Pre-symptomatic detection of deterioration in CAR-T therapy (PREDDICT)

  • Research type

    Research Study

  • Full title

    Pilot study to develop machine learning algorithms for the pre-symptomatic detection of deterioration in patients undergoing chimeric antigen receptor T-cell therapy

  • IRAS ID

    340847

  • Contact name

    David Brealey

  • Contact email

    d.brealey@nhs.net

  • Sponsor organisation

    University College London Hospital Trust

  • Duration of Study in the UK

    2 years, 11 months, 29 days

  • Research summary

    Chimeric Antigen Receptor T cells (CAR-T) are genetically modified T cells that have revolutionised the management of B-cell malignancies. However, the treatment is associated with significant toxicities, particularly hyper-inflammation manifest as cytokine release syndrome (CRS), immune effector cell-associated neurotoxicity syndrome (ICANS), and sepsis. ~20% of patients require ICU admission for these complications, driving mortality, morbidity and costs. Early recognition and intervention improve outcomes.

    We hypothesise that patients can be identified before they exhibit symptoms of these hyper-inflammatory syndromes by analysing subtle changes in physiological waveforms such as the ECG. Previously, we and others have shown that inflammatory states (surgery and sepsis), are associated with loss of variability in heart rate and respiratory rate.

    Using a novel wireless wearable monitor attached to CAR-T patients, our primary objective is to continuously analyse subtle changes in waveforms, creating algorithms that ultimately predict the onset of these hyperinflammatory syndromes before symptoms develop. This pilot study could lead to dynamic risk stratification, identifying not only those likely to deteriorate and eligible for pre-symptomatic intervention, but also those at low-risk and thus eligible for early discharge. We also want to understand whether wireless monitoring combined with continuous telemonitoring has the capability to recognise clinical deterioration, using classic physiological parameters and whether this acceptable/useful to staff and patients.

  • REC name

    London - Bromley Research Ethics Committee

  • REC reference

    24/LO/0490

  • Date of REC Opinion

    17 Jul 2024

  • REC opinion

    Further Information Favourable Opinion