The PICM risk prediction study - Application of AI to pacing
Research type
Research Study
Full title
Predictive risk algorithm for development of right ventricular pacing induced cardiomyopathy - a step towards personalized pacemaker lead deployment
IRAS ID
333705
Contact name
Christopher Aldo Rinaldi
Contact email
Sponsor organisation
R&D Guys and St Thomas's NHS Foundation Trust
Duration of Study in the UK
2 years, 5 months, 1 days
Research summary
Life-threatening slow heart rhythms are treated with pacemakers which prevent injury due to syncope, restore quality of life and reduce mortality. Pacemakers are devices which pace the heart internally in the lower chamber of the heart with the use of pacing leads which are connected to a pacing device in a pocket underneath the skin. A second option are leadless pacemakers – the pacing device itself functions as a pulse generator and is deployed directly in the heart chamber. It paces the heart without the use of leads.
It has been noted that patients who receive pacemakers can develop heart failure for which the pacemaker itself is the culprit of heart function deterioration – this is called pacemaker induced cardiomyopathy (PICM). PICM has been associated with an increase in hospital admissions due to heart failure and is correlated with high morbidity and mortality.
Prior studies have shown that pacing and patient related factors can contribute to the development of PICM. Moreover, newer pacing techniques have been developed which have shown lower rates of PICM, such as conduction system pacing (CSP) and biventricular pacing (BiVP) with promising results, but it has not been established yet which patient group would benefit from the new pacing modes. The aim of the study would be the pre-procedural identification of patients at high risk of PICM. Our study would be the first to look for the impact of personal risk factors in relation to patient selection for any given pacing method with the help of machine learning. The goal of this study is to optimise patient’s care through the development of a machine learning algorithm which can predict development of PICM in patients who require pacing and offering them alternativepacing methods up-front whilst sparing them from future interventions in form of pacemaker upgrades due to heart failure.REC name
North West - Greater Manchester South Research Ethics Committee
REC reference
24/NW/0145
Date of REC Opinion
1 Jul 2024
REC opinion
Further Information Favourable Opinion