Search

Background: A deep learning (DL) model based on a chest x-ray was reported to predict elevated pulmonary artery wedge pressure (PAWP) as heart failure (HF). Objectives: The aim of this study was to (1) investigate the role of probability of elevated PAWP for the prediction of clinical outcomes in association with other parameters, and (2) to evaluate whether probability of elevated PAWP based on DL added prognostic information to other conventional clinical prognostic factors in HF. Methods: We evaluated 192 patients hospitalized with HF. We used a previously developed AI model to predict HF and calculated probability of elevated PAWP. Readmission following HF and cardiac mortality were the primary endpoints. Results: Probability of elevated PAWP was associated with diastolic function by echocardiography. During a median follow-up period of 58 months, 57 individuals either died or were readmitted. Probability of elevated PAWP appeared to be associated with worse clinical outcomes. After adjustment for readmission score and laboratory data in a Cox proportional-hazards model, probability of elevated PAWP at pre-discharge was associated with event free survival, independent of elevated left atrial pressure (LAP) based on echocardiographic guidelines (p < 0.001). In sequential Cox models, a model based on clinical data was improved by elevated LAP (p = 0.005), and increased further by probability of elevated PAWP (p < 0.001). In contrast, the addition of pulmonary congestion interpreted by a doctor did not statistically improve the ability of a model containing clinical variables (compared p = 0.086). Conclusions: This study showed the potential of using a DL model on a chest x-ray to predict PAWP and its ability to add prognostic information to other conventional clinical prognostic factors in HF. The results may help to enhance the accuracy of prediction models used to evaluate the risk of clinical outcomes in HF, potentially resulting in more informed clinical decis

Introduction: This study aimed to evaluate the impacts of dapagliflozin on 24-hour glucose variability and diabetes-related biochemical variables in Japanese patients with type 2 diabetes who had received basal insulin supported oral therapy (BOT). Research design and methods: Changes in mean daily blood glucose level before and after 48–72 hours of add-on or no add-on of dapagliflozin (primary end point) and diabetes-related biochemical variables and major safety variables during the 12 weeks (secondary end point) were evaluated in the multicenter, randomized, two-arm, open-label, parallel-group comparison study. Results: Among 36 participants, 18 were included in the no add-on group and 18 were included in the dapagliflozin add-on group. Age, gender, and body mass index were comparable between the groups. There were no changes in continuous glucose monitoring metrics in the no add-on group. In the dapagliflozin add-on group, mean glucose (183–156mg/dL, p=0.001), maximum glucose (300–253, p<0.01), and SD glucose (57–45, p<0.05) decreased. Time in range increased (p<0.05), while time above the range decreased in the dapagliflozin add-on group but not in the no add-on group. After 12-week treatment with dapagliflozin add-on, 8-hydroxy-2’-deoxyguanosine (8OHdG), as well as hemoglobin A1c (HbA1c), decreased. Conclusions: This study showed that the mean daily blood glucose and other daily glucose profiles were amended after 48–72 hours of dapagliflozin add-on in Japanese patients with type 2 diabetes who received BOT. The diabetes-related biochemical variables such as HbA1c and urinary 8OHdG were also obtained during the 12 weeks of dapagliflozin add-on without major adverse events. A preferable 24-hour glucose profile in ‘time in ranges’ and an improvement in reactive oxygen species by dapagliflozin warrant us to evaluate these benefits in larger clinical studies.

Type 2 diabetes mellitus (T2DM) is a major cause of microvascular dysfunction. However, its effect on blood flow patterns during ischemic demand has not been adequately elucidated. In this study, we investigated the hypothesis that microvascular dysfunction in patients with T2DM manifests as brachial reactive hyperemia (BRH), defined as the ratio of peak blood flow velocities in a brachial artery before and after forearm cuff occlusion. The study enrolled 943 subjects (men, n = 152 [T2DM] and n = 371 [non-T2DM]; women, n = 107 [T2DM] and n = 313 [non-T2DM], respectively) with no history of cardiovascular disease. Semiautomatic measurements were obtained three times at 1.5-year intervals to confirm the reproducibility of factors involved in BRH for each sex. An age-adjusted mixed model demonstrated attenuated BRH in the presence of T2DM in both men (p = 0.022) and women (p = 0.031) throughout the study period. Post hoc analysis showed that the estimated BRH was significantly attenuated in patients with T2DM regardless of sex, except at baseline in women. In multivariate regression analysis, T2DM was a negative predictor of BRH at every measurement in men. For women, BRH was more strongly associated with alcohol consumption. Repeated measurements analysis revealed that T2DM was associated with attenuated postocclusion reactive hyperemia.

Objective: Precise and reliable echocardiographic assessment of left ventricular ejection fraction (LVEF) is needed for clinical decision-making. Recently, artificial intelligence (AI) models have been developed to estimate LVEF accurately. The aim of this study was to evaluate whether an AI model could estimate an expert read of LVEF and reduce the interinstitutional variability of level 1 readers with the AI-LVEF displayed on the echocardiographic screen. Methods: This prospective, multicentre echocardiographic study was conducted by five cardiologists of level 1 echocardiographic skill (minimum level of competency to interpret images) from different hospitals. Protocol 1: Visual LVEFs for the 48 cases were measured without input from the AI-LVEF. Protocol 2: the 48 cases were again shown to all readers with inclusion of AI-LVEF data. To assess the concordance and accuracy with or without AI-LVEF, each visual LVEF measurement was compared with an average of the estimates by five expert readers as a reference. Results: A good correlation was found between AI-LVEF and reference LVEF (r=0.90, p<0.001) from the expert readers. For the classification LVEF, the area under the curve was 0.95 on heart failure with preserved EF and 0.96 on heart failure reduced EF. For the precision, the SD was reduced from 6.1±2.3 to 2.5±0.9 (p<0.001) with AI-LVEF. For the accuracy, the root-mean squared error was improved from 7.5±3.1 to 5.6±3.2 (p=0.004) with AI-LVEF. Conclusions: AI can assist with the interpretation of systolic function on an echocardiogram for level 1 readers from different institutions.