Dataset Information

Machine learning-based model for predicting 1 year mortality of hospitalized patients with heart failure.

ABSTRACT:

Aims

Individual risk stratification is a fundamental strategy in managing patients with heart failure (HF). Artificial intelligence, particularly machine learning (ML), can develop superior models for predicting the prognosis of HF patients, and administrative claim data (ACD) are suitable for ML analysis because ACD is a structured database. The objective of this study was to analyse ACD using an ML algorithm, predict the 1 year mortality of patients with HF, and finally develop an easy-to-use prediction model with high accuracy using the top predictors identified by the ML algorithm.

Methods and results

Machine learning-based prognostic prediction models were developed from the ACD on 10 175 HF patients from the Japanese Registry of Acute Decompensated Heart Failure with 17% mortality during 1 year follow-up. The top predictors for prognosis in HF were identified by the permutation feature importance technique, and an easy-to-use prediction model was developed based on these predictors. The c-statistics and Brier scores of the developed ML-based models were compared with those of conventional risk models: Seattle Heart Failure Model (SHFM) and Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC). A voting classifier algorithm (ACD-VC) achieved the highest c-statistics among the six ML algorithms. The permutation feature importance technique enabled identification of the top predictors such as Barthel index, age, body mass index, duration of hospitalization, last hospitalization, renal disease, and non-loop diuretics use (feature importance values were 0.054, 0.025, 0.010, 0.005, 0.005, 0.004, and 0.004, respectively). Upon combination of some of the predictors that can be assessed from a brief interview, the Simple Model by ARTificial intelligence for HF risk stratification (SMART-HF) was established as an easy-to-use prediction model. Compared with the conventional models, SMART-HF achieved a higher c-statistic {ACD-VC: 0.777 [95% confidence interval (CI) 0.751-0.803], SMART-HF: 0.765 [95% CI 0.739-0.791], SHFM: 0.713 [95% CI 0.684-0.742], MAGGIC: 0.726 [95% CI 0.698-0.753]} and better Brier scores (ACD-VC: 0.121, SMART-HF: 0.124, SHFM: 0.139, MAGGIC: 0.130).

Conclusions

The ML model based on ACD predicted the 1 year mortality of HF patients with high accuracy, and SMART-HF along with the ML model achieved superior performance to that of the conventional risk models. The SMART-HF model has the clear merit of easy operability even by non-healthcare providers with a user-friendly online interface (https://hfriskcalculator.herokuapp.com/). Risk models developed using SMART-HF may provide a novel modality for risk stratification of patients with HF.

SUBMITTER: Tohyama T

PROVIDER: S-EPMC8497366 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

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:AimsPredicting the risk of malignant arrhythmias (MA) in hospitalized patients with heart failure (HF) is challenging. Machine learning (ML) can handle a large volume of complex data more effectively than traditional statistical methods. This study explored the feasibility of ML methods for predicting the risk of MA in hospitalized HF patients.Methods and resultsWe evaluated the baseline data and MA events of 2794 hospitalized HF patients in the HF cohort in Anhui Province and randomly divided the study population into training and validation sets in a 7:3 ratio. The Lasso-logistic regression, multivariate adaptive regression splines (MARS), classification and regression tree (CART), random forest (RF), and eXtreme gradient boosting (XGBoost) algorithms were used to construct risk prediction models in the training set, and model performance was verified in the validation set. The area under the receiver operating characteristic curve (AUC) and Brier score were employed to evaluate the discrimination and calibration of the model, respectively. Clinical utility of the Lasso-logistic regression model was analysed using decision curve analysis (DCA). The median (Q1, Q3) age of the study population was 70 (61, 77) years, and 39.5% were female. MA events occurred in 117 patients (4.2%) during hospitalization. In the training set (n = 1964), the AUC of the XGBoost model was 0.998 [95% confidence interval (CI) 0.997-1.000], which was higher than the other models (all P < 0.001). In the validation set (n = 830), there was no significant difference in AUC of Lasso-logistic model 1 [AUC: 0.867 (95% CI 0.819-0.915)], Lasso-logistic model 2 [AUC: 0.828 (95% CI 0.764-0.892)], MARS model [AUC: 0.852 (95% CI 0.793-0.910)], RF model [AUC: 0.804 (95% CI 0.726-0.881)], and XGBoost model [AUC: 0.864 (95% CI 0.810-0.918); all P > 0.05], which were higher than that of CART model [AUC: 0.743 (95% CI 0.661-0.824); all P < 0.05]. Brier scores for all prediction models were less than 0.05. DCA results showed that the Lasso-logistic model had a net clinical benefit. Oral antiarrhythmic drug, left bundle branch block, serum magnesium, d-dimer, and random blood glucose were significant predictors in half or more of the models.ConclusionsThe current study findings suggest that ML models based on the Lasso-logistic regression, MARS, RF, and XGBoost algorithms can effectively predict the risk of MA in hospitalized HF patients. The Lasso-logistic model had better clinical interpretability and ease of use than the other models.

Project description:Background: Development of advanced heart failure (HF) symptoms is the most common adverse pathway in hypertrophic cardiomyopathy (HCM) patients. Currently, there is a limited ability to identify HCM patients at risk of HF. Objectives: In this study, we present a machine learning (ML)-based model to identify individual HCM patients who are at high risk of developing advanced HF symptoms. Methods: From a consecutive cohort of HCM patients evaluated at the Tufts HCM Institute from 2001 to 2018, we extracted a set of 64 potential risk factors measured at baseline. Only patients with New York Heart Association (NYHA) functional class I/II and LV ejection fraction (LVEF) by echocardiography >35% were included. The study cohort (n = 1,427 patients) was split into three disjoint subsets: development (50%), model selection (10%), and independent validation (40%). The least absolute shrinkage and selection operator was used to select the most influential clinical variables. An ensemble of ML classifiers, including logistic regression, was used to identify patients with high risk of developing a HF outcome. Study outcomes were defined as progression to NYHA class III/IV, drop in LVEF below 35%, septal reduction procedure, and/or heart transplantation. Results: During a mean follow-up of 4.7 ± 3.7 years, advanced HF occurred in 283 (20% out of 1,427) patients. The model features included patients' sex, NYHA class (I or II), HCM type (i.e., obstructive or not), LV wall thickness, LVEF, presence of HF symptoms (e.g., dyspnea, presyncope), comorbidities (atrial fibrillation, hypertension, mitral regurgitation, and systolic anterior motion), and type of cardiac medications. The developed risk stratification model showed strong differentiation power to identify patients at advanced HF risk in the testing dataset (c-statistics = 0.81; 95% confidence interval [CI]: 0.76, 0.86). The model allowed correct identification of high-risk patients with accuracy 74% (CI: 0.70, 0.78), sensitivity 80% (CI: 0.77, 0.83), and specificity 72% (CI: 0.68, 0.76). The model performance was comparable among different sex and age groups. Conclusions: A 5-year risk prediction of progressive HF in HCM patients can be accurately estimated using ML analysis of patients' clinical and imaging parameters. A set of 17 clinical and imaging variables were identified as the most important predictors of progressive HF in HCM.

Project description:To phenotype mechanistic differences between heart failure with reduced (HFrEF) and preserved (HFpEF) ejection fraction, a closed-loop model of the cardiovascular system coupled with patient-specific transthoracic echocardiography (TTE) and right heart catheterization (RHC) data was used to identify key parameters representing haemodynamics. Thirty-one patient records (10 HFrEF, 21 HFpEF) were obtained from the Cardiovascular Health Improvement Project database at the University of Michigan. Model simulations were tuned to match RHC and TTE pressure, volume, and cardiac output measurements in each patient. The underlying physiological model parameters were plotted against model-based norms and compared between HFrEF and HFpEF. Our results confirm the main mechanistic parameter driving HFrEF is reduced left ventricular (LV) contractility, whereas HFpEF exhibits a heterogeneous phenotype. Conducting principal component analysis, k -means clustering, and hierarchical clustering on the optimized parameters reveal (i) a group of HFrEF-like HFpEF patients (HFpEF1), (ii) a classic HFpEF group (HFpEF2), and (iii) a group of HFpEF patients that do not consistently cluster (NCC). These subgroups cannot be distinguished from the clinical data alone. Increased LV active contractility ( p<0.001 ) and LV passive stiffness ( p<0.001 ) at rest are observed when comparing HFpEF2 to HFpEF1. Analysing the clinical data of each subgroup reveals that elevated systolic and diastolic LV volumes seen in both HFrEF and HFpEF1 may be used as a biomarker to identify HFrEF-like HFpEF patients. These results suggest that modelling of the cardiovascular system and optimizing to standard clinical data can designate subgroups of HFpEF as separate phenotypes, possibly elucidating patient-specific treatment strategies. KEY POINTS: Analysis of data from right heart catheterization (RHC) and transthoracic echocardiography (TTE) of heart failure (HF) patients using a closed-loop model of the cardiovascular system identifies key parameters representing haemodynamic cardiovascular function in patients with heart failure with reduced and preserved ejection fraction (HFrEF and HFpEF). Analysing optimized parameters representing cardiovascular function using machine learning shows mechanistic differences between HFpEF groups that are not seen analysing clinical data alone. HFpEF groups presented here can be subdivided into three subgroups: HFpEF1 described as 'HFrEF-like HFpEF', HFpEF2 as 'classic HFpEF', and a third group of HFpEF patients that do not consistently cluster. Focusing purely on cardiac function consistently captures the underlying dysfunction in HFrEF, whereas HFpEF is better characterized by dysfunction in the entire cardiovascular system. Our methodology reveals that elevated left ventricular systolic and diastolic volumes are potential biomarkers for identifying HFrEF-like HFpEF patients.

Project description:AimsFrailty may be found in heart failure patients especially in the elderly and is associated with a poor prognosis. However, assessment of frailty status is time-consuming, and the electronic frailty indices developed using health records have served as useful surrogates. We hypothesized that an electronic frailty index developed using machine learning can improve short-term mortality prediction in patients with heart failure.Methods and resultsThis was a retrospective observational study that included patients admitted to nine public hospitals for heart failure from Hong Kong between 2013 and 2017. Age, sex, variables in the modified frailty index, Deyo's Charlson co-morbidity index (≥2), neutrophil-to-lymphocyte ratio (NLR), and prognostic nutritional index at baseline were analysed. Gradient boosting, which is a supervised sequential ensemble learning algorithm with weak prediction submodels (typically decision trees), was applied to predict mortality. Variables were ranked in the order of importance with a total score of 100 and used to build the frailty models. Comparisons were made with decision tree and multivariable logistic regression. A total of 8893 patients (median: age 81, Q1-Q3: 71-87 years old) were included, in whom 9% had 30 day mortality and 17% had 90 day mortality. Prognostic nutritional index, age, and NLR were the most important variables predicting 30 day mortality (importance score: 37.4, 32.1, and 20.5, respectively) and 90 day mortality (importance score: 35.3, 36.3, and 14.6, respectively). Gradient boosting significantly outperformed decision tree and multivariable logistic regression. The area under the curve from a five-fold cross validation was 0.90 for gradient boosting and 0.87 and 0.86 for decision tree and logistic regression in predicting 30 day mortality. For the prediction of 90 day mortality, the area under the curve was 0.92, 0.89, and 0.86 for gradient boosting, decision tree, and logistic regression, respectively.ConclusionsThe electronic frailty index based on co-morbidities, inflammation, and nutrition information can readily predict mortality outcomes. Their predictive performances were significantly improved by gradient boosting techniques.

Project description:Abstract Aims The development of acute heart failure (AHF) is a critical decision point in the natural history of the disease and carries a dismal prognosis. The lack of appropriate risk-stratification tools at hospital discharge of AHF patients significantly limits clinical ability to precisely tailor patient-specific therapeutic regimen at this pivotal juncture. Machine learning-based strategies may improve risk stratification by incorporating analysis of high-dimensional patient data with multiple covariates and novel prediction methodologies. In the current study, we aimed at evaluating the drivers for success in prediction models and establishing an institute-tailored artificial Intelligence-based prediction model for real-time decision support. Methods and results We used a cohort of all 10 868 patients AHF patients admitted to a tertiary hospital during a 12 years period. A total of 372 covariates were collected from admission to the end of the hospitalization. We assessed model performance across two axes: (i) type of prediction method and (ii) type and number of covariates. The primary outcome was 1-year survival from hospital discharge. For the model-type axis, we experimented with seven different methods: logistic regression (LR) with either L1 or L2 regularization, random forest (RF), Cox proportional hazards model (Cox), extreme gradient boosting (XGBoost), a deep neural-net (NeuralNet) and an ensemble classifier of all the above methods. We were able to achieve an area under receiver operator curve (AUROC) prediction accuracy of more than 80% with most prediction models including L1/L2-LR (80.4%/80.3%), Cox (80.2%), XGBoost (80.5%), NeuralNet (80.4%). RF was inferior to other methods (78.8%), and the ensemble model was slightly superior (81.2%). The number of covariates was a significant modifier (P < 0.001) of prediction success, the use of multiplex-covariates preformed significantly better (AUROC 80.4% for L1-LR) compared with a set of known clinical covariates (AUROC 77.8%). Demographics followed by lab-tests and administrative data resulted in the largest gain in model performance. Conclusions The choice of the predictive modelling method is secondary to the multiplicity and type of covariates for predicting AHF prognosis. The application of a structured data pre-processing combined with the use of multiple-covariates results in an accurate, institute-tailored risk prediction in AHF Graphical Abstract Graphical Abstract

Project description:BackgroundPatients with heart failure (HF) with diabetes may face a poorer prognosis and higher mortality than patients with either disease alone, especially for those in intensive care unit. So far, there is no precise mortality risk prediction indicator for this kind of patient.MethodTwo high-quality critically ill databases, the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and the Telehealth Intensive Care Unit (eICU) Collaborative Research Database (eICU-CRD) Collaborative Research Database, were used for study participants' screening as well as internal and external validation. Nine machine learning models were compared, and the best one was selected to define indicators associated with hospital mortality for patients with HF with diabetes. Existing attributes most related to hospital mortality were identified using a visualization method developed for machine learning, namely, Shapley Additive Explanations (SHAP) method. A new composite indicator ASL was established using logistics regression for patients with HF with diabetes based on major existing indicators. Then, the new index was compared with existing indicators to confirm its discrimination ability and clinical value using the receiver operating characteristic (ROC) curve, decision curve, and calibration curve.ResultsThe random forest model outperformed among nine models with the area under the ROC curve (AUC) = 0.92 after hyper-parameter optimization. By using this model, the top 20 attributes associated with hospital mortality in these patients were identified among all the attributes based on SHAP method. Acute Physiology Score (APS) III, Sepsis-related Organ Failure Assessment (SOFA), and Max lactate were selected as major attributes related to mortality risk, and a new composite indicator was developed by combining these three indicators, which was named as ASL. Both in the initial and external cohort, the new indicator, ASL, had greater risk discrimination ability with AUC higher than 0.80 in both low- and high-risk groups compared with existing attributes. The decision curve and calibration curve indicated that this indicator also had a respectable clinical value compared with APS III and SOFA. In addition, this indicator had a good risk stratification ability when the patients were divided into three risk levels.ConclusionA new composite indicator for predicting mortality risk in patients with HF with diabetes admitted to intensive care unit was developed on the basis of attributes identified by the random forest model. Compared with existing attributes such as APS III and SOFA, the new indicator had better discrimination ability and clinical value, which had potential value in reducing the mortality risk of these patients.