Prediction of 30-Day All-Cause Readmissions in Patients Hospitalized for Heart Failure

Frizzell, Jarrod D.; Li, Liang; Schulte, Phillip J.; Yancy, Clyde W.; Heidenreich, Paul A.; Hernandez, Adrian F.; Bhatt, Deepak L.; Fonarow, Gregg C.; Laskey, Warren K.

doi:10.1001/jamacardio.2016.3956

Cited by 288 publications

(235 citation statements)

References 14 publications

Supporting

Mentioning

215

Contrasting

Unclassified

Order By: Relevance

“…These results replicate our previous findings10, 11, 12 and provide further evidence regarding the utility of this biomarker in the prediction of recurrent hospitalizations, an end point of clinical significance that currently cannot be predicted accurately with standard prognostic factors 3, 4…”

Section: Discussionsupporting

confidence: 89%

Serum Neprilysin and Recurrent Admissions in Patients With Heart Failure

Núñez

Barallat

et al. 2017

JAHA

View full text Add to dashboard Cite

BackgroundOur aim was to evaluate the association between the soluble form of neprilysin (sNEP) levels and long‐term all‐cause, cardiovascular, and acute heart failure (AHF) recurrent admissions in an ambulatory cohort of patients with heart failure. sNEP has emerged as a new biomarker with promising implications for prognosis and therapy in patients with heart failure. Reducing the recurrent admission rate of heart failure patients has become an important target of public health planning strategies.Methods and ResultsWe measured sNEP levels in 1021 consecutive ambulatory heart failure patients. End points were the number of all‐cause, cardiovascular, and AHF hospitalizations during follow‐up. We used covariate‐adjusted incidence rate ratios to identify associations. At a median follow‐up of 3.4 years (interquartile range: 1.8–5.7), 391 (38.3%) patients died, 477 (46.7%) patients had 1901 all‐cause admissions, 324 (31.7%) patients had 770 cardiovascular admissions, and 218 (21.4%) patients had 488 AHF admissions. The medians for sNEP and amino‐terminal pro‐brain natriuretic peptide were 0.64 ng/mL (interquartile range: 0.39–1.22) and 1248 pg/mL (interquartile range: 538–2825), respectively. In a multivariate setting, the adjusted incidence rate ratios for the top (>1.22 ng/mL) versus the bottom (≤0.39 ng/mL) quartiles of sNEP were 1.37 (95% confidence interval: 1.03–1.82), P=0.032; 1.51 (95% confidence interval: 1.10–2.06), P=0.010; and 1.51 (95% confidence interval: 1.05–2.16), P=0.026 for all‐cause, cardiovascular, and AHF admissions, respectively.ConclusionsElevated sNEP levels predicted an increased risk of recurrent all‐cause, cardiovascular, and AHF admissions in ambulatory patients with heart failure.

show abstract

Section: Discussionsupporting

confidence: 89%

Serum Neprilysin and Recurrent Admissions in Patients With Heart Failure

Núñez

Barallat

et al. 2017

JAHA

View full text Add to dashboard Cite

show abstract

“…Missing data for the remaining 86 variables were handled using mean (numeric variables) or most common value (non‐numeric variables) imputation. We trained a random forest model to predict survival up to 1 year after hospital discharge or at an outpatient clinic visit 18, 19. The random forest algorithm was chosen because it can be applied to a data set with mixed variable types, performs well on data sets with large numbers of variables, is not prone to overfitting, and allows estimation of variable importance.…”

Section: Methodsmentioning

confidence: 99%

“…The Random Forest (RF) machine learning algorithm is a process of fitting a series of classification and regression trees to the data 18. A tree is constructed by first taking a single bootstrap sample of the data.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients

Ahmad

Lund

Rao³

et al. 2018

JAHA

180

150

View full text Add to dashboard Cite

BackgroundWhereas heart failure (HF) is a complex clinical syndrome, conventional approaches to its management have treated it as a singular disease, leading to inadequate patient care and inefficient clinical trials. We hypothesized that applying advanced analytics to a large cohort of HF patients would improve prognostication of outcomes, identify distinct patient phenotypes, and detect heterogeneity in treatment response.Methods and ResultsThe Swedish Heart Failure Registry is a nationwide registry collecting detailed demographic, clinical, laboratory, and medication data and linked to databases with outcome information. We applied random forest modeling to identify predictors of 1‐year survival. Cluster analysis was performed and validated using serial bootstrapping. Association between clusters and survival was assessed with Cox proportional hazards modeling and interaction testing was performed to assess for heterogeneity in response to HF pharmacotherapy across propensity‐matched clusters. Our study included 44 886 HF patients enrolled in the Swedish Heart Failure Registry between 2000 and 2012. Random forest modeling demonstrated excellent calibration and discrimination for survival (C‐statistic=0.83) whereas left ventricular ejection fraction did not (C‐statistic=0.52): there were no meaningful differences per strata of left ventricular ejection fraction (1‐year survival: 80%, 81%, 83%, and 84%). Cluster analysis using the 8 highest predictive variables identified 4 clinically relevant subgroups of HF with marked differences in 1‐year survival. There were significant interactions between propensity‐matched clusters (across age, sex, and left ventricular ejection fraction and the following medications: diuretics, angiotensin‐converting enzyme inhibitors, β‐blockers, and nitrates, P<0.001, all).ConclusionsMachine learning algorithms accurately predicted outcomes in a large data set of HF patients. Cluster analysis identified 4 distinct phenotypes that differed significantly in outcomes and in response to therapeutics. Use of these novel analytic approaches has the potential to enhance effectiveness of current therapies and transform future HF clinical trials.

show abstract

“…In a recent, methodologically sound study, Frizzell et al showed that machine learning approaches performed poorly compared with traditional statistical methods in the context of congestive heart failure readmission prediction 41. As the authors themselves conclude, results of their large-scale machine learning attempt to predict readmissions are largely not concordant with both earlier and emerging findings 9 42.…”

Section: Introductionmentioning

confidence: 98%

Machine learning in cardiovascular medicine: are we there yet?

Shameer

Johnson

Glicksberg

et al. 2018

Heart

389

229

View full text Add to dashboard Cite

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine.

show abstract

Prediction of 30-Day All-Cause Readmissions in Patients Hospitalized for Heart Failure

Cited by 288 publications

References 14 publications

Serum Neprilysin and Recurrent Admissions in Patients With Heart Failure

Serum Neprilysin and Recurrent Admissions in Patients With Heart Failure

Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients

Machine learning in cardiovascular medicine: are we there yet?

Contact Info

Product

Resources

About