•With contemporary STEMI care, the need for prolonged telemetry for surveillance of an actionable arrhythmia is unclear.•Beyond the first 24-48 hours, the incident rate for an actionable arrhythmia is low.•Traditionally established prognostic variables in STEMI would likely guide triage for longer telemetry durations in STEMI.

BACKGROUND While sodium-glucose cotransport 2 receptor inhibitors (SGLT2i) improve post infarction cardiovascular outcomes, limited understanding exists on how these agents influence pathophysiology preceding myocardial infarction. OBJECTIVES The objective of this study was to explore how proteins are differentially regulated in patients on and not on an SGLT2i preceding ST-segment elevation myocardial infarction (STEMI). METHODS Between June 2021 and October 2023, blood was collected at the time of arterial sheath insertion from consecutive STEMI patients. We then identified patients with diabetes and created propensity-matched pairs of patients on and not on SGLT2i prior to STEMI (SGLT2i+ and SGLT2i-). Serum was separated, and following immunodepletion and enzymatic digestion, liquid chromatography-tandem mass spectrometry was performed to identify differentially regulated proteins between the 2 SGLT2i groups. RESULTS Of the 560 STEMI patients, 149 eligible patients had diabetes distributed by pre-existing SGLT2i use as: SGLT2i+ (n = 35) and SGLT2i-(n = 114). Both SGLT2i groups were comparable in their presenting demographics and reperfusion strategies, except for higher proportion of insulin use in SGLT2i+ patients. Thirty-three SGLT2i+/SGLT2i-propensity-matched pairs were created from which 21 differentially expressed proteins were identified; dominantly noted was up-regulation of proteins involved in heme-scavenging and nitric oxide transport in patients on SGLT2i+ compared with SGLT2i preceding STEMI. CONCLUSIONS SGLT2i appears to predominantly associate with up-regulation of heme-scavenging and nitricoxide, and plausibly through a related reduction in infarct size also associates with the observed related improvement in post infarction heart failure. (JACC Adv. 2025;4:101887) (c) 2025 The Authors. Published by Elsevier on behalf of the American College of Cardiology Foundation. This is an open access article under the CC BY-NC-ND license (http://creativecommons. org/licenses/by-nc-nd/4.0/).

Impaired cerebrovascular control in patients with heart failure with reduced ejection fraction (HFrEF) has been attributed to cardiac impairment and exaggerated sympathetic-mediated cerebral vasoconstriction. The goal of this study was to examine the effect of muscle metaboreflex activation (MMA) on cerebrovascular hemodynamics in patients with HFrEF under conditions of preserved cardiac output. It was hypothesized that reductions in the index of cerebral blood flow and cerebrovascular conductance (CVCi) during MMA would be exaggerated in HFrEF and independent of reduced cardiac output. Middle cerebral blood velocity (MCAVmean; transcranial Doppler), blood pressure, cardiac output (Finometer), and end-tidal CO2 were examined at rest, during isometric handgrip, and during muscle MMA (postexercise circulatory occlusion) in 18 patients with HFrEF and 21 healthy, sex-, and age-matched controls. To minimize differences in β-adrenergic control, patients with HFrEF withdrew from β-blockade medications before the study. Cardiac index and blood pressure were not significantly different between groups under any condition. The MCAVmean was lower at rest and during exercise in HFrEF. The CVCi (MCAVmean/mean arterial pressure) and MCAVmean decreased during MMA in the control group. In contrast, the CVCi remained unchanged and MCAVmean increased during MMA in the HFrEF group. Despite similar systemic hemodynamics, patients with HFrEF display lower MCAVmean at rest and an increase in MCAVmean during MMA. These novel findings implicate aspects other than reduced cardiac output or exaggerated sympathetic constriction as underlying causes of altered cerebrovascular regulation in HFrEF.NEW & NOTEWORTHY Compared with controls, patients with heart failure with reduced ejection fraction (HFrEF) displayed reduced indices of cerebral perfusion at rest and increases in perfusion in response to postexercise circulatory occlusion (PECO, method to isolate muscle metaboreflex activation). This occurred despite similar cardiac output and blood pressure values between groups. Thus, lower resting indices of cerebral perfusion and increased perfusion during sympathoexcitation in HFrEF may occur independently from differences in systemic hemodynamics.

This study aimed to investigate whether reduced cerebral blood flow is associated with cortical brain remodelling in patients with heart failure with reduced ejection fraction (HFrEF). Further, to assess whether these changes occur independently of decreased cardiac output and correlate with alternative markers of HFrEF severity. The findings suggest that brain remodelling in HFrEF can occur independently of reduced cardiac output, highlighting the importance of other pathophysiological factors. A nuanced understanding of these mechanisms could inform improved diagnostic and therapeutic strategies targeting cardiocerebral interactions.

Background Most people do not recognize symptoms of neurological and cardiac emergencies in a timely manner. This leads to delays in hospital arrival and reduced access to therapies that can open arteries. We created a smartphone app to help patients and families evaluate if symptoms may be high risk for stroke or heart attack (myocardial infarction, MI). The ECHAS (Emergency Call for Heart Attack and Stroke) app guides users to assess their risk through evidence-based questions and a test of weakness in one arm by evaluating finger-tapping on the smartphone. Objective This study is an initial step in the accuracy evaluation of the app focused on sensitivity. We evaluated whether the app provides appropriate triage advice for patients with known stroke or MI symptoms in the Emergency Department. We designed this study to evaluate the sensitivity of the app, since the most dangerous output of the app would be failure to recognize the need for emergency evaluation. Specificity is also important, but the consequences of low specificity are less dangerous than those of low sensitivity. Methods In this single-center cross-sectional study, we enrolled patients presenting with symptoms of possible stroke or MI. The ECHAS app assessment consisted of a series of evidence-based questions regarding symptoms and a test of finger-tapping speed and accuracy on the phone’s screen to detect unilateral arm weakness. The primary outcome was the sensitivity of the ECHAS app in detecting the need for ED evaluation. The secondary outcome was the sensitivity of the ECHAS app in detecting the need for hospital admission. Two independent and blinded board-certified physicians reviewed the medical record and adjudicated the appropriateness of the ED visit based on a 5-point score (ground truth). Finally, we asked patients semistructured questions about the app’s ease of use, drawbacks, and benefits. Results We enrolled 202 patients (57 with stroke and 145 with MI). The ECHAS score was strongly correlated with the ground truth appropriateness score (Spearman correlation 0.41, P<.001). The ECHAS app had a sensitivity of 0.98 for identifying patients in whom ED evaluation was appropriate. The app had a sensitivity of 1.0 for identifying patients who were admitted to the hospital because of their ED evaluation. Patients completed an app session in an average of 111 (SD 60) seconds for the stroke pathway and 60 (SD 33) seconds for the MI pathway. Patients reported that the app was easy to use and valuable for personal emergency situations at home. Conclusions The ECHAS app demonstrated a high sensitivity for the detection of patients who required emergency evaluation for symptoms of stroke or MI. This study supports the need for a study of specificity of the app, and then a prospective trial of the app in patients at increased risk of MI and stroke.

The exercise pressor reflex describes the autonomic response that stimulates the cardiovascular system to maintain perfusion of blood flow to working skeletal muscle. However, the exercise pressor reflex is exaggerated in patients with heart failure with reduced ejection fraction (HFrEF) whereas it is blunted in congenital heart disease (CHD). While HFrEF and CHD are clinically diverse, there may be phenotypic overlap that could provide a shared thread for observed pressor responses in these patient groups. Furthermore, the existing evidence on the effect of aging between healthy young (HY) and old (HO) appears to be conflicting.We hypothesized that the pressor response would be blunted with aging and the presence of cardiac conditions. A retrospective analysis of the immediate heart rate (electrocardiography) and mean arterial pressure (finger photoplethysmography) change from rest to during a short (3-5 sec) single bout of maximum voluntary isometric handgrip contraction was performed in HFrEF, CHD, HY, and HO (HFrEF; n =20 (6 F), 61±9 yrs; CHD, n =47 (21 F), 13±3 yrs; HY, n =40 (20 F), 13±3 yrs; HO, n =22 (10 F), 61±6 yrs). Data was analyzed by 2 x 2 ANOVA (health status; healthy and cardiac condition x age; young and old).Data were extracted as the average of three cardiac cycles at rest and a single cardiac cycle at peak systolic blood pressure during MVC. The data revealed heart rate increase from rest to MVC declined with age (8.6±8.1 Δ%, p =0.0004) and health status (8.0±4.8 Δ%, p =0.0023). Multiple comparisons revealed the increase in heart rate from rest to MVC was less in CHD (9.8±5.9 Δ%, p =0.0049), HO (11.2±9.4 Δ%, p =0.0117), and HFrEF (16.9±12.4 Δ%, p <0.0001) than HY. Furthermore, mean arterial pressure increase from rest to MVC declined with age ( p <0.0001), but not health status ( p =0.1086). Lastly, independent sample t-tests revealed MVC was greater in HO than HY (28±13 vs. 15±8 kg, p <0.0001), but not between HO and HFrEF (28±13 vs. 24±10 kg, p =0.2148) nor HY and CHD (15±8 vs. 14±9 kg, p =0.8337). During small skeletal muscle mass contraction at maximal intensity, the pressor response is impaired with aging and the presence of cardiac conditions. Together, these altered cardiovascular responses to exercise may be implicated in the reduced exercise capacity and tolerance known in these respective groups. Saskatchewan Centre for Patient Oriented Research, Heart and Stroke Foundation of Canada This abstract was presented at the American Physiology Summit 2025 and is only available in HTML format. There is no downloadable file or PDF version. The Physiology editorial board was not involved in the peer review process.

Cardiac dysfunction in heart failure with reduced ejection fraction (HFrEF) may contribute to brain atrophy and cognitive decline beyond that which is typical of healthy aging. This study tested the hypothesis that HFrEF would be associated with regionally unique brain remodeling and impaired cognitive performance independent of age. Furthermore, that cardiac index and clinical markers of HFrEF severity would predict brain remodeling and cognition with age and HFrEF, respectively. Cardiac function and brain morphology were assessed using magnetic resonance imaging in young healthy adults (24 ± 6 yr), older healthy adults (60 ± 6 yr), and patients living with HFrEF (59 ± 6 yr). The Montreal Cognitive Assessment was administered to assess cognition. Gray matter volume (GMV) (young: 492 ± 24, old: 456 ± 24, HFrEF: 433 ± 32 cm3, P ≤ 0.05) and cortical thickness (young: 2.44 ± 0.07, old: 2.33 ± 0.08, HFrEF: 2.22 ± 0.10 mm, P < 0.01) were lower with age and lowered further with HFrEF. Regional analysis revealed a unique pattern of atrophy with HFrEF. Whereas age had little effect on cortical curvature (P = 0.60), it was greater in HFrEF (young: 0.127 ± 0.003, old: 0.128 ± 0.003, HFrEF: 0.136 ± 0.005 mm-1, P < 0.01). Cardiac index was the best correlate of brain atrophy and cognitive performance with age (R = 0.33-0.47; P < 0.05). However, EF and end systolic volume index were better correlates of brain atrophy and cognitive performance in HFrEF (R = -0.50-0.49; P ≤ 0.05). These data indicate that lower GMV and cortical thickness in HFrEF are not merely an acceleration of age-related declines but reflect a unique pattern of brain atrophy and remodeling. In addition, classic markers of HF severity may be better predictors of pathological brain remodeling than reduced cardiac index.NEW & NOTEWORTHY Lower gray matter volume, and cortical thinning in heart failure are regionally dependent, and independent of age. Patients living with heart failure had higher cortical curvature, but older adults did not. Lower gray matter volume, cortical thinning, and cognitive impairment were associated with markers of cardiac dysfunction, with ejection fraction, and end systolic volume index being better predictors among the older and heart failure cohort than cardiac index.

Introduction: While timely therapy of neurologic and cardiac emergencies can improve outcomes, patients often fail to identify acute events resulting in delays in seeking emergency care. ECHAS is a smartphone application and sensor system aimed to reduce patient-related delay. We performed a retrospective study to test ECHAS in identifying patients who required emergency assessment for possible myocardial infarction (MI) or stroke. Methods: We enrolled 202 patients (57 with stroke-like, 145 MI-like symptoms) who presented to the ED at a single center in Canada. Participants answered yes-no questions about their prior history, acute symptoms, and performed a finger-tapping test on an Apple iPhone with ECHAS. Answers resulted in a risk score that guided one of the three triage decisions: 1) call 911, 2) call hotline, or 3) call your primary care physician. The ground truth for the triage decision assessment was the appropriateness of the patient’s visit to the ED. Specificity could not be calculated due to low numbers of patients who did not need emergency evaluation. Results: The mean time to complete the acute assessment was 60 seconds for MI and 111 seconds for stroke. ECHAS output recommended 66% of patients call 911, 30% hotline, and 4% primary care follow-up. The sensitivity to identify the need for emergency evaluation was 0.98. The sensitivity to identify patients who were admitted for possible MI or stroke was 1.0. A negative correlation was found between low ECHAS score and prolonged symptom onset to hospital arrival time for MI-like symptoms (r = -0.21, p < 0.05). Patients found ECHAS to be very useable (Fig 1). Conclusion: The ECHAS application was highly sensitive and easily usable in guiding patients to identify medical emergencies without input by healthcare personnel. These pilot results will drive a planned 4,000-patient prospective randomized trial to evaluate whether ECHAS will reduce times from symptom onset to first medical contact for MI and stroke.

BackgroundIn patients presenting with an acute coronary syndrome (ACS), the impact of efforts leveraged at bridging historical care gaps between Indigenous and non-Indigenous patients remains limited.MethodsFor consecutive ACS presentations (STEMI and NSTEMI/UA, respectively) at the Royal University Hospital, Saskatoon, we compared between self-identified Indigenous and non-Indigenous patients their demographics, treatments and all-cause mortality (in-hospital and 3-years). We used propensity score-inverse probability weighting to mitigate confounding, and Cox regression models to estimate the adjusted hazard (aHR, 95% confidence intervals) for all-cause mortality.ResultsOf 3946 ACS patients, 37.2% (n=1468) were STEMI of whom 11.3% (n=166) were Indigenous. Of the NSTEMI/UA (n=2478), 12.6% (n=311) were Indigenous. Overall, Indigenous compared with non-Indigenous patients were likely to be younger, female, have higher risk burden, and lived more remotely; Indigenous STEMI patients triaged to primary PCI had longer first medical contact-to-device times, while Indigenous NSTEMI/UA patients more likely to present with heart failure, cardiac arrest and/or cardiogenic shock.No significant differences were noted for in-hospital mortality (STEMI 8.4% vs 5.7%, p= 0.16; NSTEMI/UA 1.9% vs 1.6%, p=0.68), however, in follow-up, Indigenous STEMI patients associated with a higher all-cause mortality risk (aHR 1.98, 95% CI 1.19, 3.31, p=0.009) with no between-group differences evident for NSTEMI/UA (aHR 1.03, 95% CI 0.63 1.69, p=0.91).ConclusionsIndigenous compared with non-Indigenous patients presenting with an ACS had higher cardiovascular risk profiles, and consequently residual mortality risk. Improving primary care and intensifying secondary risk reduction, and particularly so for Indigenous patients, will substantially modify ACS outcomes in Saskatchewan.

Patients with heart failure with reduced ejection fraction (HFrEF) have exaggerated sympathoexcitation and impaired peripheral vascular conductance. Evidence demonstrating consequent impaired functional sympatholysis is limited in HFrEF. This study aimed to determine the magnitude of reduced limb vascular conductance during sympathoexcitation and whether functional sympatholysis would abolish such reductions in HFrEF. Twenty patients with HFrEF and 22 age-matched controls performed the cold pressor test (CPT) [left foot 2-min in -0.5 (1)degrees C water] alone and with right handgrip exercise (EX + CPT). Right forearm vascular conductance (FVC), forearm blood flow (FBF), and mean arterial pressure (MAP) were measured. Patients with HFrEF had greater decreases in %Delta FVC and %Delta FBF during CPT (both P < 0.0001) but not EX + CPT (P = 0.449, P = 0.199) compared with controls, respectively. %Delta FVC and %Delta FBF decreased from CPT to EX + CPT in patients with HFrEF (both P < 0.0001) and controls (P = 0.018, P = 0.015), respectively. MAP increased during CPT and EX + CPT in both groups (all P < 0.0001). MAP was greater in controls than in patients with HFrEF during EX + CPT (P = 0.025) but not CPT (P = 0.209). In conclusion, acute sympathoexcitation caused exaggerated peripheral vasoconstriction and reduced peripheral blood flow in patients with HFrEF. Handgrip exercise abolished sympathoexcitatory-mediated peripheral vasoconstriction and normalized peripheral blood flow in patients with HFrEF. These novel data reveal intact functional sympatholysis in the upper limb and suggest that exercise-mediated, local control of blood flow is preserved when cardiac limitations that are cardinal to HFrEF are evaded with dynamic handgrip exercise. NEW & NOTEWORTHY Patients with HFrEF demonstrate impaired peripheral blood flow regulation, evidenced by heightened peripheral vasoconstriction that reduces limb blood flow in response to physiological sympathoexcitation (cold pressor test). Despite evidence of exaggerated sympathetic vasoconstriction, patients with HFrEF demonstrate a normal hyperemic response to moderate-intensity handgrip exercise. Most importantly, acute, simultaneous handgrip exercise restores normal limb vasomotor control and vascular conductance during acute sympathoexcitation (cold pressor test), suggesting intact functional sympatholysis in patients with HFrEF.

Chest pain/discomfort (CP) is a common symptom and can be a diagnostic dilemma for many clinicians. The misdiagnosis of an acute or progressive chronic cardiac etiology may carry a significant risk of morbidity and mortality. This review summarizes the different options and modalities for establishing the diagnosis and severity of coronary artery disease. An effective test selection algorithm should be individually tailored to each patient to maximize diagnostic accuracy in a timely fashion, determine short- and long-term prognosis, and permit implementation of evidence-based treatments in a cost-effective manner. Through collaboration, a decision algorithm was developed (www.chowmd.ca/cadtesting) that could be adopted widely into clinical practice.

BACKGROUND:Acute cellular rejection (ACR), an alloimmune response involving CD4+ and CD8+ T cells, occurs in up to 20% of patients within the first year following heart transplantation. The balance between a conventional versus regulatory CD4+ T cell alloimmune response is believed to contribute to developing ACR. Therefore, tracking these cells may elucidate whether changes in these cell populations could signal ACR risk.METHODS:We used a CD4+ T cell gene signature (TGS) panel that tracks CD4+ conventional T cells (Tconv) and regulatory T cells (Treg) on longitudinal samples from 94 adult heart transplant recipients. We evaluated combined diagnostic performance of the TGS panel with a previously developed biomarker panel for ACR diagnosis, HEARTBiT, while also investigating TGS' prognostic utility.RESULTS:Compared with nonrejection samples, rejection samples showed decreased Treg- and increased Tconv-gene expression. The TGS panel was able to discriminate between ACR and nonrejection samples and, when combined with HEARTBiT, showed improved specificity compared with either model alone. Furthermore, the increased risk of ACR in the TGS model was associated with lower expression of Treg genes in patients who later developed ACR. Reduced Treg gene expression was positively associated with younger recipient age and higher intrapatient tacrolimus variability.CONCLUSIONS:We demonstrated that expression of genes associated with CD4+ Tconv and Treg could identify patients at risk of ACR. In our post hoc analysis, complementing HEARTBiT with TGS resulted in an improved classification of ACR. Our study suggests that HEARTBiT and TGS may serve as useful tools for further research and test development.

Stroke volume decreases and end-systolic volume increases during muscle metaboreflex activation in patients with heart failure with reduced ejection fraction (HFrEF), suggesting impaired contractile reserve during muscle metaboreflex activation in patients with HFrEF. Total peripheral resistance increases similarly during muscle metaboreflex activation in patients with HFrEF compared to controls, indicating normal levels of peripheral vasoconstriction during muscle metaboreflex activation in patients with HFrEF.

Heart failure with reduced ejection fraction is associated with increased exercise intolerance, morbidity, and mortality. Importantly, exercise intolerance in heart failure with reduced ejection fraction is a key factor limiting patient quality of life and survival. Exercise intolerance in heart failure with reduced ejection fraction stems from a multi-organ failure to maintain homeostasis at rest and during exercise, including the heart, skeletal muscle, and autonomic nervous system, lending itself to a system constantly trying to “catch-up”. Hemodynamic control during exercise is regulated primarily by the autonomic nervous system, whose operation, in turn, is partly regulated via reflexive information from exercise-stimulated receptors throughout the body (e.g., arterial baroreflex, central and peripheral chemoreceptors, and the muscle metabo- and mechanoreflexes). Persons with heart failure with reduced ejection fraction exhibit malfunctioning autonomic reflexes, which lead to exaggerated sympathoexcitation and attenuated parasympathetic tone. Chronic elevation of sympathetic activity is associated with increased morbidity and mortality. In this review, we provide an overview of how each main exercise-related autonomic reflex is changed in heart failure with reduced ejection fraction, and the role of exercise training in attenuating or reversing the counterproductive changes.

Immediately following the simultaneous cessation of HG and CPT, young but not older adults demonstrate a transient reduction in brachial artery diameter, indicative of reduced vasoreactivity.

Metformin-associated lactic acidosis occurs very infrequently; however, with the significantly greater comorbidity burden and acuity of patients with diabetes undergoing coronary angiography/angioplasty (CA), the inherent risk of metformin-associated lactic acidosis may be significantly increased. Additionally, significant variations in contemporary practice pattern around peri-CA metformin use still continue to exist. This is a pilot, single-center, open-labelled, randomized comparison of metformin continuation or 48-hour interruption following CA (Saskatoon, Clinical Trials.gov 03980990). All patients had metformin continued to the time of the angiogram. Patients presenting with cardiogenic shock, cardiac arrest, history of chronic liver disease, severe chronic kidney disease (eGFR<30 or on dialysis) or requiring coronary artery bypass graft surgery following CA were ineligible for inclusion. Planned enrollment of 500 patients had been anticipated for the calendar year (June 2019-June 2020), and stratified at randomization by in/out-patient status. The primary outcome included lactic acidosis (lactate ≥5mmol/L ± bicarbonate <18mmol/l) at 48-72 hours after CA. Key secondary outcomes included: absolute lactate levels, acute kidney injury (AKI, ≥25% or 27μmol/L rise at 48-72 hours) and all-cause mortality at 1-week. Continuous variables are expressed as medians (25th, 75th percentile) and categorical variables as frequency (%). At study interruption (March 12/20, COVID-19) 312 patients had been randomized, of whom 52% presented with an acute coronary syndrome (n= 161/312; STEMI 11%). Baseline characteristics were balanced across the two groups, including the proportion treated with PCI (Table 1). Follow up lactate levels were available in: continued arm 71% (n=112/157), interrupt arm 67% (n=104/155). No patients in either arm had serum lactate ≥5mmol/L, however, metformin continuation compared with a 48-hour interruption had significantly higher median lactate levels (1.70 [1.15, 2.2] vs. 1.40 [1.2, 1.8], p=0.02); no between-group differences were evident for serum bicarbonate (26.0 [24, 28] mmol/L vs. 25.0 [24, 27] mmol/l, p=0.15). No differences were evident in the rates of AKI (7.7% vs. 8.3% p= 1.0). No patients died in either treatment arm at 1-week (vital status available for all 312 patients). Conclusion: In this interim analysis of contemporary treated patients with diabetes, all of whom had metformin continued up to CA, metformin continuation compared with a 48-hour interruption was not associated with clinically relevant lactic acidosis. Continued metformin use however appears to associate with higher 48-72-hour lactate levels, without differences in AKI or all-cause mortality at 1-week. Trial completion is anticipated with COVID-19 pandemic resolution.

Heart failure (HF) is the most rapidly increasing cardiovascular disease globally and is associated with high rates of morbidity and mortality and high burden on health systems. 1 Ziaeian B. Fonarow G.C. Epidemiology and aetiology of heart failure. Nat Rev Cardiol. 2016; 13: 368-378 Crossref PubMed Scopus (580) Google Scholar HF is a clinical syndrome defined hemodynamically by the inability of the heart to pump blood at a rate commensurate with metabolic demands or the ability of the heart to meet metabolic demands only with high filling pressures. 2 Pfeffer M.A. Shah A.M. Borlaug B.A. Heart failure with preserved ejection fraction in perspective. Circ Res. 2019; 124: 1598-1617 Crossref PubMed Scopus (178) Google Scholar There remains no single diagnostic test for the diagnosis of HF, and history, physical examination, laboratory markers, and imaging are integrated to establish a diagnosis and guide clinical management. 3 Ezekowitz J.A. O'Meara E. McDonald M.A. et al. 2017 comprehensive update of the Canadian Cardiovascular Society guidelines for the management of heart failure. Can J Cardiol. 2017; 33: 1342-1433 Abstract Full Text Full Text PDF PubMed Scopus (307) Google Scholar Deep Learning for Detection of Elevated Pulmonary Artery Wedge Pressure Using Standard Chest X-RayCanadian Journal of CardiologyVol. 37Issue 8PreviewTo accurately diagnose and control heart failure (HF), it is important to carry out a simple assessment of elevated pulmonary arterial wedge pressure (PAWP). The aim of this study was to develop and validate an objective method for detecting elevated PAWP by applying deep learning (DL) to a chest x-ray (CXR). Full-Text PDF