Development of an electronic frailty index for predicting mortality in patients undergoing transcatheter aortic valve replacement using machine learning

Chen, Yiyi; Zhou, Jiandong; Lee, Sharen; Liu, Tong; Hothi, Sandeep S; Wong, Ian Chi Kei; Zhang, Qingpeng; Tse, Gary; Wang, Yan

doi:10.1101/2020.12.23.20248770

Cited by 3 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Possible explanations for these conflicting results may be the different EF values used as a cut-off for LV dysfunction or that patients may have concomitant pathologies causing HF, such as ischaemic cardiomyopathy, which will impact on their prognosis. The main clinical implication suggested by this finding involves the necessity of early intervention in patients with systolic dysfunction, with the use of higher LVEF cut-off values to improve their outcomes [32][33][34]. Although our data showed good recovery and it did not increased risk in patients with HFrEF after TAVR.…”

Section: Discussionmentioning

confidence: 55%

Effectiveness and safety of transcatheter aortic valve replacement in elderly people with severe aortic stenosis with different types of heart failure

Dong

Wang²,

Tse³

et al. 2023

BMC Cardiovasc Disord

Self Cite

View full text Add to dashboard Cite

Background Impaired left ventricular function is an independent predictor of adverse clinical outcomes in patients with aortic stenosis. The aim of this study is to evaluate the short-term changes of echocardiographic parameters, New York Heart Association (NYHA) class and B-type natriuretic peptide (BNP) level and adverse events amongst patients with heart failure (HF) after transcatheter aortic valve replacement (TAVR) procedure. Methods This was a retrospective cohort study conducted at affiliated Yantai Yuhuangding Hospital of Qingdao University between September 2017 and September 2022. TAVR cases were stratified into three groups [heart failure with reduced ejection fraction (HFrEF), heart failure with mildly reduced ejection fraction (HFmrEF), heart failure with preserved ejection fraction (HFpEF)] by left ventricular ejection fraction (LVEF). Baseline characteristics, changes in echocardiographic parameters (1 week and 1 month), BNP (1 month), and NYHA class (6 months) post-TAVR were compared across the three groups. Meanwhile, we observed the adverse events of the patients after TAVR. Results A total of 96 patients were included, of whom 15 (15.6%) had HFrEF, 15 (15.6%) had HFmrEF, and 66 (68.8%) had HFpEF. Compared to the HFpEF subgroup, patients in the HFrEF subgroup were younger (p < 0.05), and with a higher BNP (p < 0.05). The left ventricular end-diastolic dimension (LVEDD) in HFrEF group decreased significantly after TAVR. HFmrEF and HFrEF patients showed significant improvements in LVEF after TAVR. The pulmonary artery systolic pressure (PASP), aortic valve peak gradient (AVPG) and aortic valve peak gradient (Vmax) decreased significantly 1 month after TAVR in all three groups compared to the baseline (all p < 0.05). BNP significantly reduced in HFrEF group compared to HFpEF patients after TAVR (p < 0.05). The majority of patients experienced an improvement at least one NYHA class in all three groups 6 months post-TAVR. There is no significant increase in the risk of adverse events in the HFrEF group. Conclusions Patients who underwent TAVR achieved significant improvements in BNP, NYHA class, LVEDD, LVEF, and PASP across the three HF classes, with a more rapid and pronounced improvement in the HFrEF and HFmrEF groups. Complication rates were low in the different HF groups. There is no significant increase in the risk of periprocedural complications in the HFrEF and HFmrEF groups.

show abstract

Section: Discussionmentioning

confidence: 55%

Effectiveness and safety of transcatheter aortic valve replacement in elderly people with severe aortic stenosis with different types of heart failure

Dong

Wang²,

Tse³

et al. 2023

BMC Cardiovasc Disord

Self Cite

View full text Add to dashboard Cite

show abstract

“…The patients were identified from the Clinical Data Analysis and Reporting System (CDARS), a territory-wide database that centralizes patient information from individual local hospitals to establish comprehensive medical data. This system has previously been used by local teams to conduct population-based epidemiological studies (22,23), including the development of eFIs (24,25).…”

Section: Study Design and Populationmentioning

confidence: 99%

Development of an Electronic Frailty Index for Predicting Mortality and Complications Analysis in Pulmonary Hypertension Using Random Survival Forest Model

Zhou

Chou

Wong³

et al. 2022

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

BackgroundThe long-term prognosis of the cardio-metabolic and renal complications, in addition to mortality in patients with newly diagnosed pulmonary hypertension, are unclear. This study aims to develop a scalable predictive model in the form of an electronic frailty index (eFI) to predict different adverse outcomes.MethodsThis was a population-based cohort study of patients diagnosed with pulmonary hypertension between January 1st, 2000 and December 31st, 2017, in Hong Kong public hospitals. The primary outcomes were mortality, cardiovascular complications, renal diseases, and diabetes mellitus. The univariable and multivariable Cox regression analyses were applied to identify the significant risk factors, which were fed into the non-parametric random survival forest (RSF) model to develop an eFI.ResultsA total of 2,560 patients with a mean age of 63.4 years old (interquartile range: 38.0–79.0) were included. Over a follow-up, 1,347 died and 1,878, 437, and 684 patients developed cardiovascular complications, diabetes mellitus, and renal disease, respectively. The RSF-model-identified age, average readmission, anti-hypertensive drugs, cumulative length of stay, and total bilirubin were among the most important risk factors for predicting mortality. Pair-wise interactions of factors including diagnosis age, average readmission interval, and cumulative hospital stay were also crucial for the mortality prediction. Patients who developed all-cause mortality had higher values of the eFI compared to those who survived (P < 0.0001). An eFI ≥ 9.5 was associated with increased risks of mortality [hazard ratio (HR): 1.90; 95% confidence interval [CI]: 1.70–2.12; P < 0.0001]. The cumulative hazards were higher among patients who were 65 years old or above with eFI ≥ 9.5. Using the same cut-off point, the eFI predicted a long-term mortality over 10 years (HR: 1.71; 95% CI: 1.53–1.90; P < 0.0001). Compared to the multivariable Cox regression, the precision, recall, area under the curve (AUC), and C-index were significantly higher for RSF in the prediction of outcomes.ConclusionThe RSF models identified the novel risk factors and interactions for the development of complications and mortality. The eFI constructed by RSF accurately predicts the complications and mortality of patients with pulmonary hypertension, especially among the elderly.

show abstract

LDL-C: An Important Independent Risk Factor for New-Onset Heart Block in Patients with Severe Aortic Stenosis and Heart Failure after TAVR

Dong,

Wang,

Tse

et al. 2023

Rev. Cardiovasc. Med.

View full text Add to dashboard Cite

Background: Transcatheter aortic valve replacement (TAVR) is an effective alternative treatment for patients with aortic stenosis (AS) who have intermediate to high surgical risk or who are inoperable. However, the incidence of conduction abnormalities is high after TAVR, which can reduce the effectiveness of the surgery. Our research objective is to explore the risk factors of new-onset conduction abnormalities after TAVR, providing reference value for clinical doctors to better prevent and treat conduction abnormalities. Methods: Patients who underwent TAVR were divided into those who developed heart block and those who did not. Baseline clinical characteristics, cardiac structural parameters, procedural characteristics, electrocardiogram (ECG) changes before and after TAVR ( = postoperative minus preoperative), and surgical complications were compared. Logistic regression was applied to identify significant risk factors for new-onset heart block. Results: We studied 93 patients, of whom 34.4% developed heart blocks. Univariate logistic regression showed that prior history of malignancy, atrial fibrillation, preoperative high-level total cholesterol and low-density lipoprotein cholesterol (LDL-C), HR, QRS interval, QT interval, and QTc interval were risk factors of new-onset heart block after TAVR. Multivariate analysis showed that preoperative high-level LDL-C and QRS interval remained significant independent risk factors after adjusting for potential confounds. Conclusions: Heart block is the most common complication of TAVR, and its significant independent risk factors include high-level LDL-C and QRS interval.

show abstract

Development of an electronic frailty index for predicting mortality in patients undergoing transcatheter aortic valve replacement using machine learning

Cited by 3 publications

References 31 publications

Effectiveness and safety of transcatheter aortic valve replacement in elderly people with severe aortic stenosis with different types of heart failure

Effectiveness and safety of transcatheter aortic valve replacement in elderly people with severe aortic stenosis with different types of heart failure

Development of an Electronic Frailty Index for Predicting Mortality and Complications Analysis in Pulmonary Hypertension Using Random Survival Forest Model

LDL-C: An Important Independent Risk Factor for New-Onset Heart Block in Patients with Severe Aortic Stenosis and Heart Failure after TAVR

Contact Info

Product

Resources

About