Dataset Information

Machine Learning-Driven Models to Predict Prognostic Outcomes in Patients Hospitalized With Heart Failure Using Electronic Health Records: Retrospective Study.

ABSTRACT:

Background

With the prevalence of cardiovascular diseases increasing worldwide, early prediction and accurate assessment of heart failure (HF) risk are crucial to meet the clinical demand.

Objective

Our study objective was to develop machine learning (ML) models based on real-world electronic health records to predict 1-year in-hospital mortality, use of positive inotropic agents, and 1-year all-cause readmission rate.

Methods

For this single-center study, we recruited patients with newly diagnosed HF hospitalized between December 2010 and August 2018 at the First Affiliated Hospital of Dalian Medical University (Liaoning Province, China). The models were constructed for a population set (90:10 split of data set into training and test sets) using 79 variables during the first hospitalization. Logistic regression, support vector machine, artificial neural network, random forest, and extreme gradient boosting models were investigated for outcome predictions.

Results

Of the 13,602 patients with HF enrolled in the study, 537 (3.95%) died within 1 year and 2779 patients (20.43%) had a history of use of positive inotropic agents. ML algorithms improved the performance of predictive models for 1-year in-hospital mortality (areas under the curve [AUCs] 0.92-1.00), use of positive inotropic medication (AUCs 0.85-0.96), and 1-year readmission rates (AUCs 0.63-0.96). A decision tree of mortality risk was created and stratified by single variables at levels of high-sensitivity cardiac troponin I (<0.068 μg/L), followed by percentage of lymphocytes (<14.688%) and neutrophil count (4.870×10⁹/L).

Conclusions

ML techniques based on a large scale of clinical variables can improve outcome predictions for patients with HF. The mortality decision tree may contribute to guiding better clinical risk assessment and decision making.

SUBMITTER: Lv H

PROVIDER: S-EPMC8094022 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Heart failure is one of the leading causes of hospitalization in the United States. Advances in big data solutions allow for storage, management, and mining of large volumes of structured and semi-structured data, such as complex healthcare data. Applying these advances to complex healthcare data has led to the development of risk prediction models to help identify patients who would benefit most from disease management programs in an effort to reduce readmissions and healthcare cost, but the results of these efforts have been varied. The primary aim of this study was to develop a 30-day readmission risk prediction model for heart failure patients discharged from a hospital admission. METHODS:We used longitudinal electronic medical record data of heart failure patients admitted within a large healthcare system. Feature vectors included structured demographic, utilization, and clinical data, as well as selected extracts of un-structured data from clinician-authored notes. The risk prediction model was developed using deep unified networks (DUNs), a new mesh-like network structure of deep learning designed to avoid over-fitting. The model was validated with 10-fold cross-validation and results compared to models based on logistic regression, gradient boosting, and maxout networks. Overall model performance was assessed using concordance statistic. We also selected a discrimination threshold based on maximum projected cost saving to the Partners Healthcare system. RESULTS:Data from 11,510 patients with 27,334 admissions and 6369 30-day readmissions were used to train the model. After data processing, the final model included 3512 variables. The DUNs model had the best performance after 10-fold cross-validation. AUCs for prediction models were 0.664?±?0.015, 0.650?±?0.011, 0.695?±?0.016 and 0.705?±?0.015 for logistic regression, gradient boosting, maxout networks, and DUNs respectively. The DUNs model had an accuracy of 76.4% at the classification threshold that corresponded with maximum cost saving to the hospital. CONCLUSIONS:Deep learning techniques performed better than other traditional techniques in developing this EMR-based prediction model for 30-day readmissions in heart failure patients. Such models can be used to identify heart failure patients with impending hospitalization, enabling care teams to target interventions at their most high-risk patients and improving overall clinical outcomes.

Project description:Importance:Accurate risk stratification of patients with heart failure (HF) is critical to deploy targeted interventions aimed at improving patients' quality of life and outcomes. Objectives:To compare machine learning approaches with traditional logistic regression in predicting key outcomes in patients with HF and evaluate the added value of augmenting claims-based predictive models with electronic medical record (EMR)-derived information. Design, Setting, and Participants:A prognostic study with a 1-year follow-up period was conducted including 9502 Medicare-enrolled patients with HF from 2 health care provider networks in Boston, Massachusetts ("providers" includes physicians, clinicians, other health care professionals, and their institutions that comprise the networks). The study was performed from January 1, 2007, to December 31, 2014; data were analyzed from January 1 to December 31, 2018. Main Outcomes and Measures:All-cause mortality, HF hospitalization, top cost decile, and home days loss greater than 25% were modeled using logistic regression, least absolute shrinkage and selection operation regression, classification and regression trees, random forests, and gradient-boosted modeling (GBM). All models were trained using data from network 1 and tested in network 2. After selecting the most efficient modeling approach based on discrimination, Brier score, and calibration, area under precision-recall curves (AUPRCs) and net benefit estimates from decision curves were calculated to focus on the differences when using claims-only vs claims + EMR predictors. Results:A total of 9502 patients with HF with a mean (SD) age of 78 (8) years were included: 6113 from network 1 (training set) and 3389 from network 2 (testing set). Gradient-boosted modeling consistently provided the highest discrimination, lowest Brier scores, and good calibration across all 4 outcomes; however, logistic regression had generally similar performance (C statistics for logistic regression based on claims-only predictors: mortality, 0.724; 95% CI, 0.705-0.744; HF hospitalization, 0.707; 95% CI, 0.676-0.737; high cost, 0.734; 95% CI, 0.703-0.764; and home days loss claims only, 0.781; 95% CI, 0.764-0.798; C statistics for GBM: mortality, 0.727; 95% CI, 0.708-0.747; HF hospitalization, 0.745; 95% CI, 0.718-0.772; high cost, 0.733; 95% CI, 0.703-0.763; and home days loss, 0.790; 95% CI, 0.773-0.807). Higher AUPRCs were obtained for claims + EMR vs claims-only GBMs predicting mortality (0.484 vs 0.423), HF hospitalization (0.413 vs 0.403), and home time loss (0.575 vs 0.521) but not cost (0.249 vs 0.252). The net benefit for claims + EMR vs claims-only GBMs was higher at various threshold probabilities for mortality and home time loss outcomes but similar for the other 2 outcomes. Conclusions and Relevance:Machine learning methods offered only limited improvement over traditional logistic regression in predicting key HF outcomes. Inclusion of additional predictors from EMRs to claims-based models appeared to improve prediction for some, but not all, outcomes.

Project description:AimsThe aim of this study was to generate a biomarker-driven prognostic tool for patients with chronic HFrEF. Circulating levels of N-terminal pro B-type natriuretic peptide (NT-proBNP) and high-sensitivity cardiac troponin T (hs-cTnT) each have a marked positive relationship with adverse outcomes in heart failure with reduced ejection fraction (HFrEF). A risk model incorporating biomarkers and clinical variables has not been validated in contemporary heart failure (HF) trials.Methods and resultsIn EMPEROR-Reduced, 33 candidate variables were pre-selected. Multivariable Cox regression models were developed using stepwise selection for: (i) the primary composite outcome of HF hospitalization or cardiovascular death, (ii) all-cause death, and (iii) cardiovascular mortality. A total of 3730 patients were followed up for a median of 16 months, 823 (22%) patients had a primary outcome and 515 (14%) patients died, of whom 389 (10%) died from a cardiovascular cause. NT-proBNP and hs-cTnT were the dominant predictors of the primary outcome, and in addition, a shorter time since last HF hospitalization, longer time since HF diagnosis, lower systolic blood pressure, New York Heart Association (NYHA) Class III or IV, higher heart rate and peripheral oedema were key predictors (eight variables in total, all P < 0.001). The primary outcome risk score discriminated well (c-statistic = 0.73), with patients in the top 10th of risk having an event rate >9 times higher than those in the bottom 10th. Empagliflozin benefitted patients across risk levels for the primary outcome. NT-proBNP and hs-cTnT were also the dominant predictors of all-cause and cardiovascular mortality, followed by NYHA Class III or IV and ischaemic aetiology (four variables in total, all P < 0.001). The mortality risk model presented good event discrimination for all-cause and cardiovascular mortality (c-statistic = 0.69 for both). These simple models were externally validated in the BIOSTAT-CHF study, achieving similar c-statistics.ConclusionsThe combination of NT-proBNP and hs-cTnT with a small number of readily available clinical variables provides prognostic assessment for patients with HFrEF. This predictive tool kit can be easily implemented for routine clinical use.

Project description:B-type natriuretic peptide (BNP) has prognostic significance in heart failure (HF), and reductions in BNP may predict clinical improvement. However, there are limited data regarding the prognostic value of BNP during short-term follow-up. The aim of this study was to evaluate the relationship between short-term follow-up BNP and mortality after discharge in patients with HF.We analyzed 427 patients hospitalized with HF from the Wonju Severance Christian Hospital Heart Failure Registry from April 2011 to December 2013, with a planned follow-up period through February 2016. Of the 427 patients, 240 (mean age, 75 years; 102 males, 42.5%) had BNP measured on admission and within the short-term follow-up period (3 months). We compared all-cause mortality during the clinical follow-up period (median length of follow-up, 709.5 days) according to the median value of BNP on admission (as a baseline value) and over a short-term follow-up period after discharge.Median BNP at admission was 816.5 pg/ml, and median follow-up BNP was 369.7 pg/ml. Multivariate analysis revealed a positive association between risk of death and high BNP. High BNP during follow-up was significantly associated with a greater risk of all-cause mortality compared to low BNP (P < 0.001). Initial BNP was not significantly associated with all-cause mortality. A multivariate model showed that follow-up BNP and percent change in BNP were independently associated with all-cause mortality after adjustment for covariates. Of the 3 BNP measurement strategies, BNP after discharge (IDI of 0.072, P < .0001 and NRI of 0.707, P < .0001) and percent change in BNP (IDI of 0.113, P < .0001 and NRI of 0.782, P < .0001) demonstrated the greatest increase in discrimination and net reclassification for mortality. Unfortunately, we did not find any significant value with initial BNP. Kaplan-Meier survival analysis was performed to assess mortality stratified by BNP according to the median value, high median of follow-up BNP and percent change in BNP were associated with significantly higher mortality compared to the below median (log-rank, p < 0.001).Short-term follow-up BNP and percent change in BNP level are significant prognostic factors of all-cause mortality. These values will be clinically useful when evaluating prognosis in hospitalized patients with heart failure.