This subtheme aims to use digital technology and artificial intelligence-led applications to develop tools to improve effectiveness and efficiency in translating precision or stratified medicine into practice. We have developed an IT-enabled system for heart failure patients to support an integrated, patient-centred and proactive management of their conditions from home. This model has been well received, and the technology licensed to a commercial company for potential adaptation in the NHS and outside the UK.
Building on existing large-scale UK electronic health records, we have quantified the increasing burden of multimorbidity, and described management of patients with specific chronic conditions and their prognosis.
We continue to use this unique UK data resource particularly to develop novel, data-driven approaches to help understand how multimorbidity develops over time, and what clusters of chronic conditions matter most. Findings from this work could help determine the appropriate management and development of relevant interventions to improve prognosis in those with long-term multiple conditions.
These research activities have helped to inform how we will address the lack of good evidence surrounding the management of blood pressure in older patients or in the presence of multiple chronic diseases, particularly when blood pressure is not very high.
We are currently designing the ATEMPT Pilot Trial, a study to test innovative remote trial procedures in preparation for conducting a substantive international trial to investigate the effects of taking different numbers of blood pressure-lowering medications (the ‘intervention’) on cardiovascular health outcomes and safety. The aims of this pilot study are:
- To estimate the effectiveness of the intervention on blood pressure and change in prescribed drugs;
- To assess the acceptability and tolerability of the intervention (using patient-reported outcomes) and to rule out any major excess harms (risk of serious adverse events);
- To test the feasibility of the main components of the trial, namely: participant recruitment; randomisation; delivery of treatment and remote assessment of trial outcomes; and to obtain information about resource requirements for the main trial.
We are conducting this pilot study in the UK and in Norway, and we will be recruiting approximately 200 individuals aged 65 years or over with multiple conditions or taking multiple medications.
Achievements to date
Using large-scale, contemporary routine clinical care data, we quantified the burden of multi-morbidity in patients with long-term chronic conditions (e.g. patients with cardiovascular disease and heart failure) and described their care and prognosis; publications in high-impact journals; findings were presented at major conferences, and were widely reported in the media.
We applied machine learning approaches to predict unscheduled admissions, demonstrating that such an approach is a better predictor than existing models; the study was used as an exemplar for the application of artificial intelligence in large-scale health data analytics.
In Support-HF 2, we developed a well-received IT-enabled system to support the management of heart failure by healthcare professionals and the patients from home. This technology-enabled support system has been licensed to industry for wider application.
The IT-enabled system developed in Support-HF 2 is being used in the design of an acceptable, feasible, affordable and sustainable trial that aims to identify the safety and efficacy of blood pressure-lowering treatment in the elderly and patients with multimorbidity.
Relevant publications
SUPPORT-HF 2 Investigators and Committees. Home monitoring with IT-supported specialist management versus home monitoring alone in patients with heart failure: Design and baseline results of the SUPPORT-HF 2 randomized trial. Am Heart J. 2019 Feb;208:55-64. https://doi.org/10.1016/j.ahj.2018.09.007.
Conrad N, et al. Temporal trends and patterns in mortality after incident heart failure: A longitudinal analysis of 86 000 individuals. JAMA Cardiol. 2019. https://doi.org/10.1001/jamacardio.2019.3593.
Conrad N, et al. Diagnostic tests, drug prescriptions, and follow-up patterns after incident heart failure: A cohort study of 93,000 UK patients. PLoS Med. 2019 May 21;16(5):e1002805. https://doi.org/10.1371/journal.pmed.1002805.
Tran J, et al. Patterns and temporal trends of comorbidity among adult patients with incident cardiovascular disease in the UK between 2000 and 2014: A population-based cohort study. PLoS Med. 2018 Mar 6;15(3):e1002513. https://doi.org/10.1371/journal.pmed.1002513.
Conrad N, et al. Temporal trends and patterns in heart failure incidence: a population-based study of 4 million individuals. Lancet. 2018 Feb 10;391(10120):572-580. https://doi.org/10.1016/S0140-6736(17)32520-5.
Rahimian F, et al. Predicting the risk of emergency admission with machine learning: Development and validation using linked electronic health records. PLoS Med. 2018 Nov 20;15(11):e1002695. https://doi.org/10.1371/journal.pmed.1002695.
Principal Investigators
Professor Kazem Rahimi, Professor Richard Hobbs
Contact
For further information visit Deep Medicine and SUPPORT-HF or contact Abel Perez abel.perezcrespillo@georgeinstitute.ox.ac.uk or Catherine Taylor catherine.taylor@phc.ox.ac.uk.