Impact of epicardial fat on coronary vascular function, cardiac morphology, and cardiac function in women with suspected INOCA.

INTRODUCTION: Epicardial fat is a metabolically active adipose tissue depot situated between the myocardium and visceral pericardium that covers ∼80% of the heart surface. While epicardial fat has been associated with the development of atherosclerotic coronary artery disease (CAD), less is known about the relationship between epicardial fat and coronary vascular function. Moreover, the relations between excess epicardial fat and cardiac morphology and function remains incompletely understood. METHODS AND RESULTS: To address these knowledge gaps, we retrospectively analyzed data from 294 individuals from our database of women with suspected ischemia with no obstructive coronary disease (INOCA) who underwent both invasive coronary function testing and cardiac magnetic resonance imaging (cMRI). Epicardial fat area, biventricular morphology, and function, as well as left atrial function, were assessed from cine images, per established protocols. The major novel findings were twofold: First, epicardial fat area was not associated with coronary vascular dysfunction. Second, epicardial fat was associated with increased left ventricular concentricity (ß= 0.15, p= 0.01), increased septal thickness (ß= 0.17, p= 0.002), and reduced left atrial conduit fraction (ß= -0.15, p= 0.02), even after accounting for age, BMI, and history of hypertension. CONCLUSIONS: Taken together, these data do not support a measurable relationship between epicardial fat and coronary vascular dysfunction but does suggest that epicardial fat may be related to concentric remodeling and diastolic dysfunction in women with suspected INOCA. Prospective studies are needed to elucidate the long-term impact of epicardial fat in this patient population.

Workflow and Framework for Collecting and Implementing Point-of-Care Ultrasound Data in the Management of Heart Failure Patients.

Management and prevention of acute decompensated heart failure remain highly prevalent and challenging medical conditions. Incorporation of Point-of-Care Ultrasound (POCUS) as an adjunctive tool for assessing volume status and treatment response has shown significant promise. POCUS can be used for imaging internal anatomic structures serially and capturing these images for comparison and measurement over time. This protocol describes a scalable and standardized methodology for the serial assessment of the inferior vena cava (IVC). The methodology includes serial image collection, measurement, and presentation in the electronic medical record. A workflow for POCUS-acquired images of the IVC was created to capture the images and measure the diameter in a discrete data field for direct comparison over time and in response to clinical management. The protocol also includes the assessment of the presence or absence of pleural effusion as discrete data in the standardized workflow. By integrating POCUS into heart failure management, clinicians can improve patient outcomes through more precise and timely adjustments in treatment.

Deep Learning Phenotyping of Tricuspid Regurgitation for Automated High Throughput Assessment of Transthoracic Echocardiography.

Background and Aims: Diagnosis of tricuspid regurgitation (TR) requires careful expert evaluation. This study developed an automated deep learning pipeline for assessing TR from transthoracic echocardiography. Methods: An automated deep learning workflow was developed using 47,312 studies (2,079,898 videos) from Cedars-Sinai Medical Center (CSMC) between 2011 and 2021. The pipeline was tested on a temporally distinct test set of 2,462 studies (108,138 videos) obtained in 2022 at CSMC and a geographically distinct cohort of 5,549 studies (278,377 videos) from Stanford Healthcare (SHC). Results: In the CSMC test dataset, the view classifier demonstrated an AUC of 1.000 (0.999 - 1.000) and identified at least one A4C video with colour Doppler across the tricuspid valve in 2,410 of 2,462 studies with a sensitivity of 0.975 (0.968-0.982) and a specificity of 1.000 (1.00-1.000). In the CSMC test cohort, moderate-or-severe TR was detected with an AUC of 0.928 (0.913 - 0.943) and severe TR was detected with an AUC of 0.956 (0.940 - 0.969). In the SHC cohort, the view classifier correctly identified at least one TR colour Doppler video in 5,268 of the 5,549 studies, resulting in an AUC of 0.999 (0.998 - 0.999), a sensitivity of 0.949 (0.944 - 0.955) and specificity of 0.999 (0.999 - 0.999). The AI model detected moderate-or-severe TR with an AUC of 0.951 (0.938 - 0.962) and severe TR with an AUC of 0.980 (0.966 - 0.988). Conclusions: We developed an automated pipeline to identify clinically significant TR with excellent performance. This approach carries potential for automated TR detection and stratification for surveillance and screening. Key Question: Can an automated deep learning model assess tricuspid regurgitation severity from echocardiography? Key Finding: We developed and validated an automated tricuspid regurgitation detection algorithm pipeline across two healthcare systems with high volume echocardiography labs. The algorithm correctly identifies apical-4-chamber view videos with colour Doppler across the tricuspid valve and grades clinically significant TR with strong agreement to expert clinical readers. Take Home message: A deep learning pipeline could automate TR screening, facilitating reproducible accurate assessment of TR severity, allowing rapid triage or re-review and expand access in low-resource or primary care settings.

Opportunistic Screening of Chronic Liver Disease with Deep Learning Enhanced Echocardiography.

Importance: Chronic liver disease affects more than 1.5 billion adults worldwide, however the majority of cases are asymptomatic and undiagnosed. Echocardiography is broadly performed and visualizes the liver; but this information is not leveraged. Objective: To develop and evaluate a deep learning algorithm on echocardiography videos to enable opportunistic screening for chronic liver disease. Design: Retrospective observational cohorts. Setting: Two large urban academic medical centers. Participants: Adult patients who received echocardiography and abdominal imaging (either abdominal ultrasound or abdominal magnetic resonance imaging) with ≤30 days between tests, between July 4, 2012, to June 4, 2022. Exposure: Deep learning model predictions from a deep-learning computer vision pipeline that identifies subcostal view echocardiogram videos and detects the presence of cirrhosis or steatotic liver disease (SLD). Main Outcome and Measures: Clinical diagnosis by paired abdominal ultrasound or magnetic resonance imaging (MRI). Results: A total of 1,596,640 echocardiogram videos (66,922 studies from 24,276 patients) from Cedars-Sinai Medical Center (CSMC) were used to develop EchoNet-Liver, an automated pipeline that identifies high quality subcostal images from echocardiogram studies and detects the presence of cirrhosis or SLD. In the held-out CSMC test cohort, EchoNet-Liver was able to detect the presence of cirrhosis with an AUC of 0.837 (0.789 - 0.880) and SLD with an AUC of 0.799 (0.758 - 0.837). In a separate test cohort with paired abdominal MRIs, cirrhosis was detected with an AUC of 0.704 (0.689-0.718) and SLD was detected with an AUC of 0.726 (0.659-0.790). In an external test cohort of 106 patients (n = 5,280 videos), the model detected cirrhosis with an AUC of 0.830 (0.738 - 0.909) and SLD with an AUC of 0.768 (0.652 - 0.875). Conclusions and Relevance: Deep learning assessment of clinical echocardiography enables opportunistic screening of SLD and cirrhosis. Application of this algorithm may identify patients who may benefit from further diagnostic testing and treatment for chronic liver disease.

Alternating low-rank tensor reconstruction for improved multiparametric mapping with cardiovascular MR Multitasking.

PURPOSE: To develop a novel low-rank tensor reconstruction approach leveraging the complete acquired data set to improve precision and repeatability of multiparametric mapping within the cardiovascular MR Multitasking framework. METHODS: A novel approach that alternated between estimation of temporal components and spatial components using the entire data set acquired (i.e., including navigator data and imaging data) was developed to improve reconstruction. The precision and repeatability of the proposed approach were evaluated on numerical simulations, 10 healthy subjects, and 10 cardiomyopathy patients at multiple scan times for 2D myocardial T1/T2 mapping with MR Multitasking and were compared with those of the previous navigator-derived fixed-basis approach. RESULTS: In numerical simulations, the proposed approach outperformed the previous fixed-basis approach with lower T1 and T2 error against the ground truth at all scan times studied and showed better motion fidelity. In human subjects, the proposed approach showed no significantly different sharpness or T1/T2 measurement and significantly improved T1 precision by 20%-25%, T2 precision by 10%-15%, T1 repeatability by about 30%, and T2 repeatability by 25%-35% at 90-s and 50-s scan times The proposed approach at the 50-s scan time also showed comparable results with that of the previous fixed-basis approach at the 90-s scan time. CONCLUSION: The proposed approach improved precision and repeatability for quantitative imaging with MR Multitasking while maintaining comparable motion fidelity, T1/T2 measurement, and septum sharpness and had the potential for further reducing scan time from 90 s to 50 s.

Multi-Organ System Metabolic Stress and Sex-Divergent Vascular Associations.

Introduction: Women experience excess cardiovascular risk compared to men in the setting of similar metabolic disease burden. This consistent finding could be related to sex differences in the vascular response to various forms of metabolic stress. In this study we examine the association of both systemic and organ-specific metabolic stress with vascular health in women and men. Methods: We conducted an observational study of 4,299 adult participants (52% women, aged 59±13 years) of the National Health and Nutrition Examination Survey (NHANES) 2017-2018 cohort and 110,225 adult outpatients (55% women, aged 64±16 years) of the Cedars-Sinai Medical Center (CSMC) 2019 cohort. We used natural splines to examine the association of systemic and organ-specific measures of metabolic stress including body mass index (BMI), hemoglobin A1c (HbA1c), hepatic FIB-4 score, and CKD-EPI estimated glomerular filtration rate (eGFR) on systolic blood pressure (SBP). Piecewise linear models were generated using normal value thresholds (BMI <25 kg/m 2 , HbA1c <5.7%, FIB-4 <1.3, and eGFR ≥90 ml/min), which approximated observed spline breakpoints. The primary outcome was increase in SBP (relative to a sex-specific physiologic baseline SBP) in association with increase in level of each metabolic measure. Results: Women compared to men demonstrated larger magnitudes and an earlier onset of increase in SBP per increment increase across all metabolic stress measures. The slope of SBP increase per increment of each metabolic measure was greater for women than men particularly for metabolic measures within the normal range, with slope differences of 1.71 mmHg per kg/m2 of BMI, 9.61 mmHg per %HbA1c, 6.45 mmHg per FIB-4 unit, and 0.37 mmHg per ml/min decrement of eGFR in the NHANES cohort (P difference <0.05 for all). Overall results were consistent in the CSMC cohort. Conclusions: Women exhibited greater vascular sensitivity in the setting of multiple types of metabolic stress, particularly in periods representing the transition from metabolic health to disease. These findings underscore the importance of involving early metabolic health interventions as part of efforts to mitigate vascular risks in both women and men.

Using Deep learning to Predict Cardiovascular Magnetic Resonance Findings from Echocardiography Videos.

Background: Echocardiography is the most common modality for assessing cardiac structure and function. While cardiac magnetic resonance (CMR) imaging is less accessible, CMR can provide unique tissue characterization including late gadolinium enhancement (LGE), T1 and T2 mapping, and extracellular volume (ECV) which are associated with tissue fibrosis, infiltration, and inflammation. While deep learning has been shown to uncover findings not recognized by clinicians, it is unknown whether CMR-based tissue characteristics can be derived from echocardiography videos using deep learning. We hypothesized that deep learning applied to echocardiography could predict CMR-based measurements. Methods: In a retrospective single-center study, adult patients with CMRs and echocardiography studies within 30 days were included. A video-based convolutional neural network was trained on echocardiography videos to predict CMR-derived labels including wall motion abnormality (WMA) presence, LGE presence, and abnormal T1, T2 or ECV across echocardiography views. The model performance was evaluated in a held-out test dataset not used for training. Results: The study population included 1,453 adult patients (mean age 56±18 years, 42% female) with 2,556 paired echocardiography studies occurring on average 2 days after CMR (interquartile range 2 days prior to 6 days after). The model had high predictive capability for presence of WMA (AUC 0.873 [95%CI 0.816-0.922]), however, the model was unable to reliably detect the presence of LGE (AUC 0.699 [0.613-0.780]), native T1 (AUC 0.614 [0.500-0.715]), T2 0.553 [0.420-0.692], or ECV 0.564 [0.455-0.691]). Conclusions: Deep learning applied to echocardiography accurately identified CMR-based WMA, but was unable to predict tissue characteristics, suggesting that signal for these tissue characteristics may not be present within ultrasound videos, and that the use of CMR for tissue characterization remains essential within cardiology. Clinical Perspective: Tissue characterization of the heart muscle is useful for clinical diagnosis and prognosis by identifying myocardial fibrosis, inflammation, and infiltration, and can be measured using cardiac MRI. While echocardiography is highly accessible and provides excellent functional information, its ability to provide tissue characterization information is limited at this time. Our study using a deep learning approach to predict cardiac MRI-based tissue characteristics from echocardiography showed limited ability to do so, suggesting that alternative approaches, including non-deep learning methods should be considered in future research.

Early-Onset Hypertension and Sex-Specific Residual Risk for Cardiovascular Disease in Type 2 Diabetes.

OBJECTIVE: To investigate whether the sex disparities in type 2 diabetes-associated cardiovascular disease (CVD) risks may be related to early-onset hypertension that could benefit from intensive blood pressure (BP) control. RESEARCH DESIGN AND METHODS: We analyzed intensive versus standard BP control in relation to incident CVD events in women and men with type 2 diabetes, based on their age of hypertension diagnosis. RESULTS: Among 3,792 adults with type 2 diabetes (49% women), multivariable-adjusted CVD risk was increased per decade earlier age at hypertension diagnosis (hazard ratio 1.11 [1.03-1.21], P = 0.006). Excess risk associated with early-diagnosed hypertension was attenuated in the presence of intensive versus standard antihypertensive therapy in women (P = 0.036) but not men (P = 0.76). CONCLUSIONS: Women with type 2 diabetes and early-onset hypertension may represent a higher-risk subpopulation that not only contributes to the excess in diabetes-related CVD risk for women but may benefit from intensive BP control.

Point of Care Ultrasound for Diagnosis and Management in Heart Failure: A Targeted Literature Review.

BACKGROUND: Cardiac point of care ultrasound (POCUS) has shown increasing utility as a tool for diagnosing and managing heart failure (HF). Within cardiology, intravascular volume assessment leveraging visualization of the inferior vena cava (IVC) is a central aspect of care, as IVC size correlates with central venous pressure. This targeted literature review aimed to examine the existing literature assessing the use of POCUS in diagnosis and management of HF patients utilizing POCUS-based IVC measurement either alone or in combination with secondary methods. METHODS: A targeted PubMed and Ovid database search up until August 28, 2023 using a keyword search was completed. Studies that did not include IVC assessment with POCUS in HF were excluded. RESULTS: The initial search using both PubMed and Ovid resulted in 370 journal publications. After exclusion criteria were used 15 studies were included in the review. Studies were grouped into three categories: 1) how well POCUS was able to identify HF, 2) whether POCUS-based findings correlated with other measures evaluating HF and was able to predict the effect of diuretic administration, and 3) whether POCUS-based findings served as a good prognostic indicator. The 5 studies that evaluated HF identification with POCUS found that both diagnostic sensitivity and specificity may reach 90%-100% when IVC measurement was coupled with a lung ultrasound assessing the presence of B-lines or pleural effusion. Five studies assessing POCUS findings correlating with other HF measures and diuretic effect found that IVC diameter changed significantly with diuretic administration (p<0.05). All 6 studies assessing POCUS as a predictor of long-term mortality or hospital readmission found measures that achieved statistical significance with p<0.05. CONCLUSIONS: Including POCUS as standard-of-care - both as a diagnostic tool in the emergency department and a management tool in in-patient and out-patient facilities - may improve the treatment of HF.

Deep Learning-Derived Myocardial Strain.

BACKGROUND: Echocardiographic strain measurements require extensive operator experience and have significant intervendor variability. Creating an automated, open-source, vendor-agnostic method to retrospectively measure global longitudinal strain (GLS) from standard echocardiography B-mode images would greatly improve post hoc research applications and may streamline patient analyses. OBJECTIVES: This study was seeking to develop an automated deep learning strain (DLS) analysis pipeline and validate its performance across multiple applications and populations. METHODS: Interobserver/-vendor variation of traditional GLS, and simulated effects of variation in contour on speckle-tracking measurements were assessed. The DLS pipeline was designed to take semantic segmentation results from EchoNet-Dynamic and derive longitudinal strain by calculating change in the length of the left ventricular endocardial contour. DLS was evaluated for agreement with GLS on a large external dataset and applied across a range of conditions that result in cardiac hypertrophy. RESULTS: In patients scanned by 2 sonographers using 2 vendors, GLS had an intraclass correlation of 0.29 (95% CI: -0.01 to 0.53, P = 0.03) between vendor measurements and 0.63 (95% CI: 0.48-0.74, P < 0.001) between sonographers. With minor changes in initial input contour, step-wise pixel shifts resulted in a mean absolute error of 3.48% and proportional strain difference of 13.52% by a 6-pixel shift. In external validation, DLS maintained moderate agreement with 2-dimensional GLS (intraclass correlation coefficient [ICC]: 0.56, P = 0.002) with a bias of -3.31% (limits of agreement: -11.65% to 5.02%). The DLS method showed differences (P < 0.0001) between populations with cardiac hypertrophy and had moderate agreement in a patient population of advanced cardiac amyloidosis: ICC was 0.64 (95% CI: 0.53-0.72), P < 0.001, with a bias of 0.57%, limits of agreement of -4.87% to 6.01% vs 2-dimensional GLS. CONCLUSIONS: The open-source DLS provides lower variation than human measurements and similar quantitative results. The method is rapid, consistent, vendor-agnostic, publicly released, and applicable across a wide range of imaging qualities.

Machine Learning and Bias in Medical Imaging: Opportunities and Challenges.

Bias in health care has been well documented and results in disparate and worsened outcomes for at-risk groups. Medical imaging plays a critical role in facilitating patient diagnoses but involves multiple sources of bias including factors related to access to imaging modalities, acquisition of images, and assessment (ie, interpretation) of imaging data. Machine learning (ML) applied to diagnostic imaging has demonstrated the potential to improve the quality of imaging-based diagnosis and the precision of measuring imaging-based traits. Algorithms can leverage subtle information not visible to the human eye to detect underdiagnosed conditions or derive new disease phenotypes by linking imaging features with clinical outcomes, all while mitigating cognitive bias in interpretation. Importantly, however, the application of ML to diagnostic imaging has the potential to either reduce or propagate bias. Understanding the potential gain as well as the potential risks requires an understanding of how and what ML models learn. Common risks of propagating bias can arise from unbalanced training, suboptimal architecture design or selection, and uneven application of models. Notwithstanding these risks, ML may yet be applied to improve gain from imaging across all 3A's (access, acquisition, and assessment) for all patients. In this review, we present a framework for understanding the balance of opportunities and challenges for minimizing bias in medical imaging, how ML may improve current approaches to imaging, and what specific design considerations should be made as part of efforts to maximize the quality of health care for all.

Sex Differences in Association of Physical Activity With All-Cause and Cardiovascular Mortality.

BACKGROUND: Although physical activity is widely recommended for reducing cardiovascular and all-cause mortality risks, female individuals consistently lag behind male individuals in exercise engagement. OBJECTIVES: The goal of this study was to evaluate whether physical activity derived health benefits may differ by sex. METHODS: In a prospective study of 412,413 U.S. adults (55% female, age 44 ± 17 years) who provided survey data on leisure-time physical activity, we examined sex-specific multivariable-adjusted associations of physical activity measures (frequency, duration, intensity, type) with all-cause and cardiovascular mortality from 1997 through 2019. RESULTS: During 4,911,178 person-years of follow-up, there were 39,935 all-cause deaths including 11,670 cardiovascular deaths. Regular leisure-time physical activity compared with inactivity was associated with 24% (HR: 0.76; 95% CI: 0.73-0.80) and 15% (HR: 0.85; 95% CI: 0.82-0.89) lower risk of all-cause mortality in women and men, respectively (Wald F = 12.0, sex interaction P < 0.001). Men reached their maximal survival benefit of HR 0.81 from 300 min/wk of moderate-to-vigorous physical activity, whereas women achieved similar benefit at 140 min/wk and then continued to reach a maximum survival benefit of HR 0.76 also at ∼300 min/wk. Sex-specific findings were similar for cardiovascular death (Wald F = 20.1, sex interaction P < 0.001) and consistent across all measures of aerobic activity as well as muscle strengthening activity (Wald F = 6.7, sex interaction P = 0.009). CONCLUSIONS: Women compared with men derived greater gains in all-cause and cardiovascular mortality risk reduction from equivalent doses of leisure-time physical activity. These findings could enhance efforts to close the "gender gap" by motivating especially women to engage in any regular leisure-time physical activity.

Postural orthostatic tachycardia syndrome after COVID-19 vaccination.

BACKGROUND: There is an association between coronavirus disease 2019 (COVID-19) mRNA vaccination and the incidence or exacerbation of postural orthostatic tachycardia syndrome (POTS). OBJECTIVE: The purpose of this study was to characterize patients reporting new or exacerbated POTS after receiving the mRNA COVID-19 vaccine. METHODS: We prospectively collected data from sequential patients in a POTS clinic between July 2021 and June 2022 reporting new or exacerbated POTS symptoms after COVID-19 vaccination. Heart rate variability (HRV) and skin sympathetic nerve activity (SKNA) were compared against those of 24 healthy controls. RESULTS: Ten patients (6 women and 4 men; age 41.5 ± 7.9 years) met inclusion criteria. Four patients had standing norepinephrine levels > 600 pg/mL. All patients had conditions that could raise POTS risk, including previous COVID-19 infection (N = 4), hypermobile Ehlers-Danlos syndrome (N = 6), mast cell activation syndrome (N = 6), and autoimmune (N = 7), cardiac (N = 7), neurological (N = 6), or gastrointestinal conditions (N = 4). HRV analysis indicated a lower ambulatory root mean square of successive differences (46.19 ±24 ms; P = .042) vs control (72.49 ± 40.8 ms). SKNA showed a reduced mean amplitude (0.97 ± 0.052 µV; P = .011) vs control (1.2 ± 0.31 µV) and burst amplitude (1.67 ± 0.16 µV; P = .018) vs control (4. 3 ± 4.3 µV). After 417.2 ± 131.4 days of follow-up, all patients reported improvement with the usual POTS care, although 2 with COVID-19 reinfection and 1 with small fiber neuropathy did have relapses of POTS symptoms. CONCLUSION: All patients with postvaccination POTS had pre-existing conditions. There was no evidence of myocardial injuries or echocardiographic abnormalities. The decreased HRV suggests a sympathetic dominant state. Although all patients improved with guideline-directed care, there is a risk of relapse.

Impact of Measurement Noise on Genetic Association Studies of Cardiac Function.

Recent research has effectively used quantitative traits from imaging to boost the capabilities of genome-wide association studies (GWAS), providing further understanding of disease biology and various traits. However, it's important to note that phenotyping inherently carries measurement error and noise that could influence subsequent genetic analyses. The study focused on left ventricular ejection fraction (LVEF), a vital yet potentially inaccurate quantitative measurement, to investigate how imprecision in phenotype measurement affects genetic studies. Several methods of acquiring LVEF, along with simulating measurement noise, were assessed for their effects on ensuing genetic analyses. The results showed that by introducing just 7.9% of measurement noise, all genetic associations in an LVEF GWAS with almost forty thousand individuals could be eliminated. Moreover, a 1% increase in mean absolute error (MAE) in LVEF had an effect equivalent to a 10% reduction in the sample size of the cohort on the power of GWAS. Therefore, enhancing the accuracy of phenotyping is crucial to maximize the effectiveness of genome-wide association studies.

Deriving Convergent and Divergent Metabolomic Correlates of Pulmonary Arterial Hypertension.

High-dimensional metabolomics analyses may identify convergent and divergent markers, potentially representing aligned or orthogonal disease pathways that underly conditions such as pulmonary arterial hypertension (PAH). Using a comprehensive PAH metabolomics dataset, we applied six different conventional and statistical learning techniques to identify analytes associated with key outcomes and compared the results. We found that certain conventional techniques, such as Bonferroni/FDR correction, prioritized metabolites that tended to be highly intercorrelated. Statistical learning techniques generally agreed with conventional techniques on the top-ranked metabolites, but were also more inclusive of different metabolite groups. In particular, conventional methods prioritized sterol and oxylipin metabolites in relation to idiopathic versus non-idiopathic PAH, whereas statistical learning methods tended to prioritize eicosanoid, bile acid, fatty acid, and fatty acyl ester metabolites. Our findings demonstrate how conventional and statistical learning techniques can offer both concordant or discordant results. In the case of a rare yet morbid condition, such as PAH, convergent metabolites may reflect common pathways to shared disease outcomes whereas divergent metabolites could signal either distinct etiologic mechanisms, different sub-phenotypes, or varying stages of disease progression. Notwithstanding the need to investigate the mechanisms underlying the observed results, our main findings suggest that a multi-method approach to statistical analyses of high-dimensional human metabolomics datasets could effectively broaden the scientific yield from a given study design.

Deep learning-based electrocardiographic screening for chronic kidney disease.

BACKGROUND: Undiagnosed chronic kidney disease (CKD) is a common and usually asymptomatic disorder that causes a high burden of morbidity and early mortality worldwide. We developed a deep learning model for CKD screening from routinely acquired ECGs. METHODS: We collected data from a primary cohort with 111,370 patients which had 247,655 ECGs between 2005 and 2019. Using this data, we developed, trained, validated, and tested a deep learning model to predict whether an ECG was taken within one year of the patient receiving a CKD diagnosis. The model was additionally validated using an external cohort from another healthcare system which had 312,145 patients with 896,620 ECGs between 2005 and 2018. RESULTS: Using 12-lead ECG waveforms, our deep learning algorithm achieves discrimination for CKD of any stage with an AUC of 0.767 (95% CI 0.760-0.773) in a held-out test set and an AUC of 0.709 (0.708-0.710) in the external cohort. Our 12-lead ECG-based model performance is consistent across the severity of CKD, with an AUC of 0.753 (0.735-0.770) for mild CKD, AUC of 0.759 (0.750-0.767) for moderate-severe CKD, and an AUC of 0.783 (0.773-0.793) for ESRD. In patients under 60 years old, our model achieves high performance in detecting any stage CKD with both 12-lead (AUC 0.843 [0.836-0.852]) and 1-lead ECG waveform (0.824 [0.815-0.832]). CONCLUSIONS: Our deep learning algorithm is able to detect CKD using ECG waveforms, with stronger performance in younger patients and more severe CKD stages. This ECG algorithm has the potential to augment screening for CKD.

Chronic kidney disease (CKD) is a common condition involving loss of kidney function over time and results in a substantial number of deaths. However, CKD often has no symptoms during its early stages. To detect CKD earlier, we developed a computational approach for CKD screening using routinely acquired electrocardiograms (ECGs), a cheap, rapid, non-invasive, and commonly obtained test of the heart's electrical activity. Our model achieved good accuracy in identifying any stage of CKD, with especially high accuracy in younger patients and more severe stages of CKD. Given the high global burden of undiagnosed CKD, novel and accessible CKD screening strategies have the potential to help prevent disease progression and reduce premature deaths related to CKD.

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Artificial intelligence (AI) has been developed for echocardiography1-3, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of -10.4%, 95% confidence interval: -13.2% to -7.7%, P < 0.001 for non-inferiority, P < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of -0.96%, 95% confidence interval: -1.34% to -0.54%, P < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.