This study aimed to develop and validate deep-learning-based artificial intelligence algorithm for predicting mortality of AHF (DAHF).
12,654 dataset from 2165 patients with AHF in two hospitals were ...used as train data for DAHF development, and 4759 dataset from 4759 patients with AHF in 10 hospitals enrolled to the Korean AHF registry were used as performance test data. The endpoints were in-hospital, 12-month, and 36-month mortality. We compared the DAHF performance with the Get with the Guidelines-Heart Failure (GWTG-HF) score, Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) score, and other machine-learning models by using the test data. Area under the receiver operating characteristic curve of the DAHF were 0.880 (95% confidence interval, 0.876-0.884) for predicting in-hospital mortality; these results significantly outperformed those of the GWTG-HF (0.728 0.720-0.737) and other machine-learning models. For predicting 12- and 36-month endpoints, DAHF (0.782 and 0.813) significantly outperformed MAGGIC score (0.718 and 0.729). During the 36-month follow-up, the high-risk group, defined by the DAHF, had a significantly higher mortality rate than the low-risk group(p<0.001).
DAHF predicted the in-hospital and long-term mortality of patients with AHF more accurately than the existing risk scores and other machine-learning models.
Aims
The Korean Acute Heart Failure registry (KorAHF) aims to evaluate the clinical characteristics, management, hospital course, and long‐term outcomes of patients hospitalized for acute heart ...failure syndrome (AHFS) in Korea.
Methods and results
This is a prospective observational multicentre cohort study funded by the Korea National Institute of Health. Patients hospitalized for AHFS in 10 tertiary university hospitals across the country have been consecutively enrolled since March 2011. The study is expected to complete the scheduled enrolment of 5000 patients some time in 2014, and follow‐up is planned through 2016. As of April 2012, the interim analysis of 2066 consecutive subjects was performed to understand the baseline characteristics of the population. The mean age was 69 ± 14 years; 55% were male; and 50% were de novo heart failure. The mean left ventricular ejection fraction (LVEF) was 40 ± 18%. Ischaemia was both the leading cause (38%) and the most frequent aggravating factor (26%) of AHFS. ACE inhibitors/ARBs and beta‐blockers were prescribed at discharge in 65% and 51% of the patients, respectively. In‐hospital mortality was 5.2%, and 0.9% of patients received urgent heart transplantation. Low blood pressure and azotaemia were the most important predictors of in‐hospital mortality. The post‐discharge 30‐day and 180‐day all‐cause mortality were 1.2% and 9.2%, respectively.
Conclusions
Our analysis reveals that the prognosis of AHFS in Korea is poor and that there are specific features, including lower blood pressures at admission and lower rates of heart failure related to hypertension, compared with other registries. Adherence to current guidelines should be improved.
Background: The clinical characteristics and outcomes of acute heart failure (AHF) according to left ventricular ejection fraction (LVEF) have not been fully elucidated, especially for patients with ...mid-range LVEF. We performed a comprehensive comparison of the epidemiology, patterns of in-hospital management, and clinical outcomes in AHF patients with different LVEF categories. Methods and Results: The Korean Acute Heart Failure (KorAHF) registry is a prospective multicenter cohort of hospitalized AHF patients in Korea. A total of 5,374 patients enrolled in the KorAHF registry were classified according to LVEF based on the 2016 ESC guidelines. More than half of the HF patients (58%) had reduced EF (HFrEF), 16% had mid-range EF (HFmrEF), and 25% had preserved EF (HFpEF). The HFmrEF patients showed intermediate epidemiological profiles between HFrEF and HFpEF and had a propensity to present as de-novo HF with ischemic etiology. Patients with lower LVEF had worse short-term outcomes, and the all-cause in-hospital mortality, including urgent heart transplantation, of HFrEF, HFmrEF, and HFpEF was 7.1%, 3.6%, and 3.0%, respectively. Overall, discharged AHF patients showed poor 3-year all-cause death up to 38%, which was comparable between LVEF subgroups (P=0.623). Conclusions: Each LVEF subgroup of AHF patients was a heterogeneous population with diverse characteristics, which have a significant effect on the clinical outcomes. This finding suggested that focused phenotyping of AHF patients could help identify the optimal management strategy and develop novel effective therapies.
There are conflicting results among previous studies regarding the prognosis of heart failure with preserved ejection fraction (HFpEF) compared with heart failure with reduced ejection fraction ...(HFrEF). This study aimed to compare the outcomes of patients with de novo acute heart failure (AHF) or acute decompensated HF (ADHF) according to HFpEF (EF≥50%), or HFrEF (EF<40%) and to define the prognosis of patients with HF with mid-range EF (HFmrEF, 40≤EF<50%).
Between March 2011 and February 2014, 5625 consecutive patients with AHF were recruited from 10 university hospitals. A total of 5414 (96.2%) patients with EF data were enrolled, which consisted of 2867 (53.0%) patients with de novo and 2547 (47.0%) with ADHF. Each of the enrolled group was stratified by EF.
In de novo, all-cause death rates were not significantly different between HFpEF and HFrEF (HFpEF vs HFrEF, 206/744 (27.7%) vs 438/1631 (26.9%), HR
1.15, 95% CI 0.96 to 1.38, p=0.14). However, among patients with ADHF, HFrEF had a significantly higher mortality rate compared with HFpEF (HFpEF vs HFrEF, 245/613 (40.0%) vs 694/1551 (44.7%), HR
1.25, 95% CI 1.06 to 1.47, p=0.007). Also, in ADHF, HFmrEF was associated with a significantly lower mortality rate within 1 year compared with HFrEF (HFmrEF vs HFrEF, 88/383 (23.0%) vs 430/1551 (27.7%), HR
1.31, 95% CI 1.03 to 1.65, p=0.03), but a significantly higher mortality rate after 1 year compared with HFpEF (HFmrEF vs HFpEF, 83/295 (28.1%) vs 101/469 (21.5%), HR
0.70, 95% CI 0.52 to 0.96, p=0.02).
HFpEF may indicate a better prognosis compared with HFrEF in ADHF, but not in de novo AHF. For patients with ADHF, the prognosis associated with HFmrEF was similar to that of HFpEF within the first year following hospitalisation and similar to HFrEF 1 year after hospitalisation.
•The risk of 30-day heart failure (HF) readmission or death can be estimated with 12 variables.•The risk for short-term HF-specific readmission or death can be calculated easily.•The model has the ...potential to reduce readmission by identifying high-risk patients.•The risk model can be utilized to guide suitable interventions or care in patients.
Identifying patients with acute heart failure (HF) at high risk for readmission or death after hospital discharge will enable the optimization of treatment and management. The objective of this study was to develop a risk score for 30-day HF-specific readmission or death in Korea.
We analyzed the data from the Korean Acute Heart Failure (KorAHF) registry to develop a risk score. The model was derived from a multiple logistic regression analysis using a stepwise variable selection method. We also proposed a point-based risk score to predict the risk of 30-day HF-specific readmission or death by simply summing the scores assigned to each risk variable. Model performance was assessed using an area under the receiver operating characteristic curve (AUC), the Hosmer–Lemeshow goodness-of-fit test, the net reclassification improvement (NRI), and the integrated discrimination improvement (IDI) index to evaluate discrimination, calibration, and reclassification, respectively.
Data from 4566 patients aged ≥40 years were included in the analysis. Among them, 446 (9.8%) had 30-day HF-specific readmission or death. The final model included 12 independent variables (age, New York Heart Association functional class, clinical history of hypertension, HF admission, chronic obstructive pulmonary disease, etiology of cardiomyopathy, systolic blood pressure, left ventricular ejection fraction, serum sodium, brain natriuretic peptide, N-terminal prohormone of brain natriuretic peptide at discharge, and prescription of β-blockers and angiotensin-converting enzyme inhibitors or angiotensin II receptor antagonists at discharge). The point risk score showed moderate discrimination (AUC of 0.710; 95% confidence interval, 0.685–0.735) and good calibration (χ2=8.540, p=0.3826).
The risk score for the prediction of the risk of 30-day HF-specific readmission or death after hospital discharge was developed using 12 predictors. It can be utilized to guide appropriate interventions or care strategies for patients with HF.
To increase the fault tolerance for cascaded H-bridge multilevel inverters (CHMIs) based on level-shifted pulse width modulation (LS-PWM), a modified LS-PWM method is proposed for the inverters ...operating under faulty conditions. To cover both open- and short-device fault cases, two types of switching scheme are included in this PWM method. With this PWM method, the neutral shift can be applied as fault-tolerant control for CHMIs based on LS-PWM. Finally, three-phase-balanced line-to-line voltages and currents with minimum harmonic distortion are produced for the inverter with disabled power cells. In addition, this LS-PWM method has the capability to improve power distribution among the H-bridge power cells under the faulty conditions. Simulation and experimental results show that the proposed PWM method performs satisfactorily to achieve fault tolerance.
Conductive fibers, which are highly adaptable to the morphologies of the human body, are attractive for the development of wearable systems, smart clothing, and textronics to detect various ...biological signals and human motions. A fiber‐based conductive sensor interconnected with hierarchical microhairy architectures, exhibiting remarkable stretchability (<200%) and sensitivity for various stimuli (pressure, stretching, and bending), is developed. For distinguishability of multiple gestures, two hierarchical hairy conductive fibers are twisted to fabricate a fiber‐type sensor, which monitors distinct waveforms of electrical signals retrieved from pressure, stretching, and bending. This sensor is highly robust under repeated appliances of external stimuli over multiple cyclic tests of various modes (<2200 cycles for each stimulus). Upon formation of a self‐assembled monolayer, it exhibits stable performance even under wet conditions. For practical applications, this sensor can be weaved into a smart glove to demonstrate a pressure and gesture‐discernible wearable controller for virtual reality (VR) interface, shedding light on advances in wearable electronics with medical and healthcare functionalities and VR systems.
A fiber‐based conductive hierarchical sensor with excellent sensitivity and stretchability available for distinguishing three different types (pressure, stretching, and bending) of human motion gestures by recognizing distinct waveforms is described. The remarkable mechanical stability, sensitivity, water resistance, and signal distinguishability of this sensor enable its use in a smart, wearable glove for controlling of actions within a virtual interface.
Graphene provides outstanding properties that can be integrated into various flexible and stretchable electronic devices in a conventional, scalable fashion. The mechanical, electrical, and optical ...properties of graphene make it an attractive candidate for applications in electronics, energy‐harvesting devices, sensors, and other systems. Recent research progress on graphene‐based flexible and stretchable electronics is reviewed here. The production and fabrication methods used for target device applications are first briefly discussed. Then, the various types of flexible and stretchable electronic devices that are enabled by graphene are discussed, including logic devices, energy‐harvesting devices, sensors, and bioinspired devices. The results represent important steps in the development of graphene‐based electronics that could find applications in the area of flexible and stretchable electronics.
The outstanding properties of graphene enable a novel form of electronics in a conventional, scalable fashion. Recent progress in graphene‐based flexible and stretchable electronics is reviewed, from the production of the graphene to its applications, including logic gates, energy‐harvesting devices, sensors, and bioinspired devices.
We investigated the role of nutritional risk index (NRI) in predicting 1-year mortality in patients with acute decompensated heart failure (ADHF).
Among 5,625 cohort patients enrolled in Korean Acute ...Heart Failure (KorAHF) Registry, a total of 5,265 patients who were possible to calculate NRI NRI = (1.519 x serum albumin g/dl) + (41.7 x weight kg/ideal body weight kg) were enrolled. The patients were divided into 4 groups according to the NRI quartile; Q1 <89 (n = 1121, 69.9 ± 14.5 years, 632 males), Q2 89-95 (n = 1234, 69.7 ± 14.4 years, 677 males), Q3 95-100 (n = 1199, 68.8 ± 14.0 years, 849 males), Q4 >100 (n = 1711, 65.6 ± 14.5 years, 779 males). Primary end-point was all-cause mortality at 1-year clinical follow-up.
The 1-year mortality was significantly increased as the NRI quartile decreased, and the lowest NRI quartile was associated with the highest 1-year mortality (Q1: 27.5% vs. Q2: 20.9% vs. Q3: 12.9% vs. Q4: 8.7%, linear p <0.001). On Kaplan-Meier survival analysis, the significant inter-quartile difference was observed (p <0.001 for all). In multivariate analysis using Cox proportional hazard regression, the lowest NRI quartile was an independent predictor of 1-year mortality in patients with ADHF.
Poor nutritional status as assessed by NRI and quartile grading of NRI was associated with 1-year mortality in Korean patients with ADHF. The assessment of nutritional status by NRI may provide additional prognostic information and thus would be useful in the risk stratification of the patients with ADHF.
PDF
