P839Lifetime cost-effectiveness of diagnostic artificial intelligence tool for evaluating individuals with stable chest pain. The co-operative ARTICA registry database

Abstract

Abstract Background Non-invasive cardiac imaging testing has been often favored as an initial test for symptomatic patients with at least intermediate pre-test likelihood (pt-lk) of obstructive CAD. Despite this condition, uncertainty remains regarding the optimal testing strategies. It is known that intelligence applied with automatic decision support system (AI DSS) is able to correctly identify absence of significant CAD versus standard care (SD) in patients with stable chest pain (SCP). No evidence of long-term cost-effectiveness about AI DSS has been published in this setting. Purpose The aim is to determine the cost-effectiveness of AI DSS when applied to individuals without known CAD presenting with stable chest pain syndrome. Methods 1725 subjects, 982 males, age 61±12 years, with SCP were referred for clinical evaluation by human standard care (SD) and AI DSS administration during same day visit on a 2 years period. Exercise treadmill test (ETT), coronary tomographic angiography (CTA), invasive coronary angiography (ICA), stress echocardiography (SE)/gated myocardial perfusion scintigraphy (gMPS) and follow up/no tests (FNT) alone and combined strategies were analyzed. For the post-diagnosis follow up period of 16±3 months, we employed a Markov model based on 1-year cycle to account for outcomes for those correctly diagnosed with CAD. All subjects performed CTA to verify presence of CAD. CAD was defined as ≥70% stenosis in at least one major epicardial coronary artery vessels. Monte Carlo simulation was performed to derive mean values for costs and QALYs at different CAD prevalence of 15%, 50% and 80%. Results Data from ARTICA registry about lifelong costs based upon different diagnostic strategies in subjects with 15%, 50% and 80% CAD pt-lk are shown in Table. Lifelong costs related to strategies FNT (€) ETT-SE/gMPS-ICA (€) SE/gMPS-ICA (€) CTA-ICA (€) CTA-SE/gMPS-ICA pt-lk CAD 15% AI DSS 350 8,250 8,850 10,450 11,020 SD 1,015 11,100 12,715 12.215 12,215 pt-lk CAD 50% AI DSS 1,610 17,375 19,540 20,410 20,110 SD 1,855 19,650 21,340 22,950 22,115 pt-lk CAD 80% AI DSS 2,910 28,210 30,875 31,215 31,765 CD 4,110 32,715 34,815 35,755 35,660 Conclusion Data from ARTICA registry demonstrate that automatic use of AI DSS result in improved costs and enhanced effectiveness when compared with human SD in subjects with stable chest pain.