John Lynn Jefferies

Background: Left ventricular (LV) dysfunction and heart failure with preserved ejection fraction (HFpEF) often present with early signs that are frequently overlooked or attributed to other conditions. This study proposes a novel, externally validated artificial intelligence (AI) tool using ECG data (ECG‐AI) for the simultaneous detection of subtypes of LV dysfunction and HFpEF. Methods: Two ECG‐AI models, using 12‐lead or single‐lead ECG, were developed using data from Atrium Health Wake Forest Baptist and University of Tennessee Health Science Center (UTHSC) to classify ECGs into 4 categories: reduced LV ejection fraction (rEF; EF<40), midrange EF (mEF; 40≤mEF<50), HFpEF, and controls (no LV dysfunction or HFpEF). Next, a boosting algorithm was used to incorporate clinical risk factors. Finally, the models were independently validated on pediatric data from UTHSC. Results: The Atrium Health Wake Forest Baptist cohort included 1 078 198 digital ECGs from 165 243 patients (5% rEF, 8% mEF, 2% HFpEF), and the UTHSC external validation cohort comprised 72 832 ECGs from 42 880 patients (1% rEF, 1% mEF, 1% HFpEF). For the 12‐lead (Lead‐I) ECG‐AI model, areas under the curve for rEF/mEF/HFpEF were 0.90/0.81/0.80 (0.89/0.78/0.75) in the Atrium Health Wake Forest Baptist holdout data and 0.92/0.76/0.73 (0.90/0.75/0.74) in the UTHSC data. Clinical data‐only machine‐learning models lacked generalizability; clinical + ECG‐AI models did not show any significant improvement compared with ECG‐alone models. With 8418 ECGs (142 cases, 8276 controls) from UTHSC pediatric data, the 12‐lead model achieved areas under the curve of 0.97/0.71/0.64 for rEF/mEF/HFpEF, and the Lead I model had areas under the curve of 0.94/0.77/0.67. Conclusions: ECG‐AI can accurately detect LV dysfunction and HFpEF even from single‐lead ECG, enabling potential low‐cost screening.

Background: This review delves into the intricate landscape of cardiorenal syndrome (CRS) and highlights the pivotal role of blood volume analysis (BVA) in improving patient care and outcomes. Summary: BVA offers a direct and highly accurate quantification of intravascular volume, red blood cell volume, and plasma volume, complete with patient-specific norms. This diagnostic tool enhances the precision of diuretic and red cell therapies, significantly elevating the effectiveness of conventional care. Key Messages: Our objectives encompass a comprehensive understanding of how BVA informs the evaluation and treatment of CRS, including its subtypes, pathophysiology, and clinical significance. We delve into BVA principles, techniques, and measurements, elucidating its diagnostic potential and advantages compared to commonly used surrogate measures. We dissect the clinical relevance of BVA in various CRS scenarios, emphasizing its unique contributions to each subtype. By assessing the tangible impact of BVA on patient outcomes through meticulous analysis of relevant clinical studies, we unveil its potential to enhance health outcomes and optimize resource utilization. Acknowledging the challenges and limitations associated with BVA’s clinical implementation, we underscore the importance of multidisciplinary collaboration among cardiologists, nephrologists, and other clinicians. Finally, we identify research gaps and propose future directions for BVA and CRS, contributing to ongoing advancements in this field and patients affected by this complicated clinical syndrome.

**Author Listing - Lead/ Submitting Author (we will be communicating with this individual): Name, Institution, City and State where the work was | POSTER

PURPOSE: Little is known about the prevalence of prediabetes and associated risk of cardiovascular events and chronic kidney disease (CKD) with this reversable condition in survivors.METHODS: Prevalence of prediabetes (fasting plasma glucose 100-125 mg/dL or hemoglobin A1c 5.7%-6.4%) and diabetes was clinically assessed in 3,529 adults ≥5 years from childhood cancer diagnosis and 448 controls stratified by age. Cox proportional hazards regression estimated progression from prediabetes to diabetes, and risk of future cardiac events, stroke, CKD, and death.RESULTS: Among survivors, median age 30 years (IQR, 18-65), and the prevalence of prediabetes was 29.2% (95% CI, 27.7 to 30.7) versus 18.1% (14.5 to 21.6) in controls and of diabetes was 6.5% (5.7 to 7.3) versus 4.7% (2.7 to 6.6). By age 40-49 years, more than half of the survivors had prediabetes (45.5%) or diabetes (14.0%). Among 695 survivors with prediabetes and longitudinal follow-up, 68 (10%; median follow-up, 5.1 years) progressed to diabetes. After adjustment for demographic factors and body composition, risk of progression was associated with radiation exposure to the pancreatic tail ≥10 Gy (hazard ratio [HR], 2.7 [95% CI, 1.1 to 6.8]) and total-body irradiation (4.4 [1.5 to 13.1]). Compared with survivors with normal glucose control, adjusting for relevant treatment exposures, those with prediabetes were at increased risk of future myocardial infarction (HR, 2.4 [95% CI, 1.2 to 4.8]) and CKD (2.9 [1.04 to 8.15]), while those with diabetes were also at increased risk of future cardiomyopathy (3.8 [1.4 to 10.5]) or stroke (3.4 [1.3 to 8.9]).CONCLUSION: Prediabetes is highly prevalent in adult survivors of childhood cancer and independently associated with an increased risk of future cardiovascular and kidney complications. Prediabetes, a modifiable risk factor among childhood cancer survivors, represents a new target for intervention that may prevent subsequent morbidity and mortality.

Background: Pediatric dilated cardiomyopathy often leads to death or cardiac transplantation. We sought to determine whether changes in left ventricular (LV) end‐diastolic dimension (LVEDD), LV end‐diastolic posterior wall thickness, and LV fractional shortening (LVFS) over time may help predict adverse outcomes. Methods and Results: We studied children up to 18 years old with dilated cardiomyopathy, enrolled between 1990 and 2009 in the Pediatric Cardiomyopathy Registry. Changes in LVFS, LVEDD, LV end‐diastolic posterior wall thickness, and the LV end‐diastolic posterior wall thickness:LVEDD ratio between baseline and follow‐up echocardiograms acquired ≈1 year after diagnosis were determined for children who, at the 1‐year follow‐up had died, received a heart transplant, or were alive and transplant‐free. Within 1 year after diagnosis, 40 (5.0%) of the 794 eligible children had died, 117 (14.7%) had undergone cardiac transplantation, and 585 (73.7%) had survived without transplantation. At diagnosis, survivors had higher median LVFS and lower median LVEDD Z scores. Median LVFS and LVEDD Z scores improved among survivors ( Z score changes of +2.6 and −1.1, respectively) but remained stable or worsened in the other 2 groups. The LV end‐diastolic posterior wall thickness:LVEDD ratio increased in survivors only, suggesting beneficial reverse LV remodeling. The risk for death or cardiac transplantation up to 7 years later was lower when LVFS was improved at 1 year (hazard ratio [HR], 0.83; P =0.004) but was higher in those with progressive LV dilation (HR, 1.45; P <0.001). Conclusions: Progressive deterioration in LV contractile function and increasing LV dilation are associated with both early and continuing mortality in children with dilated cardiomyopathy. Serial echocardiographic monitoring of these children is therefore indicated. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT00005391.