Dataset Information

Predicting 90?day acute heart failure readmission and death using machine learning-supported decision analysis.

ABSTRACT: Readmission or death soon after heart failure (HF) admission is a significant problem. Traditional analyses for predicting such events often fail to consider the gamut of characteristics that may contribute- tending to focus on 30-day outcomes even though the window of increased vulnerability may last up to 90?days. Risk assessments incorporating machine learning (ML) methods may be better suited than traditional statistical analyses alone to sort through multitude of data in the electronic health record (EHR) and identify patients at higher risk. HYPOTHESIS: ML-based decision analysis may better identify patients at increased risk for 90-day acute HF readmission or death after incident HF admission. METHODS AND RESULTS: Among 3189 patients who underwent index HF hospitalization, 15.2% experienced primary or acute HF readmission and 11.5% died within 90?days. For risk assessment models, 98 variables were considered across nine data categories. ML techniques were used to help select variables for a final logistic regression (LR) model. The final model's AUC was 0.760 (95% CI 0.752 to 0.767), with sensitivity of 83%. This proved superior to an LR model alone [AUC 0.744 (95% CI 0.732 to 0.755)]. Eighteen variables were identified as risk factors including dilated inferior vena cava, elevated blood pressure, elevated BUN, reduced albumin, abnormal sodium or bicarbonate, and NT pro-BNP elevation. A risk prediction ML-based model developed from comprehensive characteristics within the EHR can efficiently identify patients at elevated risk of 90-day acute HF readmission or death for whom closer follow-up or further interventions may be considered.

SUBMITTER: Sarijaloo F

PROVIDER: S-EPMC7852168 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting 90 day acute heart failure readmission and death using machine learning-supported decision analysis.

Sarijaloo FarnazBabaie F Park Jaeyoung J Zhong Xiang X Wokhlu Anita A

Clinical cardiology 20201223 2

Readmission or death soon after heart failure (HF) admission is a significant problem. Traditional analyses for predicting such events often fail to consider the gamut of characteristics that may contribute- tending to focus on 30-day outcomes even though the window of increased vulnerability may last up to 90 days. Risk assessments incorporating machine learning (ML) methods may be better suited than traditional statistical analyses alone to sort through multitude of data in the electronic heal ...[more]

PMID: 33355945

Similar Datasets

Project description:AimsThis study aimed to review the performance of machine learning (ML) methods compared with conventional statistical models (CSMs) for predicting readmission and mortality in patients with heart failure (HF) and to present an approach to formally evaluate the quality of studies using ML algorithms for prediction modelling.Methods and resultsFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we performed a systematic literature search using MEDLINE, EPUB, Cochrane CENTRAL, EMBASE, INSPEC, ACM Library, and Web of Science. Eligible studies included primary research articles published between January 2000 and July 2020 comparing ML and CSMs in mortality and readmission prognosis of initially hospitalized HF patients. Data were extracted and analysed by two independent reviewers. A modified CHARMS checklist was developed in consultation with ML and biostatistics experts for quality assessment and was utilized to evaluate studies for risk of bias. Of 4322 articles identified and screened by two independent reviewers, 172 were deemed eligible for a full-text review. The final set comprised 20 articles and 686 842 patients. ML methods included random forests (n = 11), decision trees (n = 5), regression trees (n = 3), support vector machines (n = 9), neural networks (n = 12), and Bayesian techniques (n = 3). CSMs included logistic regression (n = 16), Cox regression (n = 3), or Poisson regression (n = 3). In 15 studies, readmission was examined at multiple time points ranging from 30 to 180 day readmission, with the majority of studies (n = 12) presenting prediction models for 30 day readmission outcomes. Of a total of 21 time-point comparisons, ML-derived c-indices were higher than CSM-derived c-indices in 16 of the 21 comparisons. In seven studies, mortality was examined at 9 time points ranging from in-hospital mortality to 1 year survival; of these nine, seven reported higher c-indices using ML. Two of these seven studies reported survival analyses utilizing random survival forests in their ML prediction models. Both reported higher c-indices when using ML compared with CSMs. A limitation of studies using ML techniques was that the majority were not externally validated, and calibration was rarely assessed. In the only study that was externally validated in a separate dataset, ML was superior to CSMs (c-indices 0.913 vs. 0.835).ConclusionsML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.

Project description:AimsLimited data on the uptake of guideline-directed medical therapies (GDMTs) and the mortality of acute decompensated HF (ADHF) patients are available from India. The National Heart Failure Registry (NHFR) aimed to assess clinical presentation, practice patterns, and the mortality of ADHF patients in India.Methods and resultsThe NHFR is a facility-based, multi-centre clinical registry of consecutive ADHF patients with prospective follow-up. Fifty three tertiary care hospitals in 21 states in India participated in the NHFR. All consecutive ADHF patients who satisfied the European Society of Cardiology criteria were enrolled in the registry. All-cause mortality at 90 days was the main outcome measure. In total, 10 851 consecutive patients were recruited (mean age: 59.9 years, 31% women). Ischaemic heart disease was the predominant aetiology for HF (72%), followed by dilated cardiomyopathy (18%). Isolated right HF was noted in 62 (0.6%) participants. In eligible HF patients, 47.5% received GDMT. The 90 day mortality was 14.2% (14.9% and 13.9% in women and men, respectively) with a re-admission rate of 8.4%. An inverse relationship between educational class based on years of education and 90 day mortality (high mortality in the lowest educational class) was observed in the study population. Patients with HF with reduced ejection fraction and HF with mildly reduced ejection fraction who did not receive GDMT experienced higher mortality (log-rank P < 0.001) than those who received GDMT. Baseline educational class, body mass index, New York Heart Association functional class, ejection fraction, dependent oedema, serum creatinine, QRS > 120 ms, atrial fibrillation, mitral regurgitation, haemoglobin levels, serum sodium, and GDMT independently predicted 90 day mortality.ConclusionOne of seven ADHF patients in the NHFR died during the first 90 days of follow-up. One of two patients received GDMT. Adherence to GDMT improved survival in HF patients with reduced and mildly reduced ejection fractions. Our findings call for innovative quality improvement initiatives to improve the uptake of GDMT among HF patients in India.

Dataset Information

Predicting 90?day acute heart failure readmission and death using machine learning-supported decision analysis.

Publications

Predicting 90 day acute heart failure readmission and death using machine learning-supported decision analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets