Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 23;11(4):434-444.
doi: 10.1093/ehjqcco/qcae085.

Cost-effectiveness of a novel AI technology to quantify coronary inflammation and cardiovascular risk in patients undergoing routine coronary computed tomography angiography

Apostolos Tsiachristas  1 , Kenneth Chan  2 , Elizabeth Wahome  2 , Ben Kearns  3 , Parijat Patel  2 , Maria Lyasheva  2 , Nigar Syed  4 , Sam Fry  4 , Thomas Halborg  2 , Henry West  2   5 , Edward Nicol  6   7 , David Adlam  8   9 , Bhavik Modi  8   9 , Attila Kardos  10 , John P Greenwood  11   12 , Nikant Sabharwal  2 , Giovanni Luigi De Maria  2 , Shahzad Munir  13 , Elisa McAlindon  13 , Yogesh Sohan  4 , Pete Tomlins  4 , Muhammad Siddique  4 , Cheerag Shirodaria  2   4 , Ron Blankstein  14 , Milind Desai  15 , Stefan Neubauer  2 , Keith M Channon  2 , John Deanfield  16 , Ron Akehurst  3 , Charalambos Antoniades  2 ; ORFAN Consortium
Collaborators, Affiliations

Cost-effectiveness of a novel AI technology to quantify coronary inflammation and cardiovascular risk in patients undergoing routine coronary computed tomography angiography

Apostolos Tsiachristas et al. Eur Heart J Qual Care Clin Outcomes. .

Abstract

Aims: Coronary computed tomography angiography (CCTA) is a first-line investigation for chest pain in patients with suspected obstructive coronary artery disease (CAD). However, many acute cardiac events occur in the absence of obstructive CAD. We assessed the lifetime cost-effectiveness of integrating a novel artificial intelligence-enhanced image analysis algorithm (AI-Risk) that stratifies the risk of cardiac events by quantifying coronary inflammation, combined with the extent of coronary artery plaque and clinical risk factors, by analysing images from routine CCTA.

Methods and results: A hybrid decision-tree with population cohort Markov model was developed from 3393 consecutive patients who underwent routine CCTA for suspected obstructive CAD and followed up for major adverse cardiac events over a median (interquartile range) of 7.7(6.4-9.1) years. In a prospective real-world evaluation survey of 744 consecutive patients undergoing CCTA for chest pain investigation, the availability of AI-Risk assessment led to treatment initiation or intensification in 45% of patients. In a further prospective study of 1214 consecutive patients with extensive guidelines recommended cardiovascular risk profiling, AI-Risk stratification led to treatment initiation or intensification in 39% of patients beyond the current clinical guideline recommendations. Treatment guided by AI-Risk modelled over a lifetime horizon could lead to fewer cardiac events (relative reductions of 11%, 4%, 4%, and 12% for myocardial infarction, ischaemic stroke, heart failure, and cardiac death, respectively). Implementing AI-Risk Classification in routine interpretation of CCTA is highly likely to be cost-effective (incremental cost-effectiveness ratio £1371-3244), both in scenarios of current guideline compliance, or when applied only to patients without obstructive CAD.

Conclusions: Compared with standard care, the addition of AI-Risk assessment in routine CCTA interpretation is cost-effective, by refining risk-guided medical management.

Keywords: Coronary CT angiography; Coronary artery disease; Cost-effectiveness analysis; Inflammation.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: S.F., N.S., P.T., Y.S., and M.S. are employees of Caristo Diagnostics Ltd. S.N., K.M.C., and C.A. are founders, shareholders, and directors of Caristo Diagnostics Ltd, a CT-image analysis company. C.A. is the inventor of patents US10695023B2, US11393137B2, GB2018/1818049.7, GR20180100490, and GR20180100510. S.N. and K.M.C. are co-inventors of patent US10695023B2. These are licensed to Caristo Diagnostics by the University of Oxford. A.T. has received research funding from NIHR Oxford Health Biomedical Research Center, NHS AI award, and NIHR Applied Research Collaboration Oxford. A.K. has received grants from Lantheus Medical USA, and honoraria from Bracco UK Ltd/Philips Medical Ltd. B.M. has received honoraria from Chiesi, Sanofi, Novartis, and Boston Scientific. C.A. has a leadership role in British Atherosclerosis Society, EU Marie Curie Fellowship committee, and received honoraria from Amarin, Covance, and consulting fees from Slience Therapeutics. D.A. has a leadership role in Spontaneous Coronary Artery Dissection Study group, inventor of patents related to cardiac assist device (EP3277337A1, PCT/GB2017/050877) and received grant support from AstraZeneca, Abbott Vascular, and consulting fees from General Electric Inc. E.M. has received research support from NHS AI award. E.N. has a leadership role in Society of Cardiac CT and has received consulting fees from Caristo Diagnostics. J.D. has a leadership role and received consulting fees from Novo Nordisk, and received honoraria from Amgen, Boehringer Ingelheim, Merck, Pfizer, Aegerion, Novartis, Sanofi, Takeda, Novo Nordisk, and Bayer. J.R. has a leadership role in Heart and Lung Imaging LTD, and received consulting fees from NHSX and HeartFlow, and honoraria from Sanofi, Aidence, 4-C. K.M.C. has received consulting fees from Caristo Diagnostics, M.D. has received consulting fees from Bristol Myers Squibb, Tenaya Therapeutics, and VizAL, and participated on advisory board for Caristo Diagnostics. N.S. has received royalties from patent (PCT/GB2015/052359). R.A. is an employee of Lumanity, a consultancy company that has been contracted to provide advice on the conduct and reporting of this study. R.B. has a leadership role in Society of Cardiovascular Computed Tomography, has received grants from Amgen, Novartis, and Nanox AI, and consulting fees from Caristo Diagnostics and Heartflow. All other authors declare no competing interests.

Figures

Graphical Abstract
Graphical Abstract
Figure 1
Figure 1
Decision tree for patient undergoing coronary computed tomography angiogram for suspected coronary artery disease. (A) Proposed clinical pathway of additional AI-Risk Classification to standard care. (B) Decision tree for standard care with CCTA assessment of presence/absence of obstructive CAD and clinical risk factor stratification. (C) Decision tree after addition of AI-Risk assessment. CAD, coronary artery disease; CABG, coronary artery bypass grafting; CCTA, coronary computed tomography angiogram; and PCI, percutaneous coronary intervention.
Figure 2
Figure 2
Markov model illustrating transition of health state every 3 months cycle.
Figure 3
Figure 3
Estimated major adverse cardiac events in a cohort of 5000 simulated patients over a lifetime horizon. Data points indicate the total number of events, and bars represent 95% confidence intervals. The differences between standard care and AI-Risk guided management are expressed in absolute reduction of events (% reduction).
Figure 4
Figure 4
(A) Cost-effectiveness plane demonstrating the uncertainty around the incremental cost of £693 and QALY of 0.21 over 1000 sets of probabilistic sensitivity analysis, and (B) cost-effectiveness acceptability curve of AI-Risk assessment in addition to standard care compared with standard care alone assuming AI-Risk model price of £700 intercepting at an ICER of £3244. ICER, incremental cost effectiveness ratio; QALY, quality adjusted life years.
See this image and copyright information in PMC

References

    1. Luengo-Fernandez R, Walli-Attaei M, Gray A, Torbica A, Maggioni AP, Huculeci R et al. Economic burden of cardiovascular diseases in the European Union: a population-based cost study. Eur Heart J 2021, 144, 2014, 7, 276–284, 2003, 114, 485–494, 2007, 5, 5, 2023;44:4752–4767. 10.1093/eurheartj/ehad583 - DOI - PMC - PubMed
    1. Hippisley-Cox J, Coupland C, Brindle P. Development and validation of QRISK3 risk prediction algorithms to estimate future risk of cardiovascular disease: prospective cohort study. BMJ 2017;357:j2099. 10.1136/bmj.j2099 - DOI - PMC - PubMed
    1. Visseren FLJ, Mach F, Smulders YM, Carballo D, Koskinas KC, Back M et al. 2021 ESC guidelines on cardiovascular disease prevention in clinical practice. Eur Heart J 2021;42:3227–3337. 10.1093/eurheartj/ehab484 - DOI - PubMed
    1. NICE . Cardiovascular Disease: Risk Assessment and Reduction, Including Lipid Modification NICE Guideline [NG238]. Available from: https://www.nice.org.uk/guidance/ng238 (accessed 17 October 2024).
    1. Antonopoulos AS, Sanna F, Sabharwal N, Thomas S, Oikonomou EK, Herdman L et al. Detecting human coronary inflammation by imaging perivascular fat. Sci Transl Med 2017;9:398. 10.1126/scitranslmed.aal2658 - DOI - PubMed