James A. White

Background/Objectives: Coronary computed tomography angiography (CCTA) is recommended as a first-line test for suspected coronary artery disease. Many patients undergo invasive coronary angiography (ICA) after CCTA, and no prediction model exists to estimate the probability of this downstream testing. We aimed to develop and validate a parsimonious extreme gradient boosting (XGB) model for predicting ICA referral after CCTA. Methods: Adults undergoing a CCTA were identified at three Canadian centres. An XGB model was trained on 156 variables in the internal cohort (Calgary, n = 8823) and tested in an external cohort (Edmonton, n = 10,596). The full model and a reduced 15-variable model were compared using discrimination and calibration. Results: ICA referral occurred in 1161 (13.2%) internal and 1269 (12.0%) external patients. Internally, the reduced model matched the full model (AUC 0.698 vs. 0.701; p = 0.16) with equivalent calibration (Brier 0.1077 vs. 0.1076; slope 1.21 vs. 1.18). Externally, the full model retained a small but significant advantage (AUC 0.701 vs. 0.687; p < 0.001). Age, anginal nitrate use, and lowest HDL cholesterol were the strongest predictors. Conclusions: A 15-variable XGB model preserved most of the predictive performance of a 156-variable model for ICA referral after CCTA. Clinical use would require evidence that it improves patient selection for ICA.

BACKGROUND: Screening for atrial fibrillation (AF) on the basis of AF risk may be more effective. We aimed to develop, externally validate, and prospectively test a machine learning prediction model using electronic health records (EHRs) to guide AF screening. METHODS: We developed and validated a random forest prediction model for new AF within 6 months, using age, sex, and 10 comorbidities (Future Innovations in Novel Detection of Atrial Fibrillation [FIND-AF] 2.0) in EHRs in the United Kingdom (n=2 081 139), Japan (n=7 795 244), Israel (n=2 166 795), Canada (n=627 919), and China (n=149 145). We conducted a prospective study where participants ≥30 years old without AF and with a CHA ₂ DS ₂ -VASc score ≥2 in men and ≥3 in women, stratified by FIND-AF 2.0 into high and low risk, undertook 4 ECG recordings per day for 3 weeks using a handheld ECG recorder, with a primary outcome of newly diagnosed AF. We estimated stroke risk associated with nonanticoagulated AF in patients with high FIND-AF 2.0 risk in the FinACAF (Finnish Anticoagulation in Atrial Fibrillation) registry of patients with AF (n=229 565). RESULTS: FIND-AF 2.0 was applicable to all EHRs and showed good to excellent prediction performance (United Kingdom: area under the receiver operating characteristic curve [AUROC], 0.819 [95% CI, 0.809–0.829]; Israel: AUROC, 0.835 [95% CI, 0.828–0.842]; Japan: AUROC, 0.751 [95% CI, 0.745–0.757]; Canada: AUROC, 0.747 [95% CI, 0.741–0.753]; China: AUROC, 0.753 [95% CI, 0.725–0.771]), with AUROC>0.7 in men and women in all cohorts, and improved performance compared with CHA ₂ DS ₂ -VASc and C ₂ HEST (coronary artery disease or chronic obstructive pulmonary disease [1 point each]; hypertension [1 point]; elderly [age ≥75 years, 2 points]; systolic HF [2 points]; thyroid disease [hyperthyroidism, 1 point]). Of 1923 participants from 15 sites in the prospective study (mean age, 70.2 [SD 9.4] years), with a mean of 74.8 (SD, 19.4) ECG recordings, AF was diagnosed in 5 of 902 (0.6%) with low FIND-AF 2.0 risk and 46 of 1021 (4.5%) with high FIND-AF 2.0 risk (odds ratio, 8.46 [95% CI, 3.35–21.40], P <0.001). Median AF burden among high FIND-AF 2.0 risk–detected cases was 33.4% (interquartile range, 5.1%–91.6%), and 96.1% initiated oral anticoagulants. In the FinACAF registry, the rate of ischemic stroke for patients with high FIND-AF 2.0 risk, AF, and no anticoagulants was 6.0 events per 100 patient-years. CONCLUSIONS: The EHR-based machine learning model, FIND-AF 2.0, identifies a high-risk subpopulation for AF diagnosis among patients at elevated risk of stroke and could enable scalable, EHR-driven, risk-guided AF screening.

Background: Transthyretin amyloidosis cardiomyopathy (ATTR-CM) is an infiltrative cardiomyopathy and an increasingly recognized cause of heart failure. With improved survival from disease-modifying therapies, an increasing number of patients are presenting for surgery and may be at increased risk of adverse postoperative outcomes. This study reports outcomes of ATTR-CM patients undergoing surgery and evaluates the utility of the Revised Cardiac Risk Index (RCRI), a perioperative risk tool. Methods: A total of 145 ATTR-CM patients were included, among which 51 patients underwent at least one eligible surgical procedure. Preoperative risk was assessed using the RCRI, analyzed both as a categorical and as a dichotomized (≥3 vs 48 hours), and major adverse cardiac events. Models were adjusted for frailty (Clinical Frailty Scale ≥5) and major surgery, using multivariable, ordinal, and Firth penalized logistic regression analyses. Results: Patients were predominantly male (86%) with a mean age of 76 ± 9 years, and 61% were frail. Higher RCRI scores were associated with unplanned postoperative hospital admission (RCRI ≥3: adjusted OR 48.9, 95% CI 4.8–502.2) and longer LOS (RCRI ≥3: adjusted OR 40.7, 95% CI 4.3–382.8). RCRI ≥3 was also associated with prolonged hospitalization (>48 hours) in Firth penalized logistic regression, whereas frailty was not independently associated. Conclusions: In a real-world ATTR-CM cohort undergoing major non-cardiac surgery, the overall risk of adverse outcomes was low, and higher RCRI scores were associated with increased postoperative hospital admission and longer LOS, including hospitalization exceeding 48 hours. The RCRI retains prognostic utility in this high-risk cohort and may support peri-operative risk stratification.

BACKGROUND: Suboptimal left ventricular (LV) and right ventricular lead positioning has been associated with a lesser response to cardiac resynchronization therapy. The MAPIT-CRT (MRI Allocation of Pacing Targets in Cardiac Resynchronization Therapy) randomized controlled trial evaluated a novel, cardiac magnetic resonance–generated 4-dimensional phenomics cardiac magnetic resonance imaging (4DPcmr) lead placement strategy. METHODS: A total of 202 participants with New York Heart Association class II to IV heart failure on optimal medical therapy, LV ejection fraction ≤35%, and QRS duration ≥120 ms were analyzed from 7 Canadian sites. Participants were randomized to 4DPcmr-guided lead placement using a web-based application or standard lead placement. 4DPcmr-recommended LV and right ventricular (RV) lead locations were generated using the combined consideration of (1) regional scar distribution and burden, (2) maximal regional delay in LV peak systolic strain, and (3) maximal interlead distance. RESULTS: The primary end point, an increase in LV ejection fraction ≥5% at 6 months, was reached in 69 of 105 4DPcmr-guided participants (65.7%) versus 50 of 96 control participants (52.1%; risk ratio, 1.80 [95% CI, 1.02–3.17]; P =0.04). The absolute increases in LV ejection fraction observed for the respective study arms were 10.8% versus 5.8% ( P =0.01). No differences were identified in the secondary end points of all-cause mortality or heart failure hospitalization at 12 months, rate of adverse outcomes, or procedural times between the 2 study arms. CONCLUSIONS: 4DPcmr-guided LV/RV cardiac resynchronization therapy lead implantation using a practical web application was clinically feasible, safe, and was associated with greater LV ejection fraction improvement at 6 months versus standard of care with no increase in procedural times or complications. REGISTRATION: URL: https://clinicaltrials.gov/study/NCT01640769 ; Unique identifier: NCT01640769.

Left atrial (LA) four-dimensional (4D) flow quantification and strain may help predict stroke and thrombus formation in patients with atrial fibrillation (AF). We aimed to characterize flow changes in AF patients undergoing pulmonary vein isolation (PVI) and their associations with LA remodelling and contractility markers. Fifty-seven consecutive patients referred for magnetic resonance imaging before first-time PVI and twelve healthy volunteers (HV). LA velocity and stasis maps were obtained from 4D flow. Cine images were used for LA volume, ejection fraction, and strain. Patients’ age was 60 ± 9 years (25% female), versus 44 ± 15 years in HV (8% female). LA 4D flow markers showed LA stasis was reduced in AF patients (median [Q1, Q3] 45.0% (36.0, 54.0) vs. 34.5% (22.8, 45.3); p = 0.040). LA stasis and mean LA velocity were associated in AF patients (r = −0.52; p < 0.001) and HV (r = −0.9; p < 0.001). Associations were poorer for peak LA velocity in AF patients (r = −0.39; p = 0.003). LA stasis was not associated with any marker of LA contractile function in either the AF or HV cohorts. In conclusion, compared with HV patients, patients with AF showed greater LA stasis on 4D flow. LA stasis was not associated with markers of LA contractile function.

Background: Left ventricular ejection fraction (LVEF) continues to be employed as the principle phenotypic marker for the classification, prognostication, and management of cardiovascular disease. However, expanding evidence identifies similarly important roles for right ventricular ejection fraction (RVEF) across multiple referral cohorts, raising the consideration of bi-ventricular ejection fraction (BiVEF) based phenotyping in broader clinical practice. We assessed the value of cardiovascular magnetic resonance (CMR)-based BiVEF phenotyping versus conventional LVEF-only phenotyping for the prediction of NYHA functional class and future heart failure (HF) outcomes. Methods: 9,437 consecutively enrolled adult patients clinically referred for CMR were evaluated for NYHA class ≥II at time of imaging and a future composite outcome of HF hospitalization, HF death, and need for cardiac transplantation or LV assist device. Results: Median age was 57 years (Q1, Q3 44-66, 62% male). Across all LVEF strata, RVEFsub for LVEF <40% and 40-50% were 2.13 (1.64-2.77) and 1.70 (1.33-2.17); p50%. In this model, RVEF <45% was associated with 1.52 (1.25-1.86) greater hazard for future HF outcome versus RVEF ≥45% (p<0.001). Conclusions: RV contractile health is independently associated with HF symptoms and identifies patients at elevated risk of future HF outcomes. Incremental prognostic value from BiVEF phenotyping is delivered versus LVEF-only phenotyping.

Artificial intelligence (AI) is delivering value across all aspects of clinical practice. However, bias may exacerbate healthcare disparities. This review examines the origins of bias in healthcare AI, strategies for mitigation, and responsibilities of relevant stakeholders towards achieving fair and equitable use. We highlight the importance of systematically identifying bias and engaging relevant mitigation activities throughout the AI model lifecycle, from model conception through to deployment and longitudinal surveillance.

Choosing optimal revascularization strategies for patients with obstructive coronary artery disease (CAD) remains a clinical challenge. While randomized controlled trials offer population-level insights, gaps remain regarding personalized decision-making for individual patients. We applied off-policy reinforcement learning (RL) to a composite data model from 41,328 unique patients with angiography-confirmed obstructive CAD. In an offline setting, we estimated optimal treatment policies and evaluated these policies using weighted importance sampling. Our findings indicate that RL-guided therapy decisions outperformed physician-based decision making, with RL policies achieving up to 32% improvement in expected rewards based on composite major cardiovascular events outcomes. Additionally, we introduced methods to ensure that RL CAD treatment policies remain compatible with locally achievable clinical practice models, presenting an interpretable RL policy with a limited number of states. Overall, this novel RL-based clinical decision support tool, RL4CAD, demonstrates potential to optimize care in patients with obstructive CAD referred for invasive coronary angiography.