The Use of Artificial Intelligence-Enhanced Electrocardiograms in the Chest Pain Clinic to Risk Stratify Patients, Provide Rapid Reassurance and Enable a Low-Cost Clinical Pathway

Our group has been at the forefront of developing AI‐ECG models that are actionable,biologically plausible and explainable, with the aim of fostering clinical trust andmaximising their potential for integration into routine clinical care. Recently, wedeveloped the artificial‐intelligence risk‐estimation (AIRE) platform, comprising aseries of AI‐ECG models capable of predicting time‐to‐mortality, and furtherdisease‐specific AIRE models encompassing a broad range of future cardiovascularconditions from a single 12‐lead ECG.The AIRE platform was developed using the Beth Israel Deaconess Medical Centre (BIDMC)dataset, comprising more than 1.1 million ECGs from a secondary care population inBoston, USA. The tool has been externally validated across five large internationalcohorts from the USA, UK, and Brazil, encompassing diverse demographics, a range ofbaseline cardiovascular risks, including both primary and secondary care, as well asvolunteer populations.AIRE generates patient‐specific survival curves using data from a single 12‐lead ECG andcan predict time‐to‐death. In our validation studies, AIRE demonstrated strong predictiveperformance for cardiovascular (CV) mortality, achieving a concordance‐index (c‐index) of0.844 (95% confidence interval, 0.839‐0.849). This outperformed current predictive modelsbased on demographic data and traditional risk factors alone, which had a c‐index of0.733 (0.726‐0.740).We believe the rapid access chest pain clinic provides an ideal setting in which toevaluate the clinical translation of this validated AI‐ECG technology. Risk prediction iscentral to clinical‐decision making in this population, making it well‐suited forassessing the added value of AI‐enhanced tools. In low‐risk cohorts such as our proposedstudy population, the high negative predictive value of AIRE offers the potential toconfidently reassure patients at the lowest risk, in line with national guidelines.Importantly, we have demonstrated that AIRE can stratify risk even among patients whoseECGs are labelled as normal by clinicians. In this subgroup, the model effectivelydistinguishes between low‐ and higher‐risk individuals, with a significant difference inmortality observed between these groups.ORIGINAL HYPOTHESISPrimary hypothesis 1. An AI‐ECG‐assisted chest pain pathway will result in lower healthcare resource costcompared to standard clinical investigation pathways.Secondary hypotheses 2. An AI‐ECG‐assisted chest pain pathway in patients with non‐cardiac sounding chestpain is non‐inferior to routine care in terms of: 1. preventing cardiovascular events and mortality 2. initiating standard primary prevention medications 3. achieving overall symptom resolution 3. An AI‐ECG‐assisted chest pain pathway in patients with non‐cardiac sounding chestpain is superior to routine care in reducing the time from referral to diagnosiswith a definitive management plan.EXPERIMENTAL DETAILS AND DESIGN OF PROPOSED INVESTIGATION Proposal 1. There is a substantial and growing burden of referrals to chest pain clinics, oftenresulting in extensive investigations. 2. For patients with non‐cardiac sounding chest pain, a referral and investigationpathway is unlikely to provide a significant clinical benefit over guideline‐basedcare. 3. Novel AI‐guided risk prediction tools have the potential to provide rapid, low‐costreassurance for patients unlikely to benefit from further investigation.Aims To determine whether AI‐ECG screening can facilitate reassurance of patientspresenting to rapid access chest pain clinic with non‐cardiac sounding chest pain, withless resource utilisation, without adversely affecting cardiovascular outcomes.Study design This study is a multicentre, prospective, cluster‐randomised trial comparingAI‐ECG‐assisted management with routine care in patients presenting to rapid access chestpain clinics with non‐anginal chest pain.Methodology The majority of rapid access chest pain clinics in North West London are ledby specialist chest pain nurses, with support from Consultant Cardiologists. At the startof each week, three of the six participating clinic sites will be randomised to delivereither standard clinical care or an AI‐ECG guided pathway. The remaining three sites willbe assigned to the alternative pathway, ensuring that each week three sites will use eachpathway. All patients meeting the inclusion criteria who present to the clinics duringthe study will follow the care pathway to which their clinic has been assigned.In clinics following the AI‐ECG guided pathway, patients will be assessed as usual by aclinician, and in addition, undertake a quantitative symptom questionnaire based on theRose angina classification, which we are planning to embed into an app. This willidentify the nature of chest pain symptoms and establish if the chest pain is in keepingwith angina or not, in a reproducible, standardised and objective format. As previouslydiscussed, atypical angina is a vague and poorly defined descriptor. Chest pain will bedescribed as either being typical for angina or non‐anginal. Patients with typicalanginal pain will undergo standard clinical investigation as advised by the treatingclinician.All patients will undergo a 12‐lead ECG that is analysed using our AI‐ECG model. Patientswith typical angina will have clinician determined further investigation without AIanalysis feedback, but the AI‐ECG predictions will be collated for later sub‐analyses.For patients with non‐anginal chest pain, the AI‐ECG algorithm will risk stratify ECGsand identify a low‐risk group. We have defined low risk as having a 2% or lower predictedrisk of a major adverse cardiovascular events within 1‐year according to the AI‐ECGanalysis.Based on analysis of a comparable, age and sex matched cohort in our BIDMC dataset, wepredict that around 60% of patients will fall into this low‐risk group. Patients withnon‐anginal chest pain identified as having low‐risk ECGs by our AI algorithm will bereassured with no further diagnostic testing.All patients will undergo standard cardiovascular risk factor assessment and will becounselled on lifestyle modification. Where clinically indicated, primary preventiontherapy, including statins, antihypertensives, and diabetic medications, will berecommended in accordance with national guidelines. In the SCOT‐HEART study, whichaddressed the use of CT coronary angiography in a similar patient group, a key weaknesswas a lower implementation of primary prevention therapy in the control arm compared tothe intervention group. We plan to adopt an aggressive approach to primary preventiontherapies which we will maintain consistently across study groups, and measure adherenceto as a secondary outcome of the trial.At the end of each week, all clinical assessments and patient management pathways will bereviewed by a Consultant Cardiologist to ensure safety and adherence to clinicalstandards. The North West London Whole Systems Integrated Care (WSIC) digital informationsystem enables linkage to primary and secondary care records, including presentation,diagnostic and treatment information, as well as mortality outcomes for the 2.3 millionpopulation of North West London. We will use WSIC data to assess healthcare utilisation,the occurrence of cardiovascular events, and the prescription of statins andantihypertensives in the 12 months following each patient's assessment.A subgroup of 500 patients who have consented for follow up will be reviewed viatelephone at one year to assess symptom status using the Rose Angina quantitativequestionnaire app, consistent with the baseline assessment, and we will perform analysisof these patient‐reported outcomes. In addition, we will evaluate patient experience andsatisfaction with the assigned care pathway to gain insights into its acceptability,perceived effectiveness, and overall quality from the patient perspective. We propose theutilisation of the app will provide a standardised and objective format for structuredanalysis of patient reported symptoms, whilst also providing an open platform forqualitative data collection and overall thematic analysis.