OpenAlex · Aktualisierung stündlich · Letzte Aktualisierung: 12.03.2026, 04:46

Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.

Abstract PS3-04-19: Health Economic Evaluation of an Artificial Intelligence assisted Breast Cancer Multi Disciplinary Team Meeting/Tumour Board: Preliminary results from a UK Single Centre Simulation Trial

2026·0 Zitationen·Clinical Cancer Research
Volltext beim Verlag öffnen

0

Zitationen

14

Autoren

2026

Jahr

Abstract

Abstract Background: Cancer Multi-Disciplinary Team Meetings (MDTMs) in the UK ensure comprehensive, patient-centred decision-making. They operate at an industrial scale across the National Health Service England (NHSE), with an estimated annual cost of approximately £154.3. Each patient may be discussed upto an average of four times, with a base cost of £428 per patient, increasing to £485 when accounting for opportunity costs. While MDTMs aim to improve outcomes, the substantial financial burden raises questions about efficiency and value. Standard NHS Consultant Programmed Activity (PA) is 4 hours, worth almost £100. The Isle of Wight (IOW) Breast Cancer MDT comprises 2 Oncologists/Equivalent, 3 Surgeons, 1 each of Radiologist, Pathologist, Radiographer, Clinical Nurse Specialist (CNS) and MDT Coordinator, with weekly MDTMs involving 1560 to 2080 cases annually. The OncoflowTM Artificial Intelligence (AI) powered Cancer MDTM CoPilot platform is a class 1 UKCA (UK Conformity Assessed) MHRA (Medicines and Healthcare products Regulatory Agency) registered medical device (RN 32434) that uses proprietary Large Language Model (LLM) based Data Extraction and Treatment Matching. A simulation trial of this intervention vs standard manual practice was conducted to inform a cost benefit and effective analysis. Methods: The Simulation study involved 2 prospective Breast Cancer MDTMs with 10 cases each, matched to similar disease stage (early or metastatic) and complexity (simple/edge/complex). Phase 1 was standard practice and Phase 2 was the OncoFlow intervention. Manual preparation for this 10 case set involved 120 minutes or 1.5 hours of time from 10 IOW MDT members as aforementioned, with role-specific hourly rates applied. OncoFlow was assumed to eliminate labour input, incurring only an annual licence fee of £25,000. A cost-analysis model compared the resource use and associated costs of standard versus OncoFlow AI assisted breast cancer MDTM preparation. Results: Standard manual preparation cost per 10 breast cancer cases taking a total 1.5 hours time was £378.00, equating to £37.80 per case. This included £262.50 for 7 consultants’ time (£25/hour) and £115.50 for 3 other MDT staff (£25 for radiographer, £22 for MDTM coordinator, £30 for CNS). In contrast, OncoFlow’s cost per case was calculated for two scenarios based on MDTM volume, i.e., £16.03 for 1,560 cases/year and £12.02 for 2,080 cases/year, based solely on the annual licence fee. This resulted in savings of £21.77 and £25.78 per case, respectively. Annualised savings were projected from £33,961.20 (1,560 cases) to £53,622.40 (2,080 cases) for 52 weekly breast cancer MDTMs. OncoFlow also reduced preparation time from 13.5 hours per case to negligible levels (∼0.01 hours), yielding an Incremental Cost Effectiveness Ratio (ICER) of £1.91 per hour saved. This implies that for every hour of clinician time saved through automation, the cost difference was £1.91, favouring OncoFlow as a cost-saving intervention. Conclusion: The OncoflowTM AI Cancer MDTM CoPilot significantly reduces the cost burden associated with manual MDTM preparation in breast cancer pathways. The system delivers cost savings of up to £25.78 per case. With an ICER of £1.91 per hour saved, OncoFlow offers a highly cost-effective solution for modernising cancer MDTM workflows, operating at scale. Broader implementation across tumour types and MDTMs could amplify these cost benefits, contributing to more sustainable, efficient NICE (National Institute for Health and Care Excellence) commissioned cancer care delivery across the NHS. Citation Format: J. Tan, P. Garodia, R. Williams, L. Cook, M. Hasanova, A. Kirby, B. Lamb, G. Hunnings, G. Langton, R. Pearson, S. Adomah, O. Ayodele, A. Ghose, A. Maniam. Health Economic Evaluation of an Artificial Intelligence assisted Breast Cancer Multi Disciplinary Team Meeting/Tumour Board: Preliminary results from a UK Single Centre Simulation Trial [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nrPS3-04-19.

Ähnliche Arbeiten