Lopez‐Jimenez, Francisco

Background. Mortality risk assessment before kidney transplantation (KT) is imperfect. An emerging risk factor for death in nontransplant populations is physiological age as determined by the application of artificial intelligence to the electrocardiogram (ECG). The aim of this study was to examine the relationship between ECG age and KT waitlist mortality. Methods. We applied a previously developed convolutional neural network to the ECGs of KT candidates evaluated 2014 to 2019 to determine ECG age. We used a Cox proportional hazard model to examine whether ECG age was associated with waitlist mortality. Results. Of the 2183 patients evaluated, 59.1% were male, 81.4% were white, and 11.4% died during follow-up. Mean ECG age was 59.0 ± 12.0 y and mean chronological age at ECG was 53.3 ± 13.6 y. After adjusting for chronological age, comorbidities, and other characteristics associated with mortality, each increase in ECG age of >10 y than the average ECG age for patients of a similar chronological age was associated with an increase in mortality risk (hazard ratio 3.59 per 10-y increase; 95% confidence interval, 2.06-5.72; P < 0.0001). Conclusions. ECG age is a risk factor for KT waitlist mortality. Determining ECG age through artificial intelligence may help guide risk-benefit assessment when evaluating candidates for KT.

Arterial stiffness is recognized as a highly clinically relevant and independent prognostic biomarker of cardiovascular disease. Arterial dispersion ultrasound vibrometry (ADUV) uses acoustic radiation force to generate propagating waves in the arterial wall and measures the wave motion to estimate arterial mechanical properties from fitting phase velocity dispersion curves to a waveguide model. ADUV measurements were made with a Verasonics V1 system with a L7-4 linear array transducer in 63 human subjects (27 male/36 female) from ages 50–88 years old. We made measurements at 10 time points within the cardiac cycle, termed cardiac stages. We estimated the phase velocity (median of cp from 400-600 Hz) and G determined from matching the dispersion curves with those from a waveguide model incorporating the artery diameter and wall thickness. Within the same study visit, we measured the intima-media thickness and diameter changes through the cardiac cycle with a General Electric Logiq E9 or E10 scanner. We also tonometry to determine the carotid-femoral pulse wave velocity. We report here comparisons of median phase velocity, cp, and inverted shear modulus, G, at different stages of the cardiac cycle with clinical metrics of arterial stiffness.

Abstract Artificial intelligence (AI)-based approaches can now use electrocardiograms (ECGs) to provide expert-level performance in detecting heart abnormalities and diagnosing disease. Additionally, patient age predicted from ECGs by AI models has shown great potential as a biomarker for cardiovascular age as recent work has found differences from chronological age ("delta age") to be associated with mortality and co-morbidities. However, the genetic underpinning of delta age is unknown, but crucial for understanding underlying individual risk. By performing a genome-wide association study using UK Biobank data (n=34,432), we identified eight loci associated with delta age (p ≤ 5 × 10−8 ), including genes linked to cardiovascular disease (CVD) (e.g. SCN5A) and (heart) muscle development (e.g. TTN). Our results indicate that the genetic basis of cardiovascular ageing is predominantly determined by genes directly involved with the cardiovascular system rather than those connected to more general mechanisms of ageing. Our insights inform the epidemiology of CVD, with implications for preventative and precision medicine.

Background: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. Methods: Consecutive patients (4/8/2015 – 12/31/2020) undergoing rest and postexercise ankle–brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 – 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. Results: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92–0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91–0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). Conclusion: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.

The aim of the present study was to evaluate the association between television viewing/physical activity (TVV/PA) interactions and cardiometabolic risk in an adult European population. A total of 2155 subjects (25–64 years) (45.2% males), a random population-based sample were evaluated in Brno, Czechia. TVV was classified as low (<2 h/day), moderate (2–4), and high (≥4). PA was classified as insufficient, moderate, and high. To assess the independent association of TVV/PA categories with cardiometabolic variables, multiple linear regression was used. After adjustments, significant associations were: High TVV/insufficient PA with body mass index (BMI) (β = 2.61, SE = 0.63), waist circumference (WC) (β = 7.52, SE = 1.58), body fat percent (%BF) (β = 6.24, SE = 1.02), glucose (β = 0.25, SE = 0.12), triglycerides (β = 0.18, SE = 0.05), and high density lipoprotein (HDL-c) (β = −0.10, SE = 0.04); high TVV/moderate PA with BMI (β = 1.98, SE = 0.45), WC (β = 5.43, SE = 1.12), %BF (β = 5.15, SE = 0.72), triglycerides (β = 0.08, SE = 0.04), total cholesterol (β = 0.21, SE = 0.10), low density protein (LDL-c) (β = 0.19, SE = 0.08), and HDL-c (β = −0.07, SE = 0.03); and moderate TVV/insufficient PA with WC (β = 2.68, SE = 1.25), %BF (β = 3.80, SE = 0.81), LDL-c (β = 0.18, SE = 0.09), and HDL-c (β = −0.07, SE = 0.03). Independent of PA levels, a higher TVV was associated with higher amounts of adipose tissue. Higher blood glucose and triglycerides were present in subjects with high TVV and insufficient PA, but not in those with high PA alone. These results affirm the independent cardiometabolic risk of sedentary routines even in subjects with high-levels of PA.

Abstract We here posit that measurements of midlife cognition can be instructive in understanding cognitive disorders. Even though molecular events signal possible onset of cognitive disorders decades prior to their clinical diagnoses, cognition and its possible early changes in midlife remain poorly understood. We characterize midlife cognition in a cognitively healthy population‐based sample using the Cogstate Brief Battery and test for associations with cardiovascular, adiposity‐related, lifestyle‐associated, and psychosocial variables. Learning and working memory showed significant variability and vulnerability to psychosocial influences in midlife. Furthermore, midlife aging significantly and progressively increased prevalence of suboptimal cognitive performance. Our findings suggest that physiological changes in cognition, measured with simple tests suitable for use in everyday clinical setting, may signal already in midlife the first clinical manifestations of the presymptomatic biologically defined cognitive disorders. This pilot study calls for longitudinal studies investigating midlife cognition to identify clinical correlates of biologically defined cognitive disorders.

Introduction : Obesity is a common risk factor in cardiac rehabilitation (CR), yet many CR patients do not realize significant weight loss, despite engaging in regular exercise training while in CR. Hypothesis : We hypothesized that standard CR would demonstrate favorable body composition (BC) changes even in the absence of weight loss and sought to measure the performance characteristics of weight loss to predict BC changes. Methods : We included consecutive patients enrolled in early outpatient CR who underwent air displacement plethysmography with measurements of height, weight, and waist circumference at initiation and completion of CR. We calculated the accuracy of weight loss to identify significant improvements in BC. Results : Data from 112 patients were available for analysis; mean age 60±12 yr., 76% male, mean body mass index (BMI) 30.2±5.3 kg/m 2 . The indication for CR was myocardial infarction (n=33), percutaneous coronary intervention (n=29), coronary artery bypass or valve surgery (n=45), and heart transplant (n=5). Repeat testing occurred after a median of 81 days and 21 phase II CR sessions. There was no change in BMI (-0.53±1.3 kg/m 2 , p=0.43) and weight (-1.6±4.0 kg, p=0.51). Fat mass showed a borderline significant decrease of 2.9±3.9 kg (p=0.08). However, BC improved significantly as measured by body fat % (-2.5±3.2%, p=0.03) and waist circumference (-4.6±5.2 cm; p=0.01). There was a correlation between weight loss and fat mass loss (r=0.85, p=0.0001, positive predictive value=0.94), and % fat change (r=0.67, p=0.0001, positive predictive value=0.91). See table 1. However, the negative predictive value to detect no fat change for patients who did not lose weight was low (0.49, when assessed by % body fat loss, and 0.57, when assessed by fat mass loss). Among patients who did not lose weight, 29 (51%) had a greater than 1% body fat loss. Conclusions : The diagnostic performance of weight change to predict favorable BC changes is poor and highlights the potential utility of BC measurements in the CR setting. Table. Diagnostic Characteristics of Weight Loss as a Predictor of Improvements in Body Composition Weight Loss (kg) Body Fat % Loss ≤ 1% Fat Mass Loss (kg) > 1kg > 1% ≤ 1kg > 1kg 49 5 51 3 ≤ 1kg or gain 29 28 25 33 Sensitivity 0.63 0.67 Specificity 0.85 0.92 PPV * 0.91 0.94 NPV ** 0.49 0.57 * PPV = Positive Predictive Valve, ** NPV = Negative Predictive Value