PROSAIC-DS
Research type
Research Study
Full title
PROSAIC-DS Study (PROState AI in Cancer - Decision Support) Evaluation of the Deontics AI platform for personalised, evidence-based treatment planning in multidisciplinary cancer care: Increasing compliance with national standards of care and streamlining MDTs in prostate cancer.
IRAS ID
304825
Contact name
Danny Ruta
Contact email
Sponsor organisation
Guy's & St Thomas' Foundation NHS Trust R&D Department
Duration of Study in the UK
1 years, 0 months, 1 days
Research summary
Reserach Summary
The NHS has seen escalating costs from the multi-disciplinary team meeting process (“MDTM”) since its introduction in the 1990s. MDTM is a meeting of medical experts (including surgeons, oncologists, nurses, and specialists in cancer, imaging and diagnosis), to discuss and recommend patients’ treatment.Due to the increasing amount of MDTMs, the cost of running them has almost doubled from £88 million to £159 million over four years (2014-2018).
Beyond increasing costs, the over-stretched MDTM process also adds time pressure and work burden on medical staff, reduces time available to discuss complex cases, and does not adequately involve patients in their treatment decision. The NHS long-term plan and NHS England Guidance indicate an urgent need to reform and modernise the MDTM.
Our research is looking into whether artificial intelligence (AI) can be used to streamline MDTMs, making them more cost-efficient and effective.
The AI we are testing is developed by Deontics: a spin out of Cancer Research UK, Oxford University and UCL research. Over two years, we will develop, adapt and test their CE-marked AI Clinical Decision Support Tool (“CDST”) to see whether it can be used in the prostate cancer treatment pathway. The tool we are developing and testing is called PROSAIC-DS.
Our research will assess PROSAIC-DS by comparing its recommendations to past cases (retrospective study) and by implementing the tool in real and current cases (prospective study). All patients whose cases are discussed in MDTM will be eligible to be a part of our study, however, we will require their consent to analyse their data. Patients can consent to standard participation (where we just use their data), or patient portal participation (where we invite them to interact with our patient portal). Note that PROSAIC-DS will NOT make treatment decisions – rather, recommendations which clinicians can choose to act on.
Summary of results
The findings demonstrate the feasibility, safety, effectiveness and potential cost-effectiveness of PROSAIC-DS as an AI clinical decision support system.- PROSAIC-DS can consistently and accurately triage up to 33% of prostate cancer patients away from the MDT (over 96% agreement with an MDT decision);
- The tool was successfully integrated with existing IT systems; Qualitative findings suggest PROSAIC-DS improves the care experience and empowers patients to make better-informed choices;
- The research was inconclusive about whether PROSAIC-DS increased MDT compliance with evidence based best practice;
- The cost-effectiveness evaluation is still being completed with results expected in February 2024.
REC name
London - London Bridge Research Ethics Committee
REC reference
22/LO/0051
Date of REC Opinion
10 Mar 2022
REC opinion
Further Information Favourable Opinion