our patients. With AI, physicians will have better predictive tools, nurses will come closer to the patients, processes will be more effective and patients will be better treated. Data scientists will be a new subset of healthcare professionals, members of a multidisciplinary team, that will also need to interface with patients and other healthcare professionals, to ensure our focus is always on delivering a personalised, life-enhancing renal care.”
According to Zoltan Szepesi, Diaverum’s Chief Transformation Officer, “today’s announcement is a milestone in a three-year journey to convert all our know-how into a proprietary digital platform, so that we can provide the most efficient, standardised, high-quality & highly scalable dialysis service in the industry. Looking ahead, Diaverum is building its own AI development factory to train, validate, deploy and monitor a series of AI models that will address important unmet clinical needs. Our ambition is to have an AI-empowered clinical workforce in all our clinics, improving outcomes that really matter to our patients, like the survival of their vascular access.”
To learn more about the company’s digital transformation and VA AI model, join a live announcement webinar hosted by Diaverum’s CEO, Dimitris Moulavasilis, and CMO, Fernando Macário.