PredictAF: From data to diagnosis

  • Research type

    Research Study

  • Full title

    ‘From data to diagnosis’: Identification of patients with paroxysmal atrial fibrillation (PAF) using computational analysis of sinus rhythm electrocardiograms.

  • IRAS ID

    302277

  • Contact name

    Kamalan Jeevaratnam

  • Contact email

    k.jeevaratnam@surrey.ac.uk

  • Sponsor organisation

    University of Surrey

  • Duration of Study in the UK

    2 years, 11 months, 10 days

  • Research summary

    Atrial Fibrillation (AF) is a type of heart condition that is characterized by abnormal heartbeats or arrhythmia. AF is a common condition, but the diagnosis of AF requires long-term patient monitoring and extensive analysis of ECG data. This is often impractical within the NHS as there isn’t sufficient resources. Typically, confirmation of an AF diagnosis would require referral to a cardiac specialist which takes time and many patients remain undiagnosed. It is estimated that 37% of AF patient remain undiagnosed thus at risk to fatal stroke events.
    We have developed additional diagnostic screening tools (algorithms) which can be embedded within a standard ECG device to provide GPs with a degree certainty on whether patients need urgent referral to a cardiologist for an intervention or can be managed at the primary care setting.

    We have proposed our ideas to GP practices and clinical directors of a number of primary care trust (Surrey and Cambridge) who are supportive of this idea. In their opinion, developing the method to rapidly detect the paroxysmal atrial fibrillation from normal sinus rhythm ECG will enable the healthcare system to significantly improve the methods of managing AF patients and reduce referral burdens.

  • REC name

    London - Chelsea Research Ethics Committee

  • REC reference

    22/PR/0513

  • Date of REC Opinion

    10 Jun 2022

  • REC opinion

    Further Information Favourable Opinion