PROSAIC-DS Study (PROState AI in Cancer - Decision Support) (PROSAIC-DS)

PROSAIC-DS (PROState AI in Cancer - Decision Support): Evaluation of the Deontics AI Platform for Evidence-based Treatment Planning in Multidisciplinary Cancer Care: Increasing Compliance and Streamlining MDTs in Prostate Cancer

King's College Hospital NHS Trust, King's College London, Deontics Limited, Somerset NHS Foundation Trust, Prostate Cancer UK

Around 375,000 cancers are diagnosed in the UK annually, with this figure expected to reach 500,000 by 2035. As the number of different cancer treatment options and our scientific understanding continue to grow rapidly, it can be difficult for clinicians to keep up-to-date with best practice, causing unjustified variations in the quality of care and clinical outcomes for patients. Currently, when a patient has been referred to and seen by a clinician, their treatment is then discussed in a Multi-Disciplinary Team Meeting (MDTM). MDTM is a meeting of medical experts, including Surgeons, Oncologists, Nurses, and specialists in cancer, imaging and diagnosis. This is the case even if a treatment decision is straightforward. A nationwide review published by CRUK in 2017 highlighted the demands on cancer teams and the MDTM process: Increased caseloads are causing dramatic increases in the time spent by clinicians in MDTMs, leading to an unsustainable rise in costs: the cost in England has increased from £88m to £159m in 4 years; There is not enough time in the MDTM to discuss complex cases; There is a failure to involve patients in the decision-making process: around 75% of patients feel their views are unrepresented in MDTMs; In our study we are looking at the potential of technology - particularly Clinical Decision Support Systems (CDSS) - to improve MDTM decision making. Deontics has a CE marked AI-based CDSS that integrates individual patient data and preferences with evidence-based clinical guidelines. This dynamically and transparently generates best-practice, individualised treatment recommendations which can help determine treatment. Deontics' AI tool has already been shown to provide personalised recommendations concordant with UK best practice while incorporating patient values, and can be used to safely triage less complex patients straight to treatment with minimal clinical oversight. Our project partners with Deontics to develop PROSAIC-DS - A CDSS for prostate cancer.

The PROSAIC-DS tool will take the variables and produce a suggested outcome. It will supply supporting evidence and best practice for its recommendations

The % of patients the PROSAIC-DS tool can appropriately triage away non-complex Prostate Cancer cases from the MDTM with appropriate treatment plans as directed by approved guidelines (EAU, BAUS, NICE, AUA).

Evaluation of PROSAIC-DS as a member of the MDTM via the impact of live PROSAIC-DS recommendations on MDTM decision concordance with approved guidelines (EAU, BAUS, NICE, AUA) on randomised patients discussed in the MDTM. This is measured through the difference in level of concordance between the MDTM with PROSAIC-DS switched off and the MDTM with PROSAIC-DS on when less complex cases (ones triaged away) are excluded.

Estimate the financial savings that PROSAIC-DS brings by triaging non-complex cases away from the MDTM.

We will use qualitative methods, and data capture methods including self-administered questionnaires, focus groups, semi-structured interviews and video analysis, to explore patient and staff views about, including concerns and satisfaction with, the use of AI technology to support clinical decisions in prostate cancer, both prior to their engagement with PROSAIC-DS, during and after deployment of the tool of the technology to patients.

Inclusion Criteria: All patients referred to the GSTT and KCH Prostate MDT meetings where sufficient information is available for the MDT to make a treatment decision (approximately 40-50 per week) will be eligible for the study. Exclusion Criteria: If data available for patients is not adequate to make any treatment decisions they will be excluded. Non-consenting patients will be excluded.

Knight SR, Cao KN, South M, Hayward N, Hunter JP, Fox J. Development of a Clinical Decision Support System for Living Kidney Donor Assessment Based on National Guidelines. Transplantation. 2018 Oct;102(10):e447-e453. doi: 10.1097/TP.0000000000002374.

Taylor C, Atkins L, Richardson A, Tarrant R, Ramirez AJ. Measuring the quality of MDT working: an observational approach. BMC Cancer. 2012 May 29;12:202. doi: 10.1186/1471-2407-12-202.

Munro AJ. Multidisciplinary Team Meetings in Cancer Care: An Idea Whose Time has Gone? Clin Oncol (R Coll Radiol). 2015 Dec;27(12):728-31. doi: 10.1016/j.clon.2015.08.008. Epub 2015 Sep 11. No abstract available.

Patkar V, Acosta D, Davidson T, Jones A, Fox J, Keshtgar M. Cancer multidisciplinary team meetings: evidence, challenges, and the role of clinical decision support technology. Int J Breast Cancer. 2011;2011:831605. doi: 10.4061/2011/831605. Epub 2011 Jul 17.

Miles A, Chronakis I, Fox J, Mayer A. Use of a computerised decision aid (DA) to inform the decision process on adjuvant chemotherapy in patients with stage II colorectal cancer: development and preliminary evaluation. BMJ Open. 2017 Mar 24;7(3):e012935. doi: 10.1136/bmjopen-2016-012935.

Patkar V, Acosta D, Davidson T, Jones A, Fox J, Keshtgar M. Using computerised decision support to improve compliance of cancer multidisciplinary meetings with evidence-based guidance. BMJ Open. 2012 Jun 25;2(3):e000439. doi: 10.1136/bmjopen-2011-000439. Print 2012.

Patkar V, Hurt C, Steele R, Love S, Purushotham A, Williams M, Thomson R, Fox J. Evidence-based guidelines and decision support services: A discussion and evaluation in triple assessment of suspected breast cancer. Br J Cancer. 2006 Dec 4;95(11):1490-6. doi: 10.1038/sj.bjc.6603470. Epub 2006 Nov 21.

Peleg M, Fox J, Patkar V, Glasspool D, Chronakis I, South M, Nassar S, Gaglia JL, Gharib H, Papini E, Paschke R, Duick DS, Valcavi R, Hegedus L, Garber JR. A Computer-Interpretable Version of the AACE, AME, ETA Medical Guidelines for Clinical Practice for the Diagnosis and Management of Thyroid Nodules. Endocr Pract. 2014 Apr;20(4):352-9. doi: 10.4158/EP13271.OR.

Bury J, Hurt C, Roy A, Cheesman L, Bradburn M, Cross S, Fox J, Saha V. LISA: a web-based decision-support system for trial management of childhood acute lymphoblastic leukaemia. Br J Haematol. 2005 Jun;129(6):746-54. doi: 10.1111/j.1365-2141.2005.05541.x.

Tural C, Ruiz L, Holtzer C, Schapiro J, Viciana P, Gonzalez J, Domingo P, Boucher C, Rey-Joly C, Clotet B; Havana Study Group. Clinical utility of HIV-1 genotyping and expert advice: the Havana trial. AIDS. 2002 Jan 25;16(2):209-18. doi: 10.1097/00002030-200201250-00010.

Walton RT, Gierl C, Yudkin P, Mistry H, Vessey MP, Fox J. Evaluation of computer support for prescribing (CAPSULE) using simulated cases. BMJ. 1997 Sep 27;315(7111):791-5. doi: 10.1136/bmj.315.7111.791.

Patkar V, Fox J. Clinical guidelines and care pathways: a case study applying PROforma decision support technology to the breast cancer care pathway. Stud Health Technol Inform. 2008;139:233-42.

https://www.cancerresearchuk.org/sites/default/files/full_report_meeting_patients_needs_improving_the_effectiveness_of_multidisciplinary_team_meetings_.pdf

Meeting Patients Needs: Improving the effectiveness of Multidisciplinary Team Meetings in Cancer Services. 2018

https://www.england.nhs.uk/wp-content/uploads/sites/6/2018/10/Transforming-MDTM-Martin-Gore-August-2017.pdf

Transforming Multidisciplinary Team Meetings (MDTMs): Report by Prof Martin Gore (2017) for NHS England

https://www.england.nhs.uk/wp-content/uploads/2020/01/multi-disciplinary-team-streamlining-guidance.pdf