ISCF HDRUK DIH Sprint Exemplar: Using a digital transformation approach to drive improved clinical outcomes for patient with heart failure

Devolution allows us to use the delegated control of our health and social care budget to improve outcomes for our 2.8 million citizens. This, combined with a large cluster of life sciences and digital organisations, strong universities, increasing digital maturity and established city-region leadership makes GM an important place to collaborate with industry to develop and evaluate new products and services.
Cardiovascular disease is a major health priority in GM, with higher mortality and morbidity rates than the UK average. 25,000 people have diagnosed heart failure - just under 1% of our population. During 2015/16 there were 4330 admissions in GM with a primary diagnosis of heart failure, costing over £17,000,000. There is emerging evidence that many of these admissions may be avoided or modified to deliver benefits to patients and to the economy.
Our exemplar sprint will generate better insights about patients’ health by using data from implantable devices already used to treat patients, to feed a new digitally-enabled platform which will detect earlier signs of deterioration. We will use these insights through a new service to prevent hospital admissions, and conduct analyses to detect other patients who are at risk and will potentially benefit from this approach.

Around 2,500 patients in GM with heart failure have implantable devices (pacemakers or defibrillators) which already transmit data onto a cloud platform (including thoracic impedance, arrhythmia burden, percentage of pacing, diurnal heart rate variability and patient activity).
Our industry, academic and NHS partners will use an existing algorithm to detect early deterioration in these patients from the data flows. These insights will drive in near real time into a new operating model for treating heart failure at home. The sprint aims to demonstrate improved outcomes for patients and the health economy, by preventing hospital admissions. We will use the data to demonstrate the efficacy of the intervention, and run machine learning algorithms to improve prediction.
We will use real world evidence and artificial intelligence (AI) to look for missed opportunities for implantable devices (for both therapeutic and diagnostic purposes) and accelerate the deployment of devices to a wider population suitable for these treatments.
Our sprint will deliver a reproducible model for digital transformation to support the life sciences (LS) product lifecycle management processes. City region commissioning in GM (which acts under delegated financial control) is a key partner in our consortium, giving opportunities for rapid scale-up of detected benefits to population and industry benefit.