Predicting the development of adverse cardiac events in patients with hypertrophic cardiomyopathy using machine learning

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events

BACKGROUND

The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters.

OBJECTIVES

This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM.

METHODS

A total of 758 patients with HCM (67% male; aged 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke.

RESULTS

MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS).

CONCLUSIONS

ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

Prediction of cardiac death in patients with hypertrophic cardiomyopathy using plasma adipokine levels

BACKGROUNDS AND AIMS

Hypertrophic cardiomyopathy (HCM) causes cardiac death through both sudden cardiac death (SCD) and death due to heart failure (HF). Although adipokines lead to adverse cardiac remodeling in HCM, the prognostic value of plasma adipokines in HCM remains unknown. We aimed to predict cardiac death in patients with HCM using plasma adipokines.

METHODS AND RESULTS

We performed a multicenter prospective cohort study of patients with HCM. The outcome was cardiac death including heart transplant, death due to HF, and SCD. With data from 1 institution (training set), a prediction model was developed using random forest classification algorithm based on 10 plasma adipokines. The performance of the prediction model adjusted for 8 clinical parameters was examined in samples from another institution (test set). Time-to-event analysis was performed in the test set to compare the rate of outcome events between the low-risk and high-risk groups determined by the prediction model. In total, 389 (267 in the training set; 122 in the test set) patients with HCM were included. During the median follow-up of 2.7 years, 21 patients experienced the outcome event. The area under the covariates-adjusted receiver-operating characteristics curve was 0.89 (95 % confidence interval [CI] 0.71-0.99) in the test set. revealed the high-risk group had a significantly higher risk of cardiac death (hazard ratio 17.8, 95 % CI 2.1-148.3, P = 0.008).

CONCLUSION

The present multicenter prospective study demonstrated that a panel of plasma adipokines predicts cardiac death in patients with HCM.

Machine Learning-Based Discrimination of Cardiovascular Outcomes in Patients With Hypertrophic Cardiomyopathy

Background

Current risk stratification strategies for patients with hypertrophic cardiomyopathy (HCM) are limited to traditional methodologies.

Objectives

The authors aimed to establish machine learning (ML)-based models to discriminate major cardiovascular events in patients with HCM.

Methods

We enrolled consecutive HCM patients from 2 tertiary referral centers and used 25 clinical and echocardiographic features to discriminate major adverse cardiovascular events (MACE), including all-cause death, admission for heart failure (HF-adm), and stroke. The best model was selected for each outcome using the area under the receiver operating characteristic curve (AUROC) with 20-fold cross-validation. After testing in the external validation cohort, the relative importance of features in discriminating each outcome was determined using the SHapley Additive exPlanations (SHAP) method.

Results

In total, 2,111 patients with HCM (age 61.4 ± 13.6 years; 67.6% men) were analyzed. During the median 4.0 years of follow-up, MACE occurred in 341 patients (16.2%). Among the 4 ML models, the logistic regression model achieved the best AUROC of 0.800 (95% CI: 0.760-0.841) for MACE, 0.789 (95% CI: 0.736-0.841) for all-cause death, 0.798 (95% CI: 0.736-0.860) for HF-adm, and 0.807 (95% CI: 0.754-0.859) for stroke. The discriminant ability of the logistic regression model remained excellent when applied to the external validation cohort for MACE (AUROC = 0.768), all-cause death (AUROC = 0.750), and HF-adm (AUROC = 0.806). The SHAP analysis identified left atrial diameter and hypertension as important variables for all outcomes of interest.

Conclusions

The proposed ML models incorporating various phenotypes from patients with HCM accurately discriminated adverse cardiovascular events and provided variables with high importance for each outcome.

Using machine learning to predict the bleeding risk for patients with cardiac valve replacement treated with warfarin in hospitalized

BACKGROUND

Distinguishing warfarin-related bleeding risk at the bedside remains challenging. Studies indicate that warfarin therapy should be suspended when international normalized ratio (INR) ≥ 4.5, or it may sharply increase the risk of bleeding. We aim to develop and validate a model to predict the high bleeding risk in valve replacement patients during hospitalization.

METHOD

Cardiac valve replacement patients from January 2016 to December 2021 across Nanjing First Hospital were collected. Five different machine-learning (ML) models were used to establish the prediction model. High bleeding risk was an INR ≥4.5. The area under the receiver operating characteristic curve (AUC) was used for evaluating the prediction performance of different models. The SHapley Additive exPlanations (SHAP) was used for interpreting the model. We also compared ML with ATRIA score and ORBIT score.

RESULTS

A total of 2376 patients were finally enrolled in this model, 131 (5.5%) of whom experienced the high bleeding risk after anticoagulation therapy of warfarin during hospitalization. The extreme gradient boosting (XGBoost) exhibited the best overall prediction performance (AUC: 0.882, confidence interval [CI] 0.817-0.946, Brier score, 0.158) compared to other prediction models. It also shows superior performance compared with ATRIA score and ORBIT score. The top 5 most influential features in XGBoost model were platelet, thyroid stimulation hormone, body surface area, serum creatinine and white blood cell.

CONCLUSION

A model for predicting high bleeding risk in valve replacement patients who treated with warfarin during hospitalization was successfully developed by using machine learning, which may well assist clinicians to identify patients at high risk of bleeding and allow timely adjust therapeutic strategies in evaluating individual patient.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Predictors of one-year outcome after cardiac re-transplantation: Machine learning analysis

BACKGROUND

As cardiac re-transplantation is associated with inferior outcomes compared with primary transplantation, allocating scarce resources to appropriate re-transplant candidates is important. The aim of this study is to elucidate the factors associated with 1-year mortality in cardiac re-transplantation using the random forests algorithm for survival analysis.

METHODS

We retrospectively reviewed the United Network for Organ Sharing registry and identified all adult (>17 years old) recipients who underwent cardiac re-transplantation between January 2000 and March 2020. The random forest algorithm on Cox modeling was used to calculate the variable importance (VIMP) of independent variables for contributing to one-year mortality.

RESULTS

A total of 1294 patients underwent cardiac re-transplantation. Of these, 137 patients were re-transplanted within one year of their first transplant, while 1157 patients were re-transplanted more than one year after their first transplant. One-year mortality was significantly higher for patients receiving early transplantation compared with those receiving late transplantation (Early 40.6% vs. Late 13.6%, log-rank P<0.001). Machine learning analysis showed that total bilirubin (>2 mg/dl) (VIMP, 2.99%) was an independent predictor of one-year mortality after early re-transplant. High BMI (>30.0 kg/m2) (VIMP, 1.43%) and ventilator dependence (VIMP, 1.47%) were independent predictors of one-year mortality for the late re-transplantation group.

CONCLUSION

Machine learning showed that optimal one-year survival following cardiac re-transplantation was significantly related to liver function in early re-transplantation, and to obesity and preoperative ventilator dependence in late re-transplantation. This article is protected by copyright. All rights reserved.

Sport practice in hypertrophic cardiomyopathy: running to stand still?

During the last decades, the practice of sport and hypertrophic cardiomyopathy (HCM) were considered as incompatible, since evidence was not sufficient to gauge the risk associated to repeat and/or vigorous exercise across the spectrum of HCM. Additionally, it was acknowledged thatrisk stratification tools developed for HCM were not derived from athlete cohorts. Recent epidemiological studies focused on HCM both in the general population and in athletes, however, have de-emphasized the contribution of this condition to the risk of sport-associated sudden death, supporting the possibility of allowing the practice of some sports, even at professional level, for certain low-risk HCM categories. We hereby analyze the complex interaction of vigorous and continuative exercise with HCM, revising the available evidence for sports eligibility in HCM, the challenges and limitations of shared decision-making, as well as the potential harms and benefits of a highly personalised exercise schedule in subjects diagnosed with this complex disease.

The cardiac surgeon's guide to artificial intelligence

PURPOSE OF REVIEW

Artificial intelligence is the ability for machines to perform intelligent tasks. Artificial intelligence is already penetrating many aspects of medicine including cardiac surgery. Here, we offer a platform introduction to artificial intelligence for cardiac surgeons to understand the implementations of this transformative tool.

RECENT FINDINGS

Artificial intelligence has contributed greatly to the automation of cardiac imaging, including echocardiography, cardiac computed tomography, cardiac MRI and most recently, in radiomics. There are also several artificial intelligence based clinical prediction tools that predict complex outcomes after cardiac surgery. Waveform analysis, specifically, automated electrocardiogram analysis, has seen significant strides with promise in wearables and remote monitoring. Experimentally, artificial intelligence has also entered the operating room in the form of augmented reality and automated robotic surgery.

SUMMARY

Artificial intelligence has many potential exciting applications in cardiac surgery. It can streamline physician workload and help make medicine more human again by placing the physician back at the bedside. Here, we offer cardiac surgeons an introduction to this transformative tool so that they may actively participate in creating clinically relevant implementations to improve our practice.

Machine Learning for Predicting Heart Failure Progression in Hypertrophic Cardiomyopathy

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.