Interhospital Variation in Admissions Managed With Critical Care Therapies or Invasive Hemodynamic Monitoring in Tertiary Cardiac Intensive Care Units: An Analysis From the Critical Care Cardiology Trials Network Registry.

BACKGROUND: Wide interhospital variations exist in cardiovascular intensive care unit (CICU) admission practices and the use of critical care restricted therapies (CCRx), but little is known about the differences in patient acuity, CCRx utilization, and the associated outcomes within tertiary centers. METHODS: The Critical Care Cardiology Trials Network is a multicenter registry of tertiary and academic CICUs in the United States and Canada that captured consecutive admissions in 2-month periods between 2017 and 2022. This analysis included 17 843 admissions across 34 sites and compared interhospital tertiles of CCRx (eg, mechanical ventilation, mechanical circulatory support, continuous renal replacement therapy) utilization and its adjusted association with in-hospital survival using logistic regression. The Pratt index was used to quantify patient-related and institutional factors associated with CCRx variability. RESULTS: The median age of the study population was 66 (56-77) years and 37% were female. CCRx was provided to 62.2% (interhospital range of 21.3%-87.1%) of CICU patients. Admissions to CICUs with the highest tertile of CCRx utilization had a greater burden of comorbidities, had more diagnoses of ST-elevation myocardial infarction, cardiac arrest, or cardiogenic shock, and had higher Sequential Organ Failure Assessment scores. The unadjusted in-hospital mortality (median, 12.7%) was 9.6%, 11.1%, and 18.7% in low, intermediate, and high CCRx tertiles, respectively. No clinically meaningful differences in adjusted mortality were observed across tertiles when admissions were stratified by the provision of CCRx. Baseline patient-level variables and institutional differences accounted for 80% and 5.3% of the observed CCRx variability, respectively. CONCLUSIONS: In a large registry of tertiary and academic CICUs, there was a >4-fold interhospital variation in the provision of CCRx that was primarily driven by differences in patient acuity compared with institutional differences. No differences were observed in adjusted mortality between low, intermediate, and high CCRx utilization sites.

Canadian Cardiovascular Society/Canadian Association of Interventional Cardiology 2023 Focused Update of the Guidelines for the Use of Antiplatelet Therapy.

Antiplatelet therapy (APT) is the foundation of treatment and prevention of atherothrombotic events in patients with atherosclerotic cardiovascular disease. Selecting the optimal APT strategies to reduce major adverse cardiovascular events, while balancing bleeding risk, requires ongoing review of clinical trials. Appended, the focused update of the Canadian Cardiovascular Society/Canadian Association of Interventional Cardiology guidelines for the use of APT provides recommendations on the following topics: (1) use of acetylsalicylic acid in primary prevention of atherosclerotic cardiovascular disease; (2) dual APT (DAPT) duration after percutaneous coronary intervention (PCI) in patients at high bleeding risk; (3) potent DAPT (P2Y12 inhibitor) choice in patients who present with an acute coronary syndrome (ACS) and possible DAPT de-escalation strategies after PCI; (4) choice and duration of DAPT in ACS patients who are medically treated without revascularization; (5) pretreatment with DAPT (P2Y12 inhibitor) before elective or nonelective coronary angiography; (6) perioperative and longer-term APT management in patients who require coronary artery bypass grafting surgery; and (7) use of APT in patients with atrial fibrillation who require oral anticoagulation after PCI or medically managed ACS. These recommendations are all on the basis of systematic reviews and meta-analyses conducted as part of the development of these guidelines, provided in the Supplementary Material.

Spontaneous Coronary Artery Dissection Across the Health Care Pathway: A National, Multicenter, Patient-Informed Investigation.

BACKGROUND: Clinical practice guidelines for the management and convalescence of patients with spontaneous coronary artery dissection (SCAD) have yet to be developed. The targeted content, delivery, and outcomes of interventions that benefit this population remain unclear. Patient-informed data are required to substantiate observational research and provide evidence to inform and standardize clinical activities. METHODS AND RESULTS: Patients diagnosed with SCAD (N=89; 86.5% women; mean age, 53.2 years) were purposively selected from 5 large tertiary care hospitals. Patients completed sociodemographic and medical questionnaires and participated in an interview using a patient-piloted semistructured interview guide. Interviews were transcribed and subjected to framework analysis using inductive and then deductive coding techniques. Approximately 1500 standard transcribed pages of interview data were collected. Emotional distress was the most commonly cited precipitating factor (56%), with an emphasis on anxiety symptoms. The awareness and detection of SCAD as a cardiac event was low among patients (35%) and perceived to be moderate among health care providers (55%). Health care providers' communication of the prognosis and self-management of SCAD were perceived to be poor (79%). Postevent psychological disorders among patients were evident (30%), and 73% feared recurrence. Short- and longer-term follow-up that was tailored to patients' needs was desired (72%). Secondary prevention programming was recommended, but there were low completion rates of conventional cardiac rehabilitation (48%), and current programming was deemed inadequate. CONCLUSIONS: This early-stage, pretrial research has important implications for the acute and long-term management of patients with SCAD. Additional work is required to validate the hypotheses generated from this patient-oriented research.

Digital Tool-Assisted Hospitalization Detection in the Tailored Antiplatelet Initiation to Lessen Outcomes due to Decreased Clopidogrel Response After Percutaneous Coronary Intervention Study Compared to Traditional Site-Coordinator Ascertainment: Intervention Study.

BACKGROUND: Accurate, timely ascertainment of clinical end points, particularly hospitalizations, is crucial for clinical trials. The Tailored Antiplatelet Initiation to Lessen Outcomes Due to Decreased Clopidogrel Response after Percutaneous Coronary Intervention (TAILOR-PCI) Digital Study extended the main TAILOR-PCI trial's follow-up to 2 years, using a smartphone-based research app featuring geofencing-triggered surveys and routine monthly mobile phone surveys to detect cardiovascular (CV) hospitalizations. This pilot study compared these digital tools to conventional site-coordinator ascertainment of CV hospitalizations. OBJECTIVE: The objectives were to evaluate geofencing-triggered notifications and routine monthly mobile phone surveys' performance in detecting CV hospitalizations compared to telephone visits and health record reviews by study coordinators at each site. METHODS: US and Canadian participants from the TAILOR-PCI Digital Follow-Up Study were invited to download the Eureka Research Platform mobile app, opting in for location tracking using geofencing, triggering a smartphone-based survey if near a hospital for ≥4 hours. Participants were sent monthly notifications for CV hospitalization surveys. RESULTS: From 85 participants who consented to the Digital Study, downloaded the mobile app, and had not previously completed their final follow-up visit, 73 (85.8%) initially opted in and consented to geofencing. There were 9 CV hospitalizations ascertained by study coordinators among 5 patients, whereas 8 out of 9 (88.9%) were detected by routine monthly hospitalization surveys. One CV hospitalization went undetected by the survey as it occurred within two weeks of the previous event, and the survey only allowed reporting of a single hospitalization. Among these, 3 were also detected by the geofencing algorithm, but 6 out of 9 (66.7%) were missed by geofencing: 1 occurred in a participant who never consented to geofencing, while 5 hospitalizations occurred among participants who had subsequently turned off geofencing prior to their hospitalization. Geofencing-detected hospitalizations were ascertained within a median of 2 (IQR 1-3) days, monthly surveys within 11 (IQR 6.5-25) days, and site coordinator methods within 38 (IQR 9-105) days. The geofencing algorithm triggered 245 notifications among 39 participants, with 128 (52.2%) from true hospital presence and 117 (47.8%) from nonhospital health care facility visits. Additional geofencing iterative improvements to reduce hospital misidentification were made to the algorithm at months 7 and 12, elevating the rate of true alerts from 35.4% (55 true alerts/155 total alerts before month 7) to 78.7% (59 true alerts/75 total alerts in months 7-12) and ultimately to 93.3% (14 true alerts/5 total alerts in months 13-21), respectively. CONCLUSIONS: The monthly digital survey detected most CV hospitalizations, while the geofencing survey enabled earlier detection but did not offer incremental value beyond traditional tools. Digital tools could potentially reduce the burden on study coordinators in ascertaining CV hospitalizations. The advantages of timely reporting via geofencing should be weighed against the issue of false notifications, which can be mitigated through algorithmic refinements.

Cardiac PET Myocardial Blood Flow Quantification Assessment of Early Cardiac Allograft Vasculopathy.

BACKGROUND: Positron emission tomography (PET) has demonstrated utility for diagnostic and prognostic assessment of cardiac allograft vasculopathy (CAV) but has not been evaluated in the first year after transplant. OBJECTIVES: The authors sought to evaluate CAV at 1 year by PET myocardial blood flow (MBF) quantification. METHODS: Adults at 2 institutions enrolled between January 2018 and March 2021 underwent prospective 3-month (baseline) and 12-month (follow-up) post-transplant PET, endomyocardial biopsy, and intravascular ultrasound examination. Epicardial CAV was assessed by intravascular ultrasound percent intimal volume (PIV) and microvascular CAV by endomyocardial biopsy. RESULTS: A total of 136 PET studies from 74 patients were analyzed. At 12 months, median PIV increased 5.6% (95% CI: 3.6%-7.1%) with no change in microvascular CAV incidence (baseline: 31% vs follow-up: 38%; P = 0.406) and persistent microvascular disease in 13% of patients. Median capillary density increased 30 capillaries/mm2 (95% CI: -6 to 79 capillaries/mm2). PET myocardial flow reserve (2.5 ± 0.7 vs 2.9 ± 0.8; P = 0.001) and stress MBF (2.7 ± 0.6 vs 2.9 ± 0.6; P = 0.008) increased, and coronary vascular resistance (CVR) (49 ± 13 vs 47 ± 11; P = 0.214) was unchanged. At 12 months, PET and PIV had modest correlation (stress MBF: r = -0.35; CVR: r = 0.33), with lower stress MBF and higher CVR across increasing PIV tertiles (all P < 0.05). Receiver-operating characteristic curves for CAV defined by upper-tertile PIV showed areas under the curve of 0.74 for stress MBF and 0.73 for CVR. CONCLUSIONS: The 1-year post-transplant PET MBF is associated with epicardial CAV, supporting potential use for early noninvasive CAV assessment. (Early Post Transplant Cardiac Allograft Vasculopahty [ECAV]; NCT03217786).

CathAI: fully automated coronary angiography interpretation and stenosis estimation.

Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.

Pulmonary Artery Catheter Use and Mortality in the Cardiac Intensive Care Unit.

BACKGROUND: The appropriate use of pulmonary artery catheters (PACs) in critically ill cardiac patients remains debated. OBJECTIVES: The authors aimed to characterize the current use of PACs in cardiac intensive care units (CICUs) with attention to patient-level and institutional factors influencing their application and explore the association with in-hospital mortality. METHODS: The Critical Care Cardiology Trials Network is a multicenter network of CICUs in North America. Between 2017 and 2021, participating centers contributed annual 2-month snapshots of consecutive CICU admissions. Admission diagnoses, clinical and demographic data, use of PACs, and in-hospital mortality were captured. RESULTS: Among 13,618 admissions at 34 sites, 3,827 were diagnosed with shock, with 2,583 of cardiogenic etiology. The use of mechanical circulatory support and heart failure were the patient-level factors most strongly associated with a greater likelihood of the use of a PAC (OR: 5.99 [95% CI: 5.15-6.98]; P < 0.001 and OR: 3.33 [95% CI: 2.91-3.81]; P < 0.001, respectively). The proportion of shock admissions with a PAC varied significantly by study center ranging from 8% to 73%. In analyses adjusted for factors associated with their placement, PAC use was associated with lower mortality in all shock patients admitted to a CICU (OR: 0.79 [95% CI: 0.66-0.96]; P = 0.017). CONCLUSIONS: There is wide variation in the use of PACs that is not fully explained by patient level-factors and appears driven in part by institutional tendency. PAC use was associated with higher survival in cardiac patients with shock presenting to CICUs. Randomized trials are needed to guide the appropriate use of PACs in cardiac critical care.

Fibrotic Plaque and Microvascular Dysfunction Predict Early Cardiac Allograft Vasculopathy Progression After Heart Transplantation: The Early Post Transplant Cardiac Allograft Vasculopathy Study.

BACKGROUND: Early cardiac allograft vasculopathy (CAV) prognostication is needed to improve long-term outcomes after heart transplantation. We characterized first year posttransplant coronary anatomic-physiologic alterations to determine predictors of early CAV progression. METHODS: Heart transplant recipients at 2 institutions (enrolled January 2018 to March 2021) underwent prospective evaluation 3 and 12-month posttransplant with angiography and left anterior descending artery intravascular ultrasound, optical coherence tomography, fractional flow reserve, coronary flow reserve, and index of microcirculatory resistance measurements. CAV progression was assessed by intravascular ultrasound change in percentage intimal volume from baseline to 12-month follow-up. RESULTS: Eighty-two patients (mean age, 51 years; 60% men) completed evaluation at mean 13.8 and 56.3 weeks posttransplant. Donor atherosclerosis (baseline intravascular ultrasound maximal intimal thickness, ≥0.5 mm) was evident in 50%. De novo (follow-up maximal intimal thickness, ≥0.5 mm) and rapidly progressive CAV (maximal intimal thickness, ≥0.5-mm increase from baseline) developed in 24% and 13%, respectively. On optical coherence tomography, baseline to follow-up median intimal volume increased 42% (0.58 mm3/mm), percentage intimal volume increased 44% (4.6%), vessel volume decreased 4% (-0.50 mm3/mm) and lumen volume decreased 9% (-1.02 mm3/mm); P<0.05 for all. Fibrotic plaque was the predominant morphology: baseline, 29% and follow-up, 50%. Coronary physiology was abnormal in 41% at baseline and 45% at follow-up, with 1 in 5 patients having microvascular dysfunction (index of microcirculatory resistance, ≥25). On multivariable linear regression analysis, recipient male sex, fibrotic plaque, and index of microcirculatory resistance were independent predictors of coronary disease progression. CONCLUSIONS: Fibrotic plaque on optical coherence tomography and index of microcirculatory resistance early posttransplant predict CAV progression in the first year of transplantation. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier: NCT03217786.

Automated Assessment of Cardiac Systolic Function From Coronary Angiograms With Video-Based Artificial Intelligence Algorithms.

Importance: Understanding left ventricular ejection fraction (LVEF) during coronary angiography can assist in disease management. Objective: To develop an automated approach to predict LVEF from left coronary angiograms. Design, Setting, and Participants: This was a cross-sectional study with external validation using patient data from December 12, 2012, to December 31, 2019, from the University of California, San Francisco (UCSF). Data were randomly split into training, development, and test data sets. External validation data were obtained from the University of Ottawa Heart Institute. Included in the analysis were all patients 18 years or older who received a coronary angiogram and transthoracic echocardiogram (TTE) within 3 months before or 1 month after the angiogram. Exposure: A video-based deep neural network (DNN) called CathEF was used to discriminate (binary) reduced LVEF (≤40%) and to predict (continuous) LVEF percentage from standard angiogram videos of the left coronary artery. Guided class-discriminative gradient class activation mapping (GradCAM) was applied to visualize pixels in angiograms that contributed most to DNN LVEF prediction. Results: A total of 4042 adult angiograms with corresponding TTE LVEF from 3679 UCSF patients were included in the analysis. Mean (SD) patient age was 64.3 (13.3) years, and 2212 patients were male (65%). In the UCSF test data set (n = 813), the video-based DNN discriminated (binary) reduced LVEF (≤40%) with an area under the receiver operating characteristic curve (AUROC) of 0.911 (95% CI, 0.887-0.934); diagnostic odds ratio for reduced LVEF was 22.7 (95% CI, 14.0-37.0). DNN-predicted continuous LVEF had a mean absolute error (MAE) of 8.5% (95% CI, 8.1%-9.0%) compared with TTE LVEF. Although DNN-predicted continuous LVEF differed 5% or less compared with TTE LVEF in 38.0% (309 of 813) of test data set studies, differences greater than 15% were observed in 15.2% (124 of 813). In external validation (n = 776), video-based DNN discriminated (binary) reduced LVEF (≤40%) with an AUROC of 0.906 (95% CI, 0.881-0.931), and DNN-predicted continuous LVEF had an MAE of 7.0% (95% CI, 6.6%-7.4%). Video-based DNN tended to overestimate low LVEFs and underestimate high LVEFs. Video-based DNN performance was consistent across sex, body mass index, low estimated glomerular filtration rate (≤45), presence of acute coronary syndromes, obstructive coronary artery disease, and left ventricular hypertrophy. Conclusion and relevance: This cross-sectional study represents an early demonstration of estimating LVEF from standard angiogram videos of the left coronary artery using video-based DNNs. Further research can improve accuracy and reduce the variability of DNNs to maximize their clinical utility.

Genetic-Guided Oral P2Y12 Inhibitor Selection and Cumulative Ischemic Events After Percutaneous Coronary Intervention.

BACKGROUND: Genetic-guided P2Y12 inhibitor selection has been proposed to reduce ischemic events by identifying CYP2C19 loss-of-function (LOF) carriers at increased risk with clopidogrel treatment after percutaneous coronary intervention (PCI). A prespecified analysis of TAILOR-PCI (Tailored Antiplatelet Therapy Following PCI) evaluated the effect of genetic-guided P2Y12 inhibitor therapy on cumulative ischemic and bleeding events. OBJECTIVES: Here, the authors detail a prespecified analysis of cumulative endpoints. The primary endpoint was cumulative incidence rate of ischemic events at 12 months. Cumulative incidence of major and minor bleeding was a secondary endpoint. Cox proportional hazards models as adapted by Wei, Lin, and Weissfeld were used to estimate the effect of this strategy on all observed events. METHODS: The TAILOR-PCI trial was a prospective trial including 5,302 post-PCI patients with acute and stable coronary artery disease (CAD) who were randomized to genetic-guided P2Y12 inhibitor or conventional clopidogrel therapy. In the genetic-guided group, LOF carriers were prescribed ticagrelor, whereas noncarriers received clopidogrel. TAILOR-PCI's primary analysis was time to first event in LOF carriers. RESULTS: Among 5,276 patients (median age 62 years; 25% women; 82% acute CAD; 18% stable CAD), 1,849 were LOF carriers (903 genetic-guided; 946 conventional therapy). The cumulative primary endpoint was significantly reduced in the genetic-guided group compared with the conventional therapy (HR: 0.61; 95% CI: 0.41-0.89; P = 0.011) with no significant difference in cumulative incidence of major or minor bleeding (HR: 1.36; 95% CI: 0.67-2.76; P = 0.39). CONCLUSIONS: Among CYP2C19 LOF carriers undergoing PCI, a genetic-guided strategy resulted in a statistically significant reduction in cumulative ischemic events without a significant difference in bleeding. (Tailored Antiplatelet Therapy Following PCI [TAILOR-PCI]; NCT01742117).

Extended dual antiplatelet therapy following percutaneous coronary intervention in clinically important patient subgroups: a systematic review and meta-analysis.

BACKGROUND: Dual antiplatelet therapy (DAPT) is routinely given to patients after percutaneous coronary intervention (PCI) with stenting; however, optimal duration remains uncertain in some situations. We assessed the benefits and harms of extending DAPT beyond 1 year after PCI in clinically important patient subgroups. METHODS: We conducted a systematic review and meta-analysis. We searched electronic databases (Embase, MEDLINE, PubMed, Cochrane Library) and grey literature (from inception to Nov. 5, 2021) and included randomized controlled trials (RCTs) of extended DAPT (> 12 mo) compared with DAPT for 6-12 months following PCI with stenting. The primary outcome was death (all cause, cardiovascular, noncardiovascular); secondary outcomes included major adverse cardiovascular and cerebrovascular events, myocardial infarction (MI), stroke, stent thrombosis and bleeding. Subgroups were based on prespecified patient characteristics (prior MI, acute coronary syndrome [ACS], diabetes mellitus, age, smoking status). Data were analyzed by random-effects pairwise meta-analysis. RESULTS: We identified 9 RCTs that provided subgroup data. We found that extended DAPT reduced the risk of MI and stent thrombosis but increased the risk of bleeding, compared with standard DAPT, with no difference in the risk of all-cause death (relative risk [RR] 1.07, 95% confidence interval [CI] 0.80-1.42) or cardiovascular death (RR 0.98, 95% CI 0.74-1.30). We found that patients with a prior MI, with ACS at presentation, without diabetes or aged younger than 75 years may derive the most benefit from extended DAPT. Among patients who received extended DAPT, the risk of all-cause death was significantly increased among those with no prior MI (RR 1.64, 95% CI 1.08-2.24), whereas there was no significant difference in the risk of all-cause death between standard and extended DAPT for patients with ACS (RR 1.20, 95% CI 0.51-2.83), with diabetes (RR 1.27, 95% CI 0.86-1.89), aged older than 75 years (RR 1.32, 95% CI 0.39-4.54) or who smoked (RR 0.90, 95% CI 0.42-1.92). Similar results were found for cardiovascular death, where data were available. INTERPRETATION: Patients with a previous MI with ACS at presentation, without diabetes, or aged younger than 75 years may derive the most benefit from extended DAPT. These findings support the need for careful selection of patients who may benefit most from extended DAPT. STUDY REGISTRATION: PROSPERO no. CRD42018082587.

Off-Hours Presentation, Door-to-Balloon Time, and Clinical Outcomes in Patients Referred for Primary Percutaneous Coronary Intervention.

OBJECTIVES: Presentation with ST-segment-elevation myocardial infarction (STEMI) during off-hours may impact timely reperfusion and clinical outcomes. We investigated the association between off-hours presentation, door-to-balloon time, and in-hospital mortality in patients with STEMI referred for primary percutaneous coronary intervention (PCI). METHODS: We included consecutive patients referred for primary PCI at the University of Ottawa Heart Institute between July 2004 and December 2017. The off-hours group included patients presenting on weekends, statutory holidays, or between 18:00 to 07:59 hours on weekdays. The on-hours group included patients presenting between 08:00 and 17:59 hours on weekdays. The primary clinical outcome was the adjusted in-hospital mortality. The primary quality-of-care indicator was door-to-balloon time. RESULTS: A total of 5132 patients were included, with 3152 (61.4%) in the off-hours group and 1980 (38.6%) in the on-hours group. The median door-to-balloon time was longer in the off-hours group compared with the on-hours group (102 minutes vs 77 minutes; P<.001), while the median onset-to-door time was similar (P=.40). There was no difference in the rates of in-hospital mortality (3.5% vs 3.0%; P=.32) or in the adjusted mortality (odds ratio, 1.2; 95% confidence interval, 0.8-1.8; P=.44) between off-hours and on-hours groups. However, door-to-balloon time was an independent predictor of in-hospital mortality (P<.01) and off-hours presentation was an independent predictor of longer door-to-balloon time (P<.001), with an excess of 22.1 minutes. CONCLUSION: Patients treated with primary PCI during off-hours had longer door-to-balloon times. Treatment during off-hours was an independent predictor of longer door-to-balloon time and longer door-to-balloon times were associated with higher mortality.

Novel Artificial Intelligence Applications in Cardiology: Current Landscape, Limitations, and the Road to Real-World Applications.

Cardiovascular diseases are the leading cause of death globally and contribute significantly to the cost of healthcare. Artificial intelligence (AI) is poised to reshape cardiology. Using supervised and unsupervised learning, the two main branches of AI, several applications have been developed in recent years to improve risk prediction, allow large-scale analysis of medical data, and phenotype patients for personalized medicine. In this review, we examine the key advances in AI in cardiology and its limitations regarding bias in the data, standardization in reporting, data access, and model trust and accountability in cases of error. Finally, we discuss implementation methods to unleash AI's potential in making healthcare more accurate and efficient. Several steps need to be followed and challenges overcome in order to successfully integrate AI in clinical practice and ensure its longevity.

Presentation and Outcomes of Patients With Preoperative Critical Illness Undergoing Cardiac Surgery.

BACKGROUND: Little is known about the prevalence and post-surgical outcomes associated with cardiac intensive care unit (CICU) therapeutics among CICU patients referred for cardiac surgery. OBJECTIVES: The purpose of this study was to investigate the clinical characteristics and outcomes of CICU patients referred for cardiac surgery from the intensive care unit. METHODS: We analyzed characteristics and outcomes of CICU admissions referred from the CICU for cardiac surgery during 2017 to 2020 across 29 centers. The primary outcome was in-hospital mortality. RESULTS: Among 10,321 CICU admissions, 887 (8.6%) underwent cardiac surgery, including 406 (46%) coronary artery bypass graftings, 201 (23%) transplants or ventricular assist devices, 171 (19%) valve surgeries, and 109 (12%) other procedures. Common indications for CICU admission included shock (33.5%) and respiratory insufficiency (24.9%). Preoperative CICU therapies included vasoactive therapy in 52.2%, mechanical circulatory support in 35.9%, renal replacement in 8.2%, mechanical ventilation in 35.7%, and 17.5% with high-flow nasal cannula or noninvasive positive pressure ventilation. In-hospital mortality was 11.7% among all CICU admissions and 9.1% among patients treated with cardiac surgery. After multivariable adjustment, pre-op mechanical circulatory support and renal replacement therapy were associated with mortality, while respiratory support and vasoactive therapy were not. CONCLUSIONS: Nearly 1 in 12 contemporary CICU patients receive cardiac surgery. Despite high preoperative disease severity, CICU admissions undergoing cardiac surgery had a comparable mortality rate to CICU patients overall; highlighting the ability of clinicians to select higher acuity patients with a reasonable perioperative risk.

Safety and Efficacy of CYP2C19 Genotype-Guided Escalation of P2Y12 Inhibitor Therapy After Percutaneous Coronary Intervention in Chronic Kidney Disease: a Post Hoc Analysis of the TAILOR-PCI Study.

PURPOSE: Chronic kidney disease (CKD) is a risk factor for ischemic and bleeding events with dual antiplatelet therapy after percutaneous coronary intervention (PCI). Whether the presence of CYP2C19 loss of function (LOF) alleles modifies this risk, and whether a genotype-guided (GG) escalation of P2Y12 inhibitor therapy post PCI is safe in this population is unclear. METHODS: This was a post hoc analysis of randomized patients in TAILOR PCI. Patients were divided into two groups based on estimated glomerular filtration rate (eGFR) threshold of < 60 ml/min/1.73 m2 for CKD (n = 539) and non-CKD (n = 4276). The aggregate of cardiovascular death, stroke, myocardial infarction, stent thrombosis, and severe recurrent coronary ischemia at 12-months post-PCI was assessed as the primary endpoint. Secondary endpoint was major or minor bleeding. RESULTS: Mean (standard deviation) eGFR among patients with CKD was 49.5 (8.4) ml/min/1.72 m2. Among all patients, there was no significant interaction between randomized strategy and CKD status for any endpoint. Among LOF carriers, the interaction between randomized strategy and CKD status on composite ischemic outcome was not significant (p = 0.2). GG strategy was not associated with an increased risk of bleeding in either CKD group. CONCLUSIONS: In this exploratory analysis, escalation of P2Y12 inhibitor therapy following a GG strategy did not reduce the primary outcome in CKD. However, P2Y12 inhibitor escalation following a GG strategy was not associated with increased bleeding risk in CKD. Larger studies in CKD are needed. CLINICAL TRIAL REGISTRATION: https://clinicaltrials.gov/ct2/show/NCT01742117?term=TAILOR-PCI&draw=2&rank=1 . NCT01742117.

Canadian Spontaneous Coronary Artery Dissection Cohort Study: 3-Year Outcomes.

BACKGROUND: Spontaneous coronary artery dissection (SCAD) is an important cause of myocardial infarction (MI) in young to middle-aged women. OBJECTIVES: We aim to define the long-term natural history of SCAD. METHODS: We performed a multicenter, prospective, observational study of patients with nonatherosclerotic SCAD presenting acutely from 22 North American centers. We recorded baseline demographics, in-hospital characteristics, precipitating and predisposing conditions, angiographic features (adjudicated), in-hospital and 3-year major adverse cardiovascular events (MACE). Cox regression multivariable analysis was performed. RESULTS: We prospectively enrolled 750 consecutive patients with SCAD from June 2014 to June 2018. Mean age was 51.7 ± 10.5 years, 88.5% were women (55.0% postmenopausal); 31.3% presented with ST-segment elevation myocardial infarction, and 68.3% with non-ST-segment elevation myocardial infarction. Precipitating emotional stressor was reported in 50.3%, and physical stressor in 28.9%. Predisposing conditions included fibromuscular dysplasia in 42.9% (56.4% in those with complete screening), peripartum state 4.5%, and genetic disorders 1.6%. Most patients were treated conservatively (84.3%); 14.1% underwent percutaneous coronary intervention (PCI), 0.7% coronary artery bypass graft. At 3.0-year median follow-up, mortality was 0.8%, recurrent MI 9.9% (extension of previous SCAD 3.5%, de novo recurrent SCAD 2.4%, iatrogenic dissection 1.9%), with overall MACE 14.0%. Presence of genetic disorders, peripartum SCAD, and extracoronary fibromuscular dysplasia were independent predictors of 3-year MACE. Patients who underwent PCI at index hospitalization had similar postdischarge MACE compared with no PCI. At 3 years, 80.0% remained on aspirin and 73.5% on beta-blockade. CONCLUSIONS: Long-term mortality and de novo recurrent SCAD was low in our contemporary large SCAD cohort that included low revascularization rate and high use of beta-blockade and aspirin. Genetic disorders, extracoronary fibromuscular dysplasia, and peripartum SCAD were independent predictors of long-term MACE.

Critical Care Cardiology Trials Network (CCCTN): a cohort profile.

AIMS: The aims of the Critical Care Cardiology Trials Network (CCCTN) are to develop a registry to investigate the epidemiology of cardiac critical illness and to establish a multicentre research network to conduct randomised clinical trials (RCTs) in patients with cardiac critical illness. METHODS AND RESULTS: The CCCTN was founded in 2017 with 16 centres and has grown to a research network of over 40 academic and clinical centres in the United States and Canada. Each centre enters data for consecutive cardiac intensive care unit (CICU) admissions for at least 2 months of each calendar year. More than 20 000 unique CICU admissions are now included in the CCCTN Registry. To date, scientific observations from the CCCTN Registry include description of variations in care, the epidemiology and outcomes of all CICU patients, as well as subsets of patients with specific disease states, such as shock, heart failure, renal dysfunction, and respiratory failure. The CCCTN has also characterised utilization patterns, including use of mechanical circulatory support in response to changes in the heart transplantation allocation system, and the use and impact of multidisciplinary shock teams. Over years of multicentre collaboration, the CCCTN has established a robust research network to facilitate multicentre registry-based randomised trials in patients with cardiac critical illness. CONCLUSION: The CCCTN is a large, prospective registry dedicated to describing processes-of-care and expanding clinical knowledge in cardiac critical illness. The CCCTN will serve as an investigational platform from which to conduct randomised controlled trials in this important patient population.

Patient Onboarding and Engagement to Build a Digital Study After Enrollment in a Clinical Trial (TAILOR-PCI Digital Study): Intervention Study.

BACKGROUND: The Tailored Antiplatelet Initiation to Lessen Outcomes Due to Decreased Clopidogrel Response After Percutaneous Coronary Intervention (TAILOR-PCI) Digital Study is a novel proof-of-concept study that evaluated the feasibility of extending the TAILOR-PCI randomized controlled trial (RCT) follow-up period by using a remote digital platform. OBJECTIVE: The aim of this study is to describe patients' onboarding, engagement, and results in a digital study after enrollment in an RCT. METHODS: In this intervention study, previously enrolled TAILOR-PCI patients in the United States and Canada within 24 months of randomization were invited by letter to download the study app. Those who did not respond to the letter were contacted by phone to survey the reasons for nonparticipation. A direct-to-patient digital research platform (the Eureka Research Platform) was used to onboard patients, obtain consent, and administer activities in the digital study. The patients were asked to complete health-related surveys and digitally provide follow-up data. Our primary end points were the consent rate, the duration of participation, and the monthly activity completion rate in the digital study. The hypothesis being tested was formulated before data collection began. RESULTS: After the parent trial was completed, letters were mailed to 907 eligible patients (representing 18.8% [907/4837] of total enrolled in the RCT) within 15.6 (SD 5.2) months of randomization across 24 sites. Among the 907 patients invited, 290 (32%) visited the study website and 110 (12.1%) consented-40.9% (45/110) after the letter, 33.6% (37/110) after the first phone call, and 25.5% (28/110) after the second call. Among the 47.4% (409/862) of patients who responded, 41.8% (171/409) declined to participate because of a lack of time, 31.2% (128/409) declined because of the lack of a smartphone, and 11.5% (47/409) declined because of difficulty understanding what was expected of them in the study. Patients who consented were older (aged 65.3 vs 62.5 years; P=.006) and had a lower prevalence of diabetes (19% vs 30%; P=.02) or tobacco use (6.4% vs 24.8%; P<.001). A greater proportion had bachelor's degrees (47.2% vs 25.7%; P<.001) and were more computer literate (90.5% vs 62.3% of daily internet use; P<.001) than those who did not consent. The average completion rate of the 920 available monthly electronic visits was 64.9% (SD 7.6%); there was no decrease in this rate throughout the study duration. CONCLUSIONS: Extended follow-up after enrollment in an RCT by using a digital study was technically feasible but was limited because of the inability to contact most eligible patients or a lack of time or access to a smartphone. Among the enrolled patients, most completed the required electronic visits. Enhanced recruitment methods, such as the introduction of a digital study at the time of RCT consent, smartphone provision, and robust study support for onboarding, should be explored further. TRIAL REGISTRATION: Clinicaltrails.gov NCT01742117; https://clinicaltrials.gov/ct2/show/NCT01742117.