A Machine Learning Approach to Management of Heart Failure Populations

Prediction of mortality in heart failure by machine learning. Comparison with statistical modeling

BACKGROUND

Assessing the relative performance of machine learning (ML) methods and conventional statistical methods in predicting prognosis in heart failure (HF) still remains a challenging research field.

METHODS

The primary outcome was three-year mortality. The following 5 machine learning approaches were used for modeling: Random Forest (RF), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Multilayer perceptron. We compared the performance of the best performing ML models to the MAGGIC (Meta-analysis Global Group in Chronic Heart Failure) score and a novel logistic regression model (LRM) developed using the same set of variables used to develop the machine learning models. The performance was determined based on discrimination, calibration, and net benefit.

RESULTS

The XGBoost and the RF were the best performing ML models. The XGBoost provided the highest discrimination (C-statistic: 0.793) and the lowest Brier score (0.178); the RF model had a C-statistic of 0.779 and provided the highest area under the precision-recall curve (0.636). Both models were well calibrated. Both the XGboost and RF models outperformed MAGGIC score. The LRM had a C-statistic of 0.811 and a Brier score of 0.160 and was well calibrated. The XGBoost, RF, and LRM gave a higher net benefit than MAGGIC score; the XGBoost, RF, and logistic regression model gave similar net benefit.

CONCLUSIONS

RF and XGBoost models outperformed MAGGIC in predicting mortality. However, they did not offer any improvement over a logistic regression model built using the same set of covariates considered in the ML modeling.

Health Care Professionals and Data Scientists' Perspectives on a Machine Learning System to Anticipate and Manage the Risk of Decompensation From Patients With Heart Failure: Qualitative Interview Study

BACKGROUND

Heart failure (HF) is a significant global health problem, affecting approximately 64.34 million people worldwide. The worsening of HF, also known as HF decompensation, is a major factor behind hospitalizations, contributing to substantial health care costs related to this condition.

OBJECTIVE

This study aimed to explore the perspectives of health care professionals and data scientists regarding the relevance, challenges, and potential benefits of using machine learning (ML) models to predict decompensation from patients with HF.

METHODS

A total of 13 individual, semistructured, qualitative interviews were conducted in Portugal between October 31, 2022, and June 23, 2023. Participants represented different health care specialties and were selected from different contexts and regions of the country to ensure a comprehensive understanding of the topic. Data saturation was determined as the point at which no new themes emerged from participants' perspectives, ensuring a sufficient sample size for analysis. The interviews were audio recorded, transcribed, and analyzed using MAXQDA (VERBI Software GmbH) through a reflexive thematic analysis. Two researchers (JS and AH) coded the interviews to ensure the consistency of the codes. Ethical approval was granted by the NOVA National School of Public Health ethics committee (CEENSP 14/2022), and informed consent was obtained from all participants.

RESULTS

The participants recognized the potential benefits of ML models for early detection, risk stratification, and personalized care of patients with HF. The importance of selecting appropriate variables for model development, such as rapid weight gain and symptoms, was emphasized. The use of wearables for recording vital signs was considered necessary, although challenges related to adoption among older patients were identified. Risk stratification emerged as a crucial aspect, with the model needing to identify patients at high-, medium-, and low-risk levels. Participants emphasized the need for a response model involving health care professionals to validate ML-generated alerts and determine appropriate interventions.

CONCLUSIONS

The study's findings highlight ML models' potential benefits and challenges for predicting HF decompensation. The relevance of ML models for improving patient outcomes, reducing health care costs, and promoting patient engagement in disease management is highlighted. Adequate variable selection, risk stratification, and response models were identified as essential components for the effective implementation of ML models in health care. In addition, the study identified technical, regulatory and ethical, and adoption and acceptance challenges that need to be overcome for the successful integration of ML models into clinical workflows. Interpretation of the findings suggests that future research should focus on more extensive and diverse samples, incorporate the patient perspective, and explore the impact of ML models on patient outcomes and personalized care in HF management. Incorporation of this study's findings into practice is expected to contribute to developing and implementing ML-based predictive models that positively impact HF management.

Fluid volume status detection model for patients with heart failure based on machine learning methods

Backgroud

Fluid volume abnormalities are a major cause of exacerbations in heart failure patients. However, there is few efficient, rapid, or cost-effective clinical approach for determining volume status, resulting in inadequate or unsatisfactory treatment. The aim was to develop an early fluid volume detection model for heart failure patients utilizing a machine learning stratification.

Methods

The training set data collected by Tianjin Chest Hospital on heart failure patients from December 2016 to December 2021, included 2056 samples and 97 medical characteristics. The minimum Redundancy Maximum Relevance(mRMR) feature selection method was utilized to filter features that were strongly related to the patient's fluid volume status. Four machine learning classification models were used to predict patients' fluid volume status, and their effectiveness was measured using the receiver operating characteristic (ROC) area under the curve (AUC), calibration curve, accuracy, precision, recall, F1 score, specificity, and sensitivity. Data from 186 heart failure patients collected between January 2022 and July 2022 were employed as an external validation set to investigate the effects of model training. SHapley Additive exPlanations (SHAP) were used to interpret the ML models.

Results

Thirty features were selected for model development, and the area under the ROC curve AUC (95 % CI) for the four machine learning models in the testing set was 0.75 (0.73-0.77), 0.77 (0.74-0.79), 0.70 (0.67-0.73), and 0.76 (0.73-0.78), and the AUC (95 % CI) in the external validation set was 0.74 (0.71-0.76), 0.70 (0.67-0.73), 0.64 (0.59-0.68), and 0.67 (0.63-0.71). Logistic regression models were globally interpreted using SHAP-based summary plots.

Conclusions

Machine learning methods are effective in detecting fluid volume status in heart failure patients and can assist physicians with assisted diagnosis, thus helping clinicians to tailor precise management.

Predictive Analytics in Heart Failure Risk, Readmission, and Mortality Prediction: A Review

Heart failure is a leading cause of death among people worldwide. The cost of treatment can be prohibitive, and early prediction of heart failure would reduce treatment costs to patients and hospitals. Improved readmission prediction would also greatly help hospitals, allowing them to manage their treatment programs and budgets better. This literature review aims to summarize recent studies of predictive analytics models that have been constructed to predict heart failure risk, readmission, and mortality. Random forest, logistic regression, neural networks, and XGBoost were among the most common modeling techniques applied. Most selected studies leveraged structured electronic health record data, including demographics, clinical values, lifestyle, and comorbidities, with some incorporating unstructured clinical notes. Preprocessing through imputation and feature selection were frequently employed in building the predictive analytics models. The reviewed studies exhibit demonstrated promise for predictive analytics in improving early heart failure diagnosis, readmission risk stratification, and mortality prediction. This review study highlights rising research activities and the potential of predictive analytics, especially the implementation of machine learning, in advancing heart failure outcomes. Further rigorous, comprehensive syntheses and head-to-head benchmarking of predictive models are needed to derive robust evidence for clinical adoption.

Treatment patterns of patients with worsening heart failure with reduced ejection fraction

AIMS

Patients with HFrEF and worsening HF events (WHFE) are at particularly high risk and urgently need disease-modifying therapy. CHART-HF assessed treatment patterns and reasons for medication decisions among HFrEF patients with and without WHFE.

METHODS AND RESULTS

CHART-HF collected retrospective electronic medical records of outpatients with HF and EF < 45% between 2017-2019 from a nationwide panel of 238 cardiologists (458 patients) and the Geisinger Health System (GHS) medical record (1000 patients). The index visit in the WHFE cohort was the first outpatient cardiologist visit ≤6 months following the WHFE, and in the reference cohort was the last visit in a calendar year without WHFE. Demographic characteristics were similar between patients with and without WHFE in both the nationwide panel and GHS. In the nationwide panel, the proportion of patients with versus without WHFE receiving ≥50% of guideline-recommended dose on index visit was 35% versus 40% for beta blocker, 74% versus 83% for ACEI/ARB/ARNI, and 48% versus 49% for MRA. The proportion of patients receiving ≥50% of guideline-recommended dose was lower in the GHS: 29% versus 34% for beta-blocker, 16% versus 31% for ACEI/ARB/ARNI, and 18% versus 22% for MRA. For patients with and without WHFE, triple therapy on index date was 42% and 44% of patients from the nationwide panel, and 14% and 17% in the GHS. Comparing end of index clinic visit with 12-month follow-up in the GHS, the proportion of patients on no GDMT increased from 14% to 28% in the WHFE cohort and from 14 to 21% in the non-WHFE group.

CONCLUSIONS

Major gaps in use of GDMT, particularly combination therapy, remain among US HFrEF patients. These gaps persist during longitudinal follow-up and are particularly large among patients with recent WHFE.

Prediction model for cardiovascular disease in patients with diabetes using machine learning derived and validated in two independent Korean cohorts

This study aimed to develop and validate a machine learning (ML) model tailored to the Korean population with type 2 diabetes mellitus (T2DM) to provide a superior method for predicting the development of cardiovascular disease (CVD), a major chronic complication in these patients. We used data from two cohorts, namely the discovery (one hospital; n = 12,809) and validation (two hospitals; n = 2019) cohorts, recruited between 2008 and 2022. The outcome of interest was the presence or absence of CVD at 3 years. We selected various ML-based models with hyperparameter tuning in the discovery cohort and performed area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. CVD was observed in 1238 (10.2%) patients in the discovery cohort. The random forest (RF) model exhibited the best overall performance among the models, with an AUROC of 0.830 (95% confidence interval [CI] 0.818-0.842) in the discovery dataset and 0.722 (95% CI 0.660-0.783) in the validation dataset. Creatinine and glycated hemoglobin levels were the most influential factors in the RF model. This study introduces a pioneering ML-based model for predicting CVD in Korean patients with T2DM, outperforming existing prediction tools and providing a groundbreaking approach for early personalized preventive medicine.

Contemporary outpatient management of patients with worsening heart failure with reduced ejection fraction: Clinical outcome results from the CHART-HF study

Background

Based on available data from randomized clinical trials, patients with heart failure with reduced ejection fraction (HFrEF) and worsening HF events (WHFE) have substantial disease burden and poor outcomes. WHFE clinical outcome data in non-clinical trial patients, more representative of the US clinical practice, has not been demonstrated.

Methods and results

CHART-HF collected data from two complementary, non-clinical trial cohort with HFrEF (LVEF <45 %): 1) 1,000 patients from an integrated delivery network and 2) 458 patients from a nationwide physician panel. CHART-HF included patients with WHFE between 2017 and 2019 followed by an index outpatient cardiology visit ≤6 months, and patients without WHFE in a given year between 2017 and 2019, with the last outpatient cardiology visit in the same year as the index visit. Compared to patients without WHFE (after covariate adjustment, all p < 0.05), patients with WHFE had a greater risk of HF-related hospitalization (hazard ratio [HR]: 1.53-2.40) and next WHFE event (HR: 1.67-2.41) following index visits in both cohorts.

Conclusion

HFrEF patients with recent WHFE consistently had worse clinical outcomes in these non-clinical trial cohorts. Despite advances in therapies, unmet need to improve clinical outcomes in HFrEF patients with WHFE remains.

The Efficacy of Machine Learning Models for Predicting the Prognosis of Heart Failure: A Systematic Review and Meta-Analysis

INTRODUCTION

Heart failure (HF) is a major global public health concern. The application of machine learning (ML) to identify individuals at high risk and enable early intervention is a promising approach for improving HF prognosis. We aim to systematically evaluate the performance and value of ML models for predicting HF prognosis.

METHODS

PubMed, Web of Science, Scopus, and Embase online databases were searched up to April 30, 2023, to identify studies on the use of ML models to predict HF prognosis. HF prognosis primarily encompasses readmission and mortality. The meta-analysis was conducted by MedCalc software. Subgroup analyses include grouping based on types of ML models, time intervals, sample sizes, the number of predictive variables, validation methods, whether to conduct hyperparameter optimization and calibration, data set partitioning methods.

RESULTS

A total of 31 studies were included. The most common ML models were random forest, boosting, support vector machine, neural network. The area under the receiver operating characteristic curve (AUC) for predicting HF readmission was 0.675 (95% CI: 0.651-0.699, p < 0.001), and the AUC for predicting HF mortality was 0.790 (95% CI: 0.765-0.816, p < 0.001). Subgroup analyses revealed that models with the prediction time interval of 1 year, sample sizes ≥10,000, the number of predictive variables ≥100, external validation, hyperparameter tuning, calibration adjustment, and data set partitioning using 10-fold cross-validation exhibited favorable performance within their respective subgroups.

CONCLUSION

The performance of ML models in predicting HF readmission is relatively poor, while its performance in predicting HF mortality is moderate. The quality of the relevant studies is generally low, it is essential to enhance the predictive capabilities of ML models through targeted improvements in practical applications.

Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

Mortality Prediction in Patients With or Without Heart Failure Using a Machine Learning Model

Background

Most risk prediction models are confined to specific medical conditions, thus limiting their application to general medical populations.

Objectives

The MARKER-HF (Machine learning Assessment of RisK and EaRly mortality in Heart Failure) risk model was developed in heart failure (HF) patients. We assessed the ability of MARKER-HF to predict 1-year mortality in a large community-based hospital registry database including patients with and without HF.

Methods

This study included 41,749 consecutive patients who underwent echocardiography in a tertiary referral hospital (4,640 patients with and 37,109 without HF). Patients without HF were further subdivided into those with (n = 22,946) and without cardiovascular disease (n = 14,163) and also into cohorts based on recent acute coronary syndrome or history of atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, hypertension, or malignancy.

Results

The median age of the 41,749 patients was 65 years, and 56.2% were male. The receiver operated area under the curves for MARKER-HF prediction of 1-year mortality of patients with HF was 0.729 (95% CI: 0.706-0.752) and for patients without HF was 0.770 (95% CI: 0.760-0.780). MARKER-HF prediction of mortality was consistent across subgroups with and without cardiovascular disease and in patients diagnosed with acute coronary syndrome, atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, or hypertension. Patients with malignancy demonstrated higher mortality at a given MARKER-HF score than did patients in the other groups.

Conclusions

MARKER-HF predicts mortality for patients with HF as well as for patients suffering from a variety of diseases.

A machine learning evaluation of patient characteristics associated with prescribing of guideline-directed medical therapy for heart failure

Introduction/background

Patients with heart failure and reduced ejection fraction (HFrEF) are consistently underprescribed guideline-directed medications. Although many barriers to prescribing are known, identification of these barriers has relied on traditional a priori hypotheses or qualitative methods. Machine learning can overcome many limitations of traditional methods to capture complex relationships in data and lead to a more comprehensive understanding of the underpinnings driving underprescribing. Here, we used machine learning methods and routinely available electronic health record data to identify predictors of prescribing.

Methods

We evaluated the predictive performance of machine learning algorithms to predict prescription of four types of medications for adults with HFrEF: angiotensin converting enzyme inhibitor/angiotensin receptor blocker (ACE/ARB), angiotensin receptor-neprilysin inhibitor (ARNI), evidence-based beta blocker (BB), or mineralocorticoid receptor antagonist (MRA). The models with the best predictive performance were used to identify the top 20 characteristics associated with prescribing each medication type. Shapley values were used to provide insight into the importance and direction of the predictor relationships with medication prescribing.

Results

For 3,832 patients meeting the inclusion criteria, 70% were prescribed an ACE/ARB, 8% an ARNI, 75% a BB, and 40% an MRA. The best-predicting model for each medication type was a random forest (area under the curve: 0.788-0.821; Brier score: 0.063-0.185). Across all medications, top predictors of prescribing included prescription of other evidence-based medications and younger age. Unique to prescribing an ARNI, the top predictors included lack of diagnoses of chronic kidney disease, chronic obstructive pulmonary disease, or hypotension, as well as being in a relationship, nontobacco use, and alcohol use.

Discussion/conclusions

We identified multiple predictors of prescribing for HFrEF medications that are being used to strategically design interventions to address barriers to prescribing and to inform further investigations. The machine learning approach used in this study to identify predictors of suboptimal prescribing can also be used by other health systems to identify and address locally relevant gaps and solutions to prescribing.

Machine Learning for Mortality Prediction in Patients With Heart Failure With Mildly Reduced Ejection Fraction

Background Machine-learning-based prediction models (MLBPMs) have shown satisfactory performance in predicting clinical outcomes in patients with heart failure with reduced and preserved ejection fraction. However, their usefulness has yet to be fully elucidated in patients with heart failure with mildly reduced ejection fraction. This pilot study aims to evaluate the prediction performance of MLBPMs in a heart failure with mildly reduced ejection fraction cohort with long-term follow-up data. Methods and Results A total of 424 patients with heart failure with mildly reduced ejection fraction were enrolled in our study. The primary outcome was all-cause mortality. Two feature selection strategies were introduced for MLBPM development. The "All-in" (67 features) strategy was based on feature correlation, multicollinearity, and clinical significance. The other strategy was the CoxBoost algorithm with 10-fold cross-validation (17 features), which was based on the selection result of the "All-in" strategy. Six MLBPMs with 5-fold cross-validation based on the "All-in" and the CoxBoost algorithm with 10-fold cross-validation strategy were developed by the eXtreme Gradient Boosting, random forest, and support vector machine algorithms. The logistic regression model with 14 benchmark predictors was used as a reference model. During a median follow-up of 1008 (750, 1937) days, 121 patients met the primary outcome. Overall, MLBPMs outperformed the logistic model. The "All-in" eXtreme Gradient Boosting model had the best performance, with an accuracy of 85.4% and a precision of 70.3%. The area under the receiver-operating characteristic curve was 0.916 (95% CI, 0.887-0.945). The Brier score was 0.12. Conclusions The MLBPMs could significantly improve outcome prediction in patients with heart failure with mildly reduced ejection fraction, which would further optimize the management of these patients.

Heart Failure Emergency Readmission Prediction Using Stacking Machine Learning Model

Heart failure is a devastating disease that has high mortality rates and a negative impact on quality of life. Heart failure patients often experience emergency readmission after an initial episode, often due to inadequate management. A timely diagnosis and treatment of underlying issues can significantly reduce the risk of emergency readmissions. The purpose of this project was to predict emergency readmissions of discharged heart failure patients using classical machine learning (ML) models based on Electronic Health Record (EHR) data. The dataset used for this study consisted of 166 clinical biomarkers from 2008 patient records. Three feature selection techniques were studied along with 13 classical ML models using five-fold cross-validation. A stacking ML model was trained using the predictions of the three best-performing models for final classification. The stacking ML model provided an accuracy, precision, recall, specificity, F1-score, and area under the curve (AUC) of 89.41%, 90.10%, 89.41%, 87.83%, 89.28%, and 0.881, respectively. This indicates the effectiveness of the proposed model in predicting emergency readmissions. The healthcare providers can intervene pro-actively to reduce emergency hospital readmission risk and improve patient outcomes and decrease healthcare costs using the proposed model.

Clinical application of artificial intelligence algorithm for prediction of one-year mortality in heart failure patients

Risk prediction for heart failure (HF) using machine learning methods (MLM) has not yet been established at practical application levels in clinical settings. This study aimed to create a new risk prediction model for HF with a minimum number of predictor variables using MLM. We used two datasets of hospitalized HF patients: retrospective data for creating the model and prospectively registered data for model validation. Critical clinical events (CCEs) were defined as death or LV assist device implantation within 1 year from the discharge date. We randomly divided the retrospective data into training and testing datasets and created a risk prediction model based on the training dataset (MLM-risk model). The prediction model was validated using both the testing dataset and the prospectively registered data. Finally, we compared predictive power with published conventional risk models. In the patients with HF (n = 987), CCEs occurred in 142 patients. In the testing dataset, the substantial predictive power of the MLM-risk model was obtained (AUC = 0.87). We generated the model using 15 variables. Our MLM-risk model showed superior predictive power in the prospective study compared to conventional risk models such as the Seattle Heart Failure Model (c-statistics: 0.86 vs. 0.68, p < 0.05). Notably, the model with an input variable number (n = 5) has comparable predictive power for CCE with the model (variable number = 15). This study developed and validated a model with minimized variables to predict mortality more accurately in patients with HF, using a MLM, than the existing risk scores.

Machine learning-based prognostic modeling of patients with acute heart failure receiving furosemide in intensive care units

Purpose

This study developed machine learning models to predict in-hospital mortality, initiation of acute renal replacement therapy, and mechanical ventilation in patients with acute heart failure receiving furosemide in intensive care units.

Method

An extensive database comprising static and dynamic features obtained from a Japanese hospital chain was used to construct and train the machine learning models.

Results

The results revealed that the proposed machine learning models predict in-hospital mortality, initiation of acute renal replacement therapy, and mechanical ventilation with good accuracy. However, the optimal models vary depending on the predicted outcomes. The linear support vector machine classification models exhibited the highest in-hospital mortality and mechanical ventilation prediction accuracy, with the area under the receiver operating characteristic curve of 0.73 and 0.73, respectively, whereas the multi-layer neural network exhibited the highest accuracy for acute renal replacement therapy initiation prediction with an area under the receiver operating characteristic curve of 0.70.

Conclusions

In conclusion, this study demonstrated that machine learning models could help predict the clinical outcomes of patients with acute heart failure receiving furosemide. However, the optimal models may differ depending on the outcome of interest.

The Athlete's Heart and Machine Learning: A Review of Current Implementations and Gaps for Future Research

BACKGROUND

Intense training exercise regimes cause physiological changes within the heart to help cope with the increased stress, known as the "athlete's heart". These changes can mask pathological changes, making them harder to diagnose and increasing the risk of an adverse cardiac outcome.

AIM

This paper reviews which machine learning techniques (ML) are being used within athlete's heart research and how they are being implemented, as well as assesses the uptake of these techniques within this area of research.

METHODS

Searches were carried out on the Scopus and PubMed online datasets and a scoping review was conducted on the studies which were identified.

RESULTS

Twenty-eight studies were included within the review, with ML being directly referenced within 16 (57%). A total of 12 different techniques were used, with the most popular being artificial neural networks and the most common implementation being to perform classification tasks. The review also highlighted the subgroups of interest: predictive modelling, reviews, and wearables, with most of the studies being attributed to the predictive modelling subgroup. The most common type of data used was the electrocardiogram (ECG), with echocardiograms being used the second most often.

CONCLUSION

The results show that over the last 11 years, there has been a growing desire of leveraging ML techniques to help further the understanding of the athlete's heart, whether it be by expanding the knowledge of the physiological changes or by improving the accuracies of models to help improve the treatments and disease management.

Applying an Improved Stacking Ensemble Model to Predict the Mortality of ICU Patients with Heart Failure

Cardiovascular diseases have been identified as one of the top three causes of death worldwide, with onset and deaths mostly due to heart failure (HF). In ICU, where patients with HF are at increased risk of death and consume significant medical resources, early and accurate prediction of the time of death for patients at high risk of death would enable them to receive appropriate and timely medical care. The data for this study were obtained from the MIMIC-III database, where we collected vital signs and tests for 6699 HF patient during the first 24 h of their first ICU admission. In order to predict the mortality of HF patients in ICUs more precisely, an integrated stacking model is proposed and applied in this paper. In the first stage of dataset classification, the datasets were subjected to first-level classifiers using RF, SVC, KNN, LGBM, Bagging, and Adaboost. Then, the fusion of these six classifier decisions was used to construct and optimize the stacked set of second-level classifiers. The results indicate that our model obtained an accuracy of 95.25% and AUROC of 82.55% in predicting the mortality rate of HF patients, which demonstrates the outstanding capability and efficiency of our method. In addition, the results of this study also revealed that platelets, glucose, and blood urea nitrogen were the clinical features that had the greatest impact on model prediction. The results of this analysis not only improve the understanding of patients' conditions by healthcare professionals but allow for a more optimal use of healthcare resources.

Dense phenotyping from electronic health records enables machine learning-based prediction of preterm birth

BACKGROUND

Identifying pregnancies at risk for preterm birth, one of the leading causes of worldwide infant mortality, has the potential to improve prenatal care. However, we lack broadly applicable methods to accurately predict preterm birth risk. The dense longitudinal information present in electronic health records (EHRs) is enabling scalable and cost-efficient risk modeling of many diseases, but EHR resources have been largely untapped in the study of pregnancy.

METHODS

Here, we apply machine learning to diverse data from EHRs with 35,282 deliveries to predict singleton preterm birth.

RESULTS

We find that machine learning models based on billing codes alone can predict preterm birth risk at various gestational ages (e.g., ROC-AUC = 0.75, PR-AUC = 0.40 at 28 weeks of gestation) and outperform comparable models trained using known risk factors (e.g., ROC-AUC = 0.65, PR-AUC = 0.25 at 28 weeks). Examining the patterns learned by the model reveals it stratifies deliveries into interpretable groups, including high-risk preterm birth subtypes enriched for distinct comorbidities. Our machine learning approach also predicts preterm birth subtypes (spontaneous vs. indicated), mode of delivery, and recurrent preterm birth. Finally, we demonstrate the portability of our approach by showing that the prediction models maintain their accuracy on a large, independent cohort (5978 deliveries) from a different healthcare system.

CONCLUSIONS

By leveraging rich phenotypic and genetic features derived from EHRs, we suggest that machine learning algorithms have great potential to improve medical care during pregnancy. However, further work is needed before these models can be applied in clinical settings.

An Artificial Intelligence Approach to Guiding the Management of Heart Failure Patients Using Predictive Models: A Systematic Review

Heart failure (HF) is one of the leading causes of mortality and hospitalization worldwide. The accurate prediction of mortality and readmission risk provides crucial information for guiding decision making. Unfortunately, traditional predictive models reached modest accuracy in HF populations. We therefore aimed to present predictive models based on machine learning (ML) techniques in HF patients that were externally validated. We searched four databases and the reference lists of the included papers to identify studies in which HF patient data were used to create a predictive model. Literature screening was conducted in Academic Search Ultimate, ERIC, Health Source Nursing/Academic Edition and MEDLINE. The protocol of the current systematic review was registered in the PROSPERO database with the registration number CRD42022344855. We considered all types of outcomes: mortality, rehospitalization, response to treatment and medication adherence. The area under the receiver operating characteristic curve (AUC) was used as the comparator parameter. The literature search yielded 1649 studies, of which 9 were included in the final analysis. The AUCs for the machine learning models ranged from 0.6494 to 0.913 in independent datasets, whereas the AUCs for statistical predictive scores ranged from 0.622 to 0.806. Our study showed an increasing number of ML predictive models concerning HF populations, although external validation remains infrequent. However, our findings revealed that ML approaches can outperform conventional risk scores and may play important role in HF management.

Contemporary outpatient management of patients with worsening heart failure with reduced ejection fraction: Rationale and design of the CHART-HF study

BACKGROUND

Patients with heart failure with reduced ejection fraction (HFrEF) and worsening HF events (WHFE) represent a distinct subset of patients with a substantial comorbidity burden, greater potential for intolerance to medical therapy, and high risk of subsequent death, hospitalization and excessive healthcare costs. Although multiple therapies have been shown to be efficacious and safe in this high-risk population, there are limited real-world data regarding factors that impact clinical decision-making when initiating or modifying therapy. Likewise, prior analyses of US clinical practice support major gaps in medical therapy for HFrEF and few medication changes during longitudinal follow-up, yet granular data on reasons why clinicians do not initiate or up-titrate guideline-directed medication are lacking.

METHODS

We designed the CHART-HF study, an observational study of approximately 1,500 patients comparing patients with and without WHFE (WHFE defined as receipt of intravenous diuretics in the inpatient, outpatient, or emergency department setting) who had an index outpatient visit in the US between 2017 and 2019. Patient-level data on clinical characteristics, clinical outcomes, and therapy will be collected from 2 data sources: a single integrated health system, and a national panel of cardiologists. Furthermore, clinician-reported rationale for treatment decisions and the factors prioritized with selection and optimization of therapies in real-world practice will be obtained. To characterize elements of clinician decision-making not documented in the medical record, the panel of cardiologists will review records of patients seen under their care to explicitly note their primary reason for initiating, discontinuing, and titrating medications specific medications, as well as the reason for not making changes to each medication during the outpatient visit.

CONCLUSIONS

Results from CHART-HF have the potential to detail real-world US practice patterns regarding care of patients with HFrEF with versus without a recent WHFE, to examine clinician-reported reasons for use and non-use of guideline-directed medical therapy, and to characterize the magnitude and nature of clinical inertia toward evidence-based medication changes for HFrEF.

Machine learning model for predicting 1-year and 3-year all-cause mortality in ischemic heart failure patients

OBJECTIVE

Machine learning (ML) model has not been developed specifically for ischemic heart failure (HF) patients. Whether the performance of ML model is better than the MAGGIC risk score and NT-proBNP is unknown. The current study was to apply ML algorithm to build risk model for predicting 1-year and 3-year all-cause mortality in ischemic HF patient and to compare the performance of ML model with the MAGGIC risk score and NT-proBNP.

METHOD

Three ML algorithms without and with feature selection were used for model exploration, and the performance was determined based on the area under the curve (AUC) in five-fold cross-validation. The best performing ML model was selected and compared with the MAGGIC risk score and NT-proBNP. The calibration of ML model was assessed by the Brier score.

RESULTS

Random forest with feature selection had the highest AUC (0.742 and 95% CI: 0.697-0.787) for predicting 1-year all-cause mortality, and support vector machine without feature selection had the highest AUC (0.732 and 95% CI: 0.694-0.707) for predicting 3-year all-cause mortality. When compared to the MAGGIC risk score and NT-proBNP, ML model had a comparable AUC for predicting 1-year (0.742 vs 0.714 vs 0.694) and 3-year all-cause mortality (0.732 vs 0.712 vs 0.682). The Brier score for predicting 1-year and 3-year all-cause mortality were 0.068 and 0.174, respectively.

CONCLUSION

ML models predicted prognosis in ischemic HF with good discrimination and well calibration. These models may be used by clinicians as a decision-making tool to estimate the prognosis of ischemic HF patients.

Generalizability and quality control of deep learning-based 2D echocardiography segmentation models in a large clinical dataset

Use of machine learning (ML) for automated annotation of heart structures from echocardiographic videos is an active research area, but understanding of comparative, generalizable performance among models is lacking. This study aimed to (1) assess the generalizability of five state-of-the-art ML-based echocardiography segmentation models within a large Geisinger clinical dataset, and (2) test the hypothesis that a quality control (QC) method based on segmentation uncertainty can further improve segmentation results. Five models were applied to 47,431 echocardiography studies that were independent from any training samples. Chamber volume and mass from model segmentations were compared to clinically-reported values. The median absolute errors (MAE) in left ventricular (LV) volumes and ejection fraction exhibited by all five models were comparable to reported inter-observer errors (IOE). MAE for left atrial volume and LV mass were similarly favorable to respective IOE for models trained for those tasks. A single model consistently exhibited the lowest MAE in all five clinically-reported measures. We leveraged the tenfold cross-validation training scheme of this best-performing model to quantify segmentation uncertainty. We observed that removing segmentations with high uncertainty from 14 to 71% studies reduced volume/mass MAE by 6-10%. The addition of convexity filters improved specificity, efficiently removing < 10% studies with large MAE (16-40%). In conclusion, five previously published echocardiography segmentation models generalized to a large, independent clinical dataset-segmenting one or multiple cardiac structures with overall accuracy comparable to manual analyses-with variable performance. Convexity-reinforced uncertainty QC efficiently improved segmentation performance and may further facilitate the translation of such models.

Loss-of-Function FLNC Variants Are Associated With Arrhythmogenic Cardiomyopathy Phenotypes When Identified Through Exome Sequencing of a General Clinical Population

BACKGROUND

The FLNC gene has recently garnered attention as a likely cause of arrhythmogenic cardiomyopathy, which is considered an actionable genetic condition. However, the association with disease in an unselected clinical population is unknown. We hypothesized that individuals with loss-of-function variants in FLNC (FLNC_LOF) would have increased odds for arrhythmogenic cardiomyopathy-associated phenotypes versus variant-negative controls in the Geisinger MyCode cohort.

METHODS

We identified rare, putative FLNC_LOF among 171 948 individuals with exome sequencing linked to health records. Associations with arrhythmogenic cardiomyopathy phenotypes from available diagnoses and cardiac evaluations were investigated.

RESULTS

Sixty individuals (0.03%; median age 58 years [47-70 interquartile range], 43% male) harbored 27 unique FLNC_LOF. These individuals had significantly increased odds ratios for dilated cardiomyopathy (odds ratio, 4.9 [95% CI, 2.6-7.6]; P<0.001), supraventricular tachycardia (odds ratio, 3.2 [95% CI, 1.1-5.6]; P=0.048), and left-dominant arrhythmogenic cardiomyopathy (odds ratio, 4.2 [95% CI, 1.4-7.9]; P=0.03). Echocardiography revealed reduced left ventricular ejection fraction (52±13% versus 57±9%; P=0.001) associated with FLNC_LOF. Overall, at least 9% of FLNC_LOF patients demonstrated evidence of penetrant disease.

CONCLUSIONS

FLNC_LOF variants are associated with increased odds of ventricular arrhythmia and dysfunction in an unselected clinical population. These findings support genomic screening of FLNC for actionable secondary findings.

Electronic Health Records and Heart Failure

Increasing the global adoption of electronic health records (EHRs) is transforming the delivery of clinical care. EHRs offer tools that are useful in the care of heart failure ranging from individualized risk stratification and decision support to population management. EHR tools can be combined to target specific areas of need such as the standardization of care, improved quality of care, and resource management. Leveraging EHR functionality has been shown to improve select outcomes including guideline-based therapies, reduction in adverse clinical outcomes, and improved cost-efficiency. Central to success is participation by clinicians and patients in the design and feedback of EHR tools.

A Novel Composite Indicator of Predicting Mortality Risk for Heart Failure Patients With Diabetes Admitted to Intensive Care Unit Based on Machine Learning

BACKGROUND

Patients 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.

METHOD

Two 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.

RESULTS

The 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.

CONCLUSION

A 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.

What can machines learn about heart failure? A systematic literature review

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

Effect of early nutritional initiation on post-cerebral infarction discharge destination: A propensity-matched analysis using machine learning

AIM

Malnutrition is associated with poor outcomes in cerebral infarction patients, with research indicating that early nutritional initiation may improve the short-term prognosis of patients. However, evidence supported by big data is lacking. Here, to determine the effect of nutritional initiation during the first 3 days after hospital admission on home discharge rates, propensity score matching was conducted in patients with acute cerebral infarction.

METHODS

This retrospective observational study, using the Diagnosis Procedure Combination anonymised database in Japan, included 41 477 ischaemic cerebral infarction patients hospitalised between 2016 and 2019. The patients were divided into two groups: those who received oral or enteral nutrition during the first 3 days of hospital admission (early nutrition group, n = 37 318) and those who did not (control group, n = 4159). One-to-one pair-matching was performed using propensity scores calculated via extreme gradient boosting to limit the confounding variables of the two groups.

RESULTS

After propensity score matching, 3541 pairs of patients were selected. The dependence of home discharge rates on early nutrition was significant (p < 0.05), and the effectiveness of early nutrition for home discharge showed an odds ratio of 1.79 (95% confidence interval of 1.59-2.03 in Fisher's exact test).

CONCLUSIONS

Our findings revealed that early nutritional initiation during the first 3 days of admission resulted in higher home discharge rates.

Prediction Model Using Machine Learning for Mortality in Patients with Heart Failure

Heart Failure (HF) is a major cause of morbidity and mortality in the US. With aging of the US population, the public health burden of HF is enormous. We aimed to develop an ensemble prediction model for 30-day mortality after discharge using machine learning. Using an electronic medical records (EMR) database, all patients with a non-elective HF admission over 10 years (January 2001 - December 2010) within the Montefiore Medical Center (MMC) health system, in the Bronx, New York, were included. We developed an ensemble model for 30-day mortality after discharge and employed discrimination, range of prediction, Brier index and explained variance as metrics in assessing model performance. A total of 7,516 patients were included. The discrimination achieved by the ensemble model was higher 0.83 (95% CI: 0.80 to 0.87) compared to the benchmark model 0.79 (95% CI: 0.75 to 0.84). The ensemble model also exhibited a better range of prediction as well as a favorable profile with respect to the other metrics employed. In conclusion, an ensemble machine learning approach exhibited an improvement in performance compared to the benchmark logistic model in predicting all-cause mortality among HF patients within 30-days of discharge. Machine learning is a promising alternative approach for risk profiling of HF patients, and it enhances individualized patient management.

State-of-the-art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

PURPOSE

We sought to develop and validate machine learning (ML) models to increase the predictive accuracy of mortality after heart transplantation (HT).

METHODS AND RESULTS

We included adult HT recipients from the United Network for Organ Sharing (UNOS) database between 2010 and 2018 using solely pre-transplant variables. The study cohort comprised 18 625 patients (53 ± 13 years, 73% males) and was randomly split into a derivation and a validation cohort with a 3:1 ratio. At 1-year after HT, there were 2334 (12.5%) deaths. Out of a total of 134 pre-transplant variables, 39 were selected as highly predictive of 1-year mortality via feature selection algorithm and were used to train five ML models. AUC for the prediction of 1-year survival was .689, .642, .649, .637, .526 for the Adaboost, Logistic Regression, Decision Tree, Support Vector Machine, and K-nearest neighbor models, respectively, whereas the Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score had an AUC of .569. Local interpretable model-agnostic explanations (LIME) analysis was used in the best performing model to identify the relative impact of key predictors. ML models for 3- and 5-year survival as well as acute rejection were also developed in a secondary analysis and yielded AUCs of .629, .609, and .610 using 27, 31, and 91 selected variables respectively.

CONCLUSION

Machine learning models showed good predictive accuracy of outcomes after heart transplantation.

Machine ​learning algorithms for claims data-based prediction of in-hospital mortality in patients with heart failure

Aims

Models predicting mortality in heart failure (HF) patients are often limited with regard to performance and applicability. The aim of this study was to develop a reliable algorithm to compute expected in‐hospital mortality rates in HF cohorts on a population level based on administrative data comparing regression analysis with different machine learning (ML) models.

Methods and results

Inpatient cases with primary International Statistical Classification of Diseases and Related Health Problems (ICD‐10) encoded discharge diagnosis of HF non‐electively admitted to 86 German Helios hospitals between 1 January 2016 and 31 December 2018 were identified. The dataset was randomly split 75%/25% for model development and testing. Highly unbalanced variables were removed. Four ML algorithms were applied, and all algorithms were tuned using a grid search with multiple repetitions. Model performance was evaluated by computing receiver operating characteristic areas under the curve. In total, 59 125 cases (69.8% aged 75 years or older, 51.9% female) were investigated, and in‐hospital mortality was 6.20%. Areas under the curve of all ML algorithms outperformed regression analysis in the testing dataset with values of 0.829 [95% confidence interval (CI) 0.814–0.843] for logistic regression, 0.875 (95% CI 0.863–0.886) for random forest, 0.882 (95% CI 0.871–0.893) for gradient boosting machine, 0.866 (95% CI 0.854–0.878) for single‐layer neural networks, and 0.882 (95% CI 0.872–0.893) for extreme gradient boosting. Brier scores demonstrated a good calibration especially of the latter three models.

Conclusions

We introduced reliable models to calculate expected in‐hospital mortality based only on administrative routine data using ML algorithms. A broad application could supplement quality measurement programs and therefore improve future HF patient care.

Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality

Machine learning promises to assist physicians with predictions of mortality and of other future clinical events by learning complex patterns from historical data, such as longitudinal electronic health records. Here we show that a convolutional neural network trained on raw pixel data in 812,278 echocardiographic videos from 34,362 individuals provides superior predictions of one-year all-cause mortality. The model's predictions outperformed the widely used pooled cohort equations, the Seattle Heart Failure score (measured in an independent dataset of 2,404 patients with heart failure who underwent 3,384 echocardiograms), and a machine learning model involving 58 human-derived variables from echocardiograms and 100 clinical variables derived from electronic health records. We also show that cardiologists assisted by the model substantially improved the sensitivity of their predictions of one-year all-cause mortality by 13% while maintaining prediction specificity. Large unstructured datasets may enable deep learning to improve a wide range of clinical prediction models.

Multiomics, virtual reality and artificial intelligence in heart failure

Aim: Multiomics delivers more biological insight than targeted investigations. We applied multiomics to patients with heart failure (HF) and reduced ejection fraction (HFrEF), with machine learning applied to advanced ECG (AECG) and echocardiography artificial intelligence (Echo AI). Patients & methods: In total, 46 patients with HFrEF and 20 controls underwent metabolomic profiling, including liquid/gas chromatography-mass spectrometry and solid-phase microextraction volatilomics in plasma and urine. HFrEF was defined using left ventricular (LV) global longitudinal strain, EF and N-terminal pro hormone BNP. AECG and Echo AI were performed over 5 min, with a subset of patients undergoing a virtual reality mental stress test. Results: A-ECG had similar diagnostic accuracy as N-terminal pro hormone BNP for HFrEF (area under the curve = 0.95, 95% CI: 0.85-0.99), and correlated with global longitudinal strain (r = -0.77, p < 0.0001), while Echo AI-generated measurements correlated well with manually measured LV end diastolic volume r = 0.77, LV end systolic volume r = 0.8, LVEF r = 0.71, indexed left atrium volume r = 0.71 and indexed LV mass r = 0.6, p < 0.005. AI-LVEF and other HFrEF biomarkers had a similar discrimination for HFrEF (area under the curve AI-LVEF = 0.88; 95% CI: -0.03 to 0.15; p = 0.19). Virtual reality mental stress test elicited arrhythmic biomarkers on AECG and indicated blunted autonomic responsiveness (alpha 2 of RR interval variability, p = 1 × 10^-4) in HFrEF. Conclusion: Multiomics-related machine learning shows promise for the assessment of HF.

Machine Learning Applications in Heart Failure Disease Management: Hype or Hope?

Purpose of the review

Machine learning (ML) approaches have emerged as powerful tools in medicine. This review focuses on the use ML to assess risk of events in patients with heart failure (HF). It provides an overview of the ML process, challenges in developing risk scores, and strategies to mitigate problems.

Recent findings

Risk scores developed using standard statistical methods have limited accuracy, particularly when they are applied to populations other than the one in which they were developed. Computerized ML algorithms which identify correlations between descriptive variables in complex, non-linear, multi-dimensional systems provide an alternative approach to predicting risk of events. The MARKER-HF mortality risk score was developed using data from the electronic health record of HF patients followed at a large academic medical center. The risk score, which uses eight commonly available variables, proved to be highly accurate in predicting mortality across the spectrum of risk. It retained accuracy in independent populations and was superior to other risk scores.

Summary

Machine learning approaches can be used to develop risk scores that are superior to ones based on standard statistical methods. Careful attention to detail in curating data, selecting covariates, and trouble-shooting the process is required to optimize results.

Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data

Background

Acute heart failure (AHF) is associated with significant morbidity and mortality. Effective patient risk stratification is essential to guiding hospitalization decisions and the clinical management of AHF. Clinical decision support systems can be used to improve predictions of mortality made in emergency care settings for the purpose of AHF risk stratification. In this study, several models for the prediction of seven-day mortality among AHF patients were developed by applying machine learning techniques to retrospective patient data from 236,275 total emergency department (ED) encounters, 1881 of which were considered positive for AHF and were used for model training and testing. The models used varying subsets of age, sex, vital signs, and laboratory values. Model performance was compared to the Emergency Heart Failure Mortality Risk Grade (EHMRG) model, a commonly used system for prediction of seven-day mortality in the ED with similar (or, in some cases, more extensive) inputs. Model performance was assessed in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity.

Results

When trained and tested on a large academic dataset, the best-performing model and EHMRG demonstrated test set AUROCs of 0.84 and 0.78, respectively, for prediction of seven-day mortality. Given only measurements of respiratory rate, temperature, mean arterial pressure, and FiO₂, one model produced a test set AUROC of 0.83. Neither a logistic regression comparator nor a simple decision tree outperformed EHMRG.

Conclusions

A model using only the measurements of four clinical variables outperforms EHMRG in the prediction of seven-day mortality in AHF. With these inputs, the model could not be replaced by logistic regression or reduced to a simple decision tree without significant performance loss. In ED settings, this minimal-input risk stratification tool may assist clinicians in making critical decisions about patient disposition by providing early and accurate insights into individual patient’s risk profiles.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13040-021-00255-w.

Machine learning, artificial intelligence and mechanical circulatory support: A primer for clinicians

Artificial intelligence (AI) refers to the ability of machines to perform intelligent tasks, and machine learning (ML) is a subset of AI describing the ability of machines to learn independently and make accurate predictions. The application of AI combined with "big data" from the electronic health records, is poised to impact how we take care of patients. In recent years, an expanding body of literature has been published using ML in cardiovascular health care, including mechanical circulatory support (MCS). This primer article provides an overview for clinicians on relevant concepts of ML and AI, reviews predictive modeling concepts in ML and provides contextual reference to how AI is being adapted in the field of MCS. Lastly, it explains how these methods could be incorporated in the practices of medicine to improve patient outcomes.