Development and Validation of Machine Learning-Based Race-Specific Models to Predict 10-Year Risk of Heart Failure: A Multicohort Analysis

Best of Both Worlds: Bridging One Model for All and Group-Specific Model Approaches using Ensemble-based Subpopulation Modeling

Subpopulation models have become of increasing interest in prediction of clinical outcomes because they promise to perform better for underrepresented patient subgroups. However, the personalization benefits gained from these models tradeoff their statistical power, and can be impractical when the subpopulation's sample size is small. We hypothesize that a hierarchical model in which population information is integrated into subpopulation models would preserve the personalization benefits and offset the loss of power. In this work, we integrate ideas from ensemble modeling, personalization, and hierarchical modeling and build ensemble-based subpopulation models in which specialization relies on whole group samples. This approach significantly improves the precision of the positive class, especially for the underrepresented subgroups, with minimal cost to the recall. It consistently outperforms one model for all and one model for each subgroup approaches, especially in the presence of a high class-imbalance, for subgroups with at least 380 training samples.

Development and validation of a machine-learning model for predicting the risk of death in sepsis patients with acute kidney injury

The mortality rate of patients with sepsis-induced acute kidney injury (S-AKI) is notably elevated. The initial categorization of prognostic indicators has a beneficial impact on elucidating and enhancing disease outcomes. This study aimed to predict the mortality risk of S-AKI patients by employing machine learning techniques. The sample size determined by a four-step procedure yielded 1508 samples. The research design necessitated the inclusion of individuals with S-AKI from the Medical Information Mart for Intensive Care (MIMIC)-IV database. The patients were initially admitted to the Intensive Care Unit (ICU) for their hospital stay. Additionally, these patients (aged from 18 to 89 years old) had encountered S-AKI on the day of their admittance. Forty-two predictive factors were analyzed, with hospitalization death as the outcome variable. The training set (4001 cases) consisted of 70 % of the participants, and the remaining (1714 cases) participants were allocated to the validation set. Furthermore, an additional validation set (MIMIC-III) consisted of 1757 patients from the MIMIC-III database. Moreover, an external validation set from the Intensive Care Department of Beijing Friendship Hospital (BFH) comprised 72 patients. Six machine learning models were employed in the prediction, namely the logistic, lasso, rpart, random forest, xgboost, and artificial neural network models. The comparative efficacy of the newly developed model in relation to the APACHE II model for predicting mortality risk was also assessed. The XGBoost model exhibited a superior performance with the training set. With the internal validation set and the two external validation sets (MIMIC-III and BFH), the xgboost algorithm demonstrated the highest performance. Meanwhile, APACHE II performed poorly at predicting the mortality risk with the BFH validation set. The mortality risk was influenced by three primary clinical parameters: urine volume, lactate, and Glasgow Coma Scale (GCS) score. Thus, we developed a prediction model for the risk of death among S-AKI patients that has an improved performance compared to previous models and is a potentially valuable tool for S-AKI prediction and treatment in the clinic.

A polygenic risk score of atrial fibrillation improves prediction of lifetime risk for heart failure

AIMS

Heart failure (HF) has shared genetic architecture with its risk factors: atrial fibrillation (AF), body mass index (BMI), coronary heart disease (CHD), systolic blood pressure (SBP), and type 2 diabetes (T2D). We aim to assess the association and risk prediction performance of risk-factor polygenic risk scores (PRSs) for incident HF and its subtypes in bi-racial populations.

METHODS AND RESULTS

Five PRSs were constructed for AF, BMI, CHD, SBP, and T2D in White participants of the Atherosclerosis Risk in Communities (ARIC) study. The associations between PRSs and incident HF and its subtypes were assessed using Cox models, and the risk prediction performance of PRSs was assessed using C statistics. Replication was performed in the ARIC study Black and Cardiovascular Health Study (CHS) White participants. In 8624 ARIC study Whites, 1922 (31% cumulative incidence) HF cases developed over 30 years of follow-up. PRSs of AF, BMI, and CHD were associated with incident HF (P < 0.001), where PRSAF showed the strongest association [hazard ratio (HR): 1.47, 95% confidence interval (CI): 1.41-1.53]. Only the addition of PRSAF to the ARIC study HF risk equation improved C statistics for 10 year risk prediction from 0.812 to 0.829 (∆C: 0.017, 95% CI: 0.009-0.026). The PRSAF was associated with both incident HF with reduced ejection fraction (HR: 1.43, 95% CI: 1.27-1.60) and incident HF with preserved ejection fraction (HR: 1.46, 95% CI: 1.33-1.62). The associations between PRSAF and incident HF and its subtypes, as well as the improved risk prediction, were replicated in the ARIC study Blacks and the CHS Whites (P < 0.050). Protein analyses revealed that N-terminal pro-brain natriuretic peptide and other 98 proteins were associated with PRSAF.

CONCLUSIONS

The PRSAF was associated with incident HF and its subtypes and had significant incremental value over an established HF risk prediction equation.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

Use of Clinical and Echocardiographic Evaluation to Assess the Risk of Heart Failure

BACKGROUND

Clinical and echocardiographic features predict incident heart failure (HF), but the optimal strategy for combining them is unclear.

OBJECTIVES

This study sought to define an effective means of using echocardiography in HF risk evaluation.

METHODS

The same clinical and echocardiographic evaluation was obtained in 2 groups with HF risk factors: a training group (n = 926, followed to 7 years) and a validation group (n = 355, followed to 10 years). Clinical risk was categorized as low, intermediate, and high using 4-year ARIC (Atherosclerosis Risk In Communities) HF risk score cutpoints of 9% and 33%. A risk stratification algorithm based on clinical risk and echocardiographic markers of stage B HF (SBHF) (abnormal global longitudinal strain [GLS], diastolic dysfunction, or left ventricular hypertrophy) was developed using a classification and regression tree analysis and was validated.

RESULTS

HF developed in 12% of the training group, including 9%, 18%, and 73% of low-, intermediate-, and high-risk patients. HF occurred in 8.6% of stage A HF and 19.4% of SBHF (P < 0.001), but stage A HF with clinical risk of ≥9% had similar outcome to SBHF. Abnormal GLS (HR: 2.92 [95% CI: 1.95-4.37]; P < 0.001) was the strongest independent predictor of HF. Normal GLS and diastolic function reclassified 61% of the intermediate-risk group into the low-risk group (HF incidence: 12%). In the validation group, 11% developed HF over 4.5 years; 4%, 17%, and 39% of low-, intermediate-, and high-risk groups. Similar results were obtained after exclusion of patients with known coronary artery disease. The echocardiographic parameters also provided significant incremental value to the ARIC score in predicting new HF admission (C-statistic: 0.78 [95% CI: 0.71-0.84] vs 0.83 [95% CI: 0.77-0.88]; P = 0.027).

CONCLUSIONS

Clinical risk assessment is adequate to classify low and high HF risk. Echocardiographic evaluation reclassifies 61% of intermediate-risk patients.

Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart Failure

BACKGROUND

Deep learning models may combat widening racial disparities in heart failure outcomes through early identification of individuals at high risk. However, demographic biases in the performance of these models have not been well-studied.

METHODS

This retrospective analysis used 12-lead ECGs taken between 2008 and 2018 from 326 518 patient encounters referred for standard clinical indications to Stanford Hospital. The primary model was a convolutional neural network model trained to predict incident heart failure within 5 years. Biases were evaluated on the testing set (160 312 ECGs) using the area under the receiver operating characteristic curve, stratified across the protected attributes of race, ethnicity, age, and sex.

RESULTS

There were 59 817 cases of incident heart failure observed within 5 years of ECG collection. The performance of the primary model declined with age. There were no significant differences observed between racial groups overall. However, the primary model performed significantly worse in Black patients aged 0 to 40 years compared with all other racial groups in this age group, with differences most pronounced among young Black women. Disparities in model performance did not improve with the integration of race, ethnicity, sex, and age into model architecture, by training separate models for each racial group, or by providing the model with a data set of equal racial representation. Using probability thresholds individualized for race, age, and sex offered substantial improvements in F1 scores.

CONCLUSIONS

The biases found in this study warrant caution against perpetuating disparities through the development of machine learning tools for the prognosis and management of heart failure. Customizing the application of these models by using probability thresholds individualized by race, ethnicity, age, and sex may offer an avenue to mitigate existing algorithmic disparities.

Prioritizing the primary prevention of heart failure: Measuring, modifying and monitoring risk

With the rising incidence of heart failure (HF) and increasing burden of morbidity, mortality, and healthcare expenditures, primary prevention of HF targeting individuals in at-risk HF (Stage A) and pre-HF (Stage B) Stages has become increasingly important with the goal to decrease progression to symptomatic (Stage C) HF. Identification of risk based on traditional risk factors (e.g., cardiovascular health which can be assessed with the American Heart Association's Life's Essential 8 framework), adverse social determinants of health, inherited risk of cardiomyopathies, and identification of risk-enhancing factors, such as patients with viral disease, exposure to cardiotoxic chemotherapy, and history of adverse pregnancy outcomes should be the first step in evaluation for HF risk. Next, use of guideline-endorsed risk prediction tools such as Pooled Cohort Equations to Prevent Heart Failure provide quantification of absolute risk of HF based in traditional risk factors. Risk reduction through counseling on traditional risk factors is a core focus of implementation of prevention and may include the use of novel therapeutics that target specific pathways to reduce risk of HF, such as mineralocorticoid receptor agonists (e.g., fineronone), angiotensin-receptor/neprolysin inhibitors, and sodium glucose co-transporter-2 inhibitors. These interventions may be limited in at-risk populations who experience adverse social determinants and/or individuals who reside in rural areas. Thus, strategies like telemedicine may improve access to preventive care. Gaps in the current knowledge base for risk-based prevention of HF are highlighted to outline future research that may target approaches for risk assessment and risk-based prevention with the use of artificial intelligence, genomics-enhanced strategies, and pragmatic trials to develop a guideline-directed medical therapy approach to reduce risk among individuals with Stage A and Stage B HF.

Biomarkers for Heart Failure Prediction and Prevention

Heart failure (HF) is a global pandemic affecting over 64 million people worldwide. Its prevalence is on an upward trajectory, with associated increasing healthcare expenditure. Organizations including the American College of Cardiology (ACC) and the American Heart Association (AHA) have identified HF prevention as an important focus. Recently, the ACC/AHA/Heart Failure Society of America (HFSA) Guidelines on heart failure were updated with a new Class IIa, Level of Evidence B recommendation for biomarker-based screening in patients at risk of developing heart failure. In this review, we evaluate the studies that have assessed the various roles and contributions of biomarkers in the prediction and prevention of heart failure. We examined studies that have utilized biomarkers to detect cardiac dysfunction or abnormality for HF risk prediction and screening before patients develop clinical signs and symptoms of HF. We also included studies with biomarkers on prognostication and risk prediction over and above existing HF risk prediction models and studies that address the utility of changes in biomarkers over time for HF risk. We discuss studies of biomarkers to guide management and assess the efficacy of prevention strategies and multi-biomarker and multimodality approaches to improve risk prediction.

Call for algorithmic fairness to mitigate amplification of racial biases in artificial intelligence models used in orthodontics and craniofacial health

Machine Learning (ML), a subfield of Artificial Intelligence (AI), is being increasingly used in Orthodontics and craniofacial health for predicting clinical outcomes. Current ML/AI models are prone to accentuate racial disparities. The objective of this narrative review is to provide an overview of how AI/ML models perpetuate racial biases and how we can mitigate this situation. A narrative review of articles published in the medical literature on racial biases and the use of AI/ML models was undertaken. Current AI/ML models are built on homogenous clinical datasets that have a gross underrepresentation of historically disadvantages demographic groups, especially the ethno-racial minorities. The consequence of such AI/ML models is that they perform poorly when deployed on ethno-racial minorities thus further amplifying racial biases. Healthcare providers, policymakers, AI developers and all stakeholders should pay close attention to various steps in the pipeline of building AI/ML models and every effort must be made to establish algorithmic fairness to redress inequities.

Deep learning-based prognostic model using non-enhanced cardiac cine MRI for outcome prediction in patients with heart failure

OBJECTIVES

To evaluate the performance of a deep learning-based multi-source model for survival prediction and risk stratification in patients with heart failure.

METHODS

Patients with heart failure with reduced ejection fraction (HFrEF) who underwent cardiac magnetic resonance between January 2015 and April 2020 were retrospectively included in this study. Baseline electronic health record data, including clinical demographic information, laboratory data, and electrocardiographic information, were collected. Short-axis non-contrast cine images of the whole heart were acquired to estimate the cardiac function parameters and the motion features of the left ventricle. Model accuracy was evaluated using the Harrell's concordance index. All patients were followed up for major adverse cardiac events (MACEs), and survival prediction was assessed using Kaplan-Meier curves.

RESULTS

A total of 329 patients were evaluated (age 54 ± 14 years; men, 254) in this study. During a median follow-up period of 1041 days, 62 patients experienced MACEs and their median survival time was 495 days. When compared with conventional Cox hazard prediction models, deep learning models showed better survival prediction performance. Multi-data denoising autoencoder (DAE) model reached the concordance index of 0.8546 (95% CI: 0.7902-0.8883). Furthermore, when divided into phenogroups, the multi-data DAE model could significantly discriminate between the survival outcomes of the high-risk and low-risk groups compared with other models (p < 0.001).

CONCLUSIONS

The proposed deep learning (DL) model based on non-contrast cardiac cine magnetic resonance imaging could independently predict the outcome of patients with HFrEF and showed better prediction efficiency than conventional methods.

CLINICAL RELEVANCE STATEMENT

The proposed multi-source deep learning model based on cardiac magnetic resonance enables survival prediction in patients with heart failure.

KEY POINTS

• A multi-source deep learning model based on non-contrast cardiovascular magnetic resonance (CMR) cine images was built to make robust survival prediction in patients with heart failure. • The ground truth definition contains electronic health record data as well as DL-based motion data, and cardiac motion information is extracted by optical flow method from non-contrast CMR cine images. • The DL-based model exhibits better prognostic value and stratification performance when compared with conventional prediction models and could aid in the risk stratification in patients with HF.

Machine learning-based intradialytic hypotension prediction of patients undergoing hemodialysis: A multicenter retrospective study

BACKGROUND AND OBJECTIVE

Intradialytic hypotension (IDH) is closely associated with adverse clinical outcomes in HD-patients. An IDH predictor model is important for IDH risk screening and clinical decision-making. In this study, we used Machine learning (ML) to develop IDH model for risk prediction in HD patients.

METHODS

62,227 dialysis sessions were randomly partitioned into training data (70%), test data (20%), and validation data (10%). IDH-A model based on twenty-seven variables was constructed for risk prediction for the next HD treatment. IDH-B model based on ten variables from 64,870 dialysis sessions was developed for risk assessment before each HD treatment. Light Gradient Boosting Machine (LightGBM), Linear Discriminant Analysis, support vector machines, XGBoost, TabNet, and multilayer perceptron were used to develop the predictor model.

RESULTS

In IDH-A model, we identified the LightGBM method as the best-performing and interpretable model with C- statistics of 0.82 in Fall30Nadir90 definitions, which was higher than those obtained using the other models (P<0.01). In other IDH standards of Nadir90, Nadir100, Fall20, Fall30, and Fall20Nadir90, the LightGBM method had a performance with C- statistics ranged 0.77 to 0.89. As a complementary application, the LightGBM model in IDH-B model achieved C- statistics of 0.68 in Fall30Nadir90 definitions and 0.69 to 0.78 in the other five IDH standards, which were also higher than the other methods, respectively.

CONCLUSION

Use ML, we identified the LightGBM method as the good-performing and interpretable model. We identified the top variables as the high-risk factors for IDH incident in HD-patient. IDH-A and IDH-B model can usefully complement each other for risk prediction and further facilitate timely intervention through applied into different clinical setting.

Applications of machine learning in familial hypercholesterolemia

Familial hypercholesterolemia (FH) is a common hereditary cholesterol metabolic disease that usually leads to an increase in the level of low-density lipoprotein cholesterol in plasma and an increase in the risk of cardiovascular disease. The lack of disease screening and diagnosis often results in FH patients being unable to receive early intervention and treatment, which may mean early occurrence of cardiovascular disease. Thus, more requirements for FH identification and management have been proposed. Recently, machine learning (ML) has made great progress in the field of medicine, including many innovative applications in cardiovascular medicine. In this review, we discussed how ML can be used for FH screening, diagnosis and risk assessment based on different data sources, such as electronic health records, plasma lipid profiles and corneal radian images. In the future, research aimed at developing ML models with better performance and accuracy will continue to overcome the limitations of ML, provide better prediction, diagnosis and management tools for FH, and ultimately achieve the goal of early diagnosis and treatment of FH.

Dendrogram of transparent feature importance machine learning statistics to classify associations for heart failure: A reanalysis of a retrospective cohort study of the Medical Information Mart for Intensive Care III (MIMIC-III) database

BACKGROUND

There is a continual push for developing accurate predictors for Intensive Care Unit (ICU) admitted heart failure (HF) patients and in-hospital mortality.

OBJECTIVE

The study aimed to utilize transparent machine learning and create hierarchical clustering of key predictors based off of model importance statistics gain, cover, and frequency.

METHODS

Inclusion criteria of complete patient information for in-hospital mortality in the ICU with HF from the MIMIC-III database were randomly divided into a training (n = 941, 80%) and test (n = 235, 20%). A grid search was set to find hyperparameters. Machine Learning with XGBoost were used to predict mortality followed by feature importance with Shapely Additive Explanations (SHAP) and hierarchical clustering of model metrics with a dendrogram and heat map.

RESULTS

Of the 1,176 heart failure ICU patients that met inclusion criteria for the study, 558 (47.5%) were males. The mean age was 74.05 (SD = 12.85). XGBoost model had an area under the receiver operator curve of 0.662. The highest overall SHAP explanations were urine output, leukocytes, bicarbonate, and platelets. Average urine output was 1899.28 (SD = 1272.36) mL/day with the hospital mortality group having 1345.97 (SD = 1136.58) mL/day and the group without hospital mortality having 1986.91 (SD = 1271.16) mL/day. The average leukocyte count in the cohort was 10.72 (SD = 5.23) cells per microliter. For the hospital mortality group the leukocyte count was 13.47 (SD = 7.42) cells per microliter and for the group without hospital mortality the leukocyte count was 10.28 (SD = 4.66) cells per microliter. The average bicarbonate value was 26.91 (SD = 5.17) mEq/L. Amongst the group with hospital mortality the average bicarbonate value was 24.00 (SD = 5.42) mEq/L. Amongst the group without hospital mortality the average bicarbonate value was 27.37 (SD = 4.98) mEq/L. The average platelet value was 241.52 platelets per microliter. For the group with hospital mortality the average platelet value was 216.21 platelets per microliter. For the group without hospital mortality the average platelet value was 245.47 platelets per microliter. Cluster 1 of the dendrogram grouped the temperature, platelets, urine output, Saturation of partial pressure of Oxygen (SPO2), Leukocyte count, lymphocyte count, bicarbonate, anion gap, respiratory rate, PCO2, BMI, and age as most similar in having the highest aggregate gain, cover, and frequency metrics.

CONCLUSION

Machine Learning models that incorporate dendrograms and heat maps can offer additional summaries of model statistics in differentiating factors between in patient ICU mortality in heart failure patients.

Tree-based survival analysis improves mortality prediction in cardiac surgery

Objectives

Machine learning (ML) classification tools are known to accurately predict many cardiac surgical outcomes. A novel approach, ML-based survival analysis, remains unstudied for predicting mortality after cardiac surgery. We aimed to benchmark performance, as measured by the concordance index (C-index), of tree-based survival models against Cox proportional hazards (CPH) modeling and explore risk factors using the best-performing model.

Methods

144,536 patients with 147,301 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) national database were used to train and validate models. Univariate analysis was performed using Student's T-test for continuous variables, Chi-squared test for categorical variables, and stratified Kaplan-Meier estimation of the survival function. Three ML models were tested, a decision tree (DT), random forest (RF), and gradient boosting machine (GBM). Hyperparameter tuning was performed using a Bayesian search strategy. Performance was assessed using 2-fold cross-validation repeated 5 times.

Results

The highest performing model was the GBM with a C-index of 0.803 (0.002), followed by RF with 0.791 (0.003), DT with 0.729 (0.014), and finally CPH with 0.596 (0.042). The 5 most predictive features were age, type of procedure, length of hospital stay, drain output in the first 4 h (ml), and inotrope use greater than 4 h postoperatively.

Conclusion

Tree-based learning for survival analysis is a non-parametric and performant alternative to CPH modeling. GBMs offer interpretable modeling of non-linear relationships, promising to expose the most relevant risk factors and uncover new questions to guide future research.

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.

Development and validation of a newly developed nomogram for predicting the risk of deep vein thrombosis after surgery for lower limb fractures in elderly patients

Background

Prevention of deep vein thrombosis (DVT) is indispensable in the treatment of lower limb fractures during the perioperative period. This study aimed to develop and validate a novel model for predicting the risk of DVT in elderly patients after orthopedic surgeries for lower limb fractures.

Methods

This observational study included 576 elderly patients with lower limb fractures who were surgically treated from January 2016 to December 2018. Eleven items affecting DVT were optimized by least absolute shrinkage and selection operator regression analysis. Multivariable logistic regression analysis was performed to construct a predictive model incorporating the selected features. C-index was applied to evaluate the discrimination. Decision curve analysis was employed to determine the clinical effectiveness of this model and calibration plot was applied to evaluate the calibration of this nomogram. The internal validation of this model was assessed by bootstrapping validation.

Results

Predictive factors that affected the rate of DVT in this model included smoking, time from injury to surgery, operation time, blood transfusion, hip replacement arthroplasty, and D-dimer level after operation. The nomogram showed significant discrimination with a C-index of 0.919 (95% confidence interval: 0.893-0.946) and good calibration. Acceptable C-index value could still be reached in the interval validation. Decision curve analysis indicated that the DVT risk nomogram was useful within all possibility threshold.

Conclusion

This newly developed nomogram could be used to predict the risk of DVT in elderly patients with lower limb fractures during the perioperative period.

Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure

Objective

Risk stratification of patients with congestive heart failure (HF) is vital in clinical practice. The aim of this study was to construct a machine learning model to predict the in-hospital all-cause mortality for intensive care unit (ICU) patients with HF.

Methods

eXtreme Gradient Boosting algorithm (XGBoost) was used to construct a new prediction model (XGBoost model) from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (training set). The eICU Collaborative Research Database dataset (eICU-CRD) was used for the external validation (test set). The XGBoost model performance was compared with a logistic regression model and an existing model (Get with the guideline-Heart Failure model) for mortality in the test set. Area under the receiver operating characteristic cure and Brier score were employed to evaluate the discrimination and the calibration of the three models. The SHapley Additive exPlanations (SHAP) value was applied to explain XGBoost model and calculate the importance of its features.

Results

The total of 11,156 and 9,837 patients with congestive HF from the training set and test set, respectively, were included in the study. In-hospital all-cause mortality occurred in 13.3% (1,484/11,156) and 13.4% (1,319/9,837) of patients, respectively. In the training set, of 17 features with the highest predictive value were selected into the models with LASSO regression. Acute Physiology Score III (APS III), age and Sequential Organ Failure Assessment (SOFA) were strongest predictors in SHAP. In the external validation, the XGBoost model performance was superior to that of conventional risk predictive methods, with an area under the curve of 0.771 (95% confidence interval, 0.757–0.784) and a Brier score of 0.100. In the evaluation of clinical effectiveness, the machine learning model brought a positive net benefit in the threshold probability of 0%–90%, prompting evident competitiveness compare to the other two models. This model has been translated into an online calculator which is accessible freely to the public (https://nkuwangkai-app-for-mortality-prediction-app-a8mhkf.streamlit.app).

Conclusion

This study developed a valuable machine learning risk stratification tool to accurately assess and stratify the risk of in-hospital all-cause mortality in ICU patients with congestive HF. This model was translated into a web-based calculator which access freely.

Predicting heart failure onset in the general population using a novel data-mining artificial intelligence method

We aimed to identify combinations of clinical factors that predict heart failure (HF) onset using a novel limitless-arity multiple-testing procedure (LAMP). We also determined if increases in numbers of predictive combinations of factors increases the probability of developing HF. We recruited people without HF who received health check-ups in 2010, who were followed annually for 4 years. Using 32,547 people, LAMP was performed to identify combinations of factors of fewer than four factors that could predict the onset of HF. The ability of the method to predict the probability of HF onset based on the number of matching predictive combinations of factors was determined in 275,658 people. We identified 549 combinations of factors for the onset of HF. Then we classified 275,658 people into six groups who had 0, 1-50, 51-100, 101-150, 151-200 or 201-250 predictive combinations of factors for the onset of HF. We found that the probability of HF progressively increased as the number of predictive combinations of factors increased. We identified combinations of variables that predict HF onset. An increased number of matching predictive combinations for the onset of HF increased the probability of HF onset.

Development and validation of questionnaire-based machine learning models for predicting all-cause mortality in a representative population of China

Background

Considering that the previously developed mortality prediction models have limited applications to the Chinese population, a questionnaire-based prediction model is of great importance for its accuracy and convenience in clinical practice.

Methods

Two national cohort, namely, the China Health and Nutrition Survey (8,355 individual older than 18) and the China Health and Retirement Longitudinal Study (12,711 individuals older than 45) were used for model development and validation. One hundred and fifty-nine variables were compiled to generate predictions. The Cox regression model and six machine learning (ML) models were used to predict all-cause mortality. Finally, a simple questionnaire-based ML prediction model was developed using the best algorithm and validated.

Results

In the internal validation set, all the ML models performed better than the traditional Cox model in predicting 6-year mortality and the random survival forest (RSF) model performed best. The questionnaire-based ML model, which only included 20 variables, achieved a C-index of 0.86 (95%CI: 0.80-0.92). On external validation, the simple questionnaire-based model achieved a C-index of 0.82 (95%CI: 0.77-0.87), 0.77 (95%CI: 0.75-0.79), and 0.79 (95%CI: 0.77-0.81), respectively, in predicting 2-, 9-, and 11-year mortality.

Conclusions

In this prospective population-based study, a model based on the RSF analysis performed best among all models. Furthermore, there was no significant difference between the prediction performance of the questionnaire-based ML model, which only included 20 variables, and that of the model with all variables (including laboratory variables). The simple questionnaire-based ML prediction model, which needs to be further explored, is of great importance for its accuracy and suitability to the Chinese general population.

Race, Social Determinants of Health, and Length of Stay Among Hospitalized Patients With Heart Failure: An Analysis From the Get With The Guidelines-Heart Failure Registry

BACKGROUND

Racial disparities in heart failure hospitalization and mortality are well established; however, the association between different social determinants of health (SDOH) and length of stay (LOS) and the extent to which this association may differ across racial groups is not well established.

METHODS

We utilized data from the Get With The Guidelines-Heart Failure registry to evaluate the association between SDOH, as determined by patients' residential ZIP Code and LOS among patients hospitalized with heart failure. We also assessed the race-specific contribution of the ZIP Code-level SDOH to LOS in patients of Black and non-Black races. Finally, we evaluated SDOH predictors of racial differences in LOS at the hospital level.

RESULTS

Among 301 500 patients (20.2% Black race), the median LOS was 4 days. In adjusted analysis accounting for patient-level and hospital-level factors, SDOH parameters of education, income, housing instability, and foreign-born were significantly associated with LOS after adjusting for clinical status and hospital-level factors. SDOH parameters accounted for 25.8% of the total attributable risk for prolonged LOS among Black patients compared with 10.1% in patients of non-Black race. Finally, hospitals with disproportionately longer LOS for Black versus non-Black patients were more likely to care for disadvantaged patients living in ZIP Codes with a higher percentage of foreign-born and non-English speaking areas.

CONCLUSIONS

ZIP Code-level SDOH markers can identify patients at risk for prolonged LOS, and the effects of SDOH parameters are significantly greater among Black adults with heart failure as compared with non-Black adults.

Improving Fairness in the Prediction of Heart Failure Length of Stay and Mortality by Integrating Social Determinants of Health

BACKGROUND

Machine learning (ML) approaches have been broadly applied to the prediction of length of stay and mortality in hospitalized patients. ML may also reduce societal health burdens, assist in health resources planning and improve health outcomes. However, the fairness of these ML models across ethnoracial or socioeconomic subgroups is rarely assessed or discussed. In this study, we aim (1) to quantify the algorithmic bias of ML models when predicting the probability of long-term hospitalization or in-hospital mortality for different heart failure (HF) subpopulations, and (2) to propose a novel method that can improve the fairness of our models without compromising predictive power.

METHODS

We built 5 ML classifiers to predict the composite outcome of hospitalization length-of-stay and in-hospital mortality for 210 368 HF patients extracted from the Get With The Guidelines-Heart Failure registry data set. We integrated 15 social determinants of health variables, including the Social Deprivation Index and the Area Deprivation Index, into the feature space of ML models based on patients' geographies to mitigate the algorithmic bias.

RESULTS

The best-performing random forest model demonstrated modest predictive power but selectively underdiagnosed underserved subpopulations, for example, female, Black, and socioeconomically disadvantaged patients. The integration of social determinants of health variables can significantly improve fairness without compromising model performance.

CONCLUSIONS

We quantified algorithmic bias against underserved subpopulations in the prediction of the composite outcome for HF patients. We provide a potential direction to reduce disparities of ML-based predictive models by integrating social determinants of health variables. We urge fellow researchers to strongly consider ML fairness when developing predictive models for HF patients.

A prediction model for major adverse cardiovascular events in patients with heart failure based on high-throughput echocardiographic data

Background

Heart failure (HF) is a serious end-stage condition of various heart diseases with increasing frequency. Few studies have combined clinical features with high-throughput echocardiographic data to assess the risk of major cardiovascular events (MACE) in patients with heart failure. In this study, we assessed the relationship between these factors and heart failure to develop a practical and accurate prognostic dynamic nomogram model to identify high-risk groups of heart failure and ultimately provide tailored treatment options.

Materials and methods

We conducted a prospective study of 468 patients with heart failure and established a clinical predictive model. Modeling to predict risk of MACE in heart failure patients within 6 months after discharge obtained 320 features including general clinical data, laboratory examination, 2-dimensional and Doppler measurements, left ventricular (LV) and left atrial (LA) speckle tracking echocardiography (STE), and left ventricular vector flow mapping (VFM) data, were obtained by building a model to predict the risk of MACE within 6 months of discharge for patients with heart failure. In addition, the addition of machine learning models also confirmed the necessity of increasing the STE and VFM parameters.

Results

Through regular follow-up 6 months after discharge, MACE occurred in 156 patients (33.3%). The prediction model showed good discrimination C-statistic value, 0.876 (p < 0.05), which indicated good identical calibration and clinical efficacy. In multiple datasets, through machine learning multi-model comparison, we found that the area under curve (AUC) of the model with VFM and STE parameters was higher, which was more significant with the XGboost model.

Conclusion

In this study, we developed a prediction model and nomogram to estimate the risk of MACE within 6 months of discharge among patients with heart failure. The results of this study can provide a reference for clinical physicians for detection of the risk of MACE in terms of clinical characteristics, cardiac structure and function, hemodynamics, and enable its prompt management, which is a convenient, practical and effective clinical decision-making tool for providing accurate prognosis.

Improving predictive performance in incident heart failure using machine learning and multi-center data

Objective

To mitigate the burden associated with heart failure (HF), primary prevention is of the utmost importance. To improve early risk stratification, advanced computational methods such as machine learning (ML) capturing complex individual patterns in large data might be necessary. Therefore, we compared the predictive performance of incident HF risk models in terms of (a) flexible ML models and linear models and (b) models trained on a single cohort (single-center) and on multiple heterogeneous cohorts (multi-center).

Design and methods

In our analysis, we used the meta-data consisting of 30,354 individuals from 6 cohorts. During a median follow-up of 5.40 years, 1,068 individuals experienced a non-fatal HF event. We evaluated the predictive performance of survival gradient boosting (SGB), CoxNet, the PCP-HF risk score, and a stacking method. Predictions were obtained iteratively, in each iteration one cohort serving as an external test set and either one or all remaining cohorts as a training set (single- or multi-center, respectively).

Results

Overall, multi-center models systematically outperformed single-center models. Further, c-index in the pooled population was higher in SGB (0.735) than in CoxNet (0.694). In the precision-recall (PR) analysis for predicting 10-year HF risk, the stacking method, combining the SGB, CoxNet, Gaussian mixture and PCP-HF models, outperformed other models with PR/AUC 0.804, while PCP-HF achieved only 0.551.

Conclusion

With a greater number and variety of training cohorts, the model learns a wider range of specific individual health characteristics. Flexible ML algorithms can be used to capture these diverse distributions and produce more precise prediction models.

Machine Learning-Based Models Incorporating Social Determinants of Health vs Traditional Models for Predicting In-Hospital Mortality in Patients With Heart Failure

Importance

Traditional models for predicting in-hospital mortality for patients with heart failure (HF) have used logistic regression and do not account for social determinants of health (SDOH).

Objective

To develop and validate novel machine learning (ML) models for HF mortality that incorporate SDOH.

Design, Setting, and Participants

This retrospective study used the data from the Get With The Guidelines-Heart Failure (GWTG-HF) registry to identify HF hospitalizations between January 1, 2010, and December 31, 2020. The study included patients with acute decompensated HF who were hospitalized at the GWTG-HF participating centers during the study period. Data analysis was performed January 6, 2021, to April 26, 2022. External validation was performed in the hospitalization cohort from the Atherosclerosis Risk in Communities (ARIC) study between 2005 and 2014.

Main Outcomes and Measures

Random forest-based ML approaches were used to develop race-specific and race-agnostic models for predicting in-hospital mortality. Performance was assessed using C index (discrimination), regression slopes for observed vs predicted mortality rates (calibration), and decision curves for prognostic utility.

Results

The training data set included 123 634 hospitalized patients with HF who were enrolled in the GWTG-HF registry (mean [SD] age, 71 [13] years; 58 356 [47.2%] female individuals; 65 278 [52.8%] male individuals. Patients were analyzed in 2 categories: Black (23 453 [19.0%]) and non-Black (2121 [2.1%] Asian; 91 154 [91.0%] White, and 6906 [6.9%] other race and ethnicity). The ML models demonstrated excellent performance in the internal testing subset (n = 82 420) (C statistic, 0.81 for Black patients and 0.82 for non-Black patients) and in the real-world-like cohort with less than 50% missingness on covariates (n = 553 506; C statistic, 0.74 for Black patients and 0.75 for non-Black patients). In the external validation cohort (ARIC registry; n = 1205 Black patients and 2264 non-Black patients), ML models demonstrated high discrimination and adequate calibration (C statistic, 0.79 and 0.80, respectively). Furthermore, the performance of the ML models was superior to the traditional GWTG-HF risk score model (C index, 0.69 for both race groups) and other rederived logistic regression models using race as a covariate. The performance of the ML models was identical using the race-specific and race-agnostic approaches in the GWTG-HF and external validation cohorts. In the GWTG-HF cohort, the addition of zip code-level SDOH parameters to the ML model with clinical covariates only was associated with better discrimination, prognostic utility (assessed using decision curves), and model reclassification metrics in Black patients (net reclassification improvement, 0.22 [95% CI, 0.14-0.30]; P < .001) but not in non-Black patients.

Conclusions and Relevance

ML models for HF mortality demonstrated superior performance to the traditional and rederived logistic regressions models using race as a covariate. The addition of SDOH parameters improved the prognostic utility of prediction models in Black patients but not non-Black patients in the GWTG-HF registry.

Association Between Thigh Muscle Fat Infiltration and Incident Heart Failure: The Health ABC Study

BACKGROUND

Excess adiposity is a well-known risk factor for heart failure (HF). Fat accumulation in and around the peripheral skeletal muscle may further inform risk for HF.

OBJECTIVES

The purpose of this study was to evaluate the association between intramuscular and intermuscular fat deposition and incident HF in a longitudinal cohort of community-dwelling older adults.

METHODS

The associations of intramuscular and intermuscular fat with incident HF were assessed using Cox models among 2,399 participants from the Health ABC (Health, Aging and Body Composition) study (70-79 years of age, 48% male, 40.2% Black) without baseline HF. Intramuscular fat was determined by bilateral thigh muscle density on computed tomography and intermuscular fat area was determined with computed tomography.

RESULTS

After a median follow-up of 12.2 years, there were 485 incident HF events. Higher sex-specific tertiles of intramuscular and intermuscular fat were each associated with HF risk. After multivariable adjustment for age, sex, race, education, blood pressure, fasting blood sugar, current smoking, prevalent coronary disease, and creatinine, higher intramuscular fat, but not intermuscular fat, was associated with higher risk for HF (HR: 1.34 [95% CI: 1.06-1.69]; P = 0.012, tertile 3 vs tertile 1). This association remained significant after additional adjustment for body mass index (HR: 1.32 [95% CI: 1.03-1.69]), total percent fat (HR: 1.33 [95% CI: 1.03-1.72]), visceral fat (HR: 1.30 [95% CI: 1.01-1.65]), and indexed thigh muscle strength (HR: 1.30 [95% CI: 1.03-1.64]). The association between higher intramuscular fat and HF appeared specific to higher risk of incident HF with reduced ejection fraction (HR: 1.53 [95% CI: 1.03-2.29]), but not with HF with preserved ejection fraction (HR: 1.28 [95% CI: 0.82-1.98]).

CONCLUSIONS

Intramuscular, but not intermuscular, thigh muscle fat is independently associated with HF after adjustment for cardiometabolic risk factors and other measurements of adiposity.

Storage conditions, sample integrity, interferences, and a decision tool for investigating unusual high-sensitivity cardiac troponin results

The current definition of high-sensitivity cardiac troponin (hs-cTn) assays is laboratory-based and their analytical attributes and characteristics have drawn significant attention in the literature at least partly due to the lower concentration cut-offs and changes in concentrations (i.e., deltas) employed in different algorithms and pathways to manage patient care. We propose that pre-analytical conditions such as sample type, storage conditions, and other interferences may also have a significant impact on hs-cTn concentrations and clinical management. The purpose of this literature review is to provide a summary of important pre-analytical and interference studies affecting hs-cTn concentrations. A breakdown of the literature for the major diagnostic companies providing core laboratory instrumentation (i.e., Abbott, Beckman, Ortho, Roche, and Siemens) is also provided. Finally, three cases are highlighted where knowledge of pre-analytical factors aids the hs-cTn clinically discordant investigations. This review highlights the importance of pre-analytical variables, especially storage condition, sample handling, and blood tubes used (i.e., sample type) when interpreting hs-cTn assays. Additional studies are needed to further elaborate on pre-analytical variables (i.e., centrifugation, sample type, stability) and interferences for all hs-cTn assays in clinical use, as knowledge of these variables may aid in hs-cTn clinically discordant investigations.

New strategies and therapies for the prevention of heart failure in high-risk patients

Despite declines in total cardiovascular mortality rates in the United States, heart failure (HF) mortality rates as well as hospitalizations and readmissions have increased in the past decade. Increases have been relatively higher among young and middle-aged adults (<65 years). Therefore, identification of individuals HF at-risk (Stage A) or with pre-HF (Stage B) before the onset of overt clinical signs and symptoms (Stage C) is urgently needed. Multivariate risk models (e.g., Pooled Cohort Equations to Prevent Heart Failure [PCP-HF]) have been externally validated in diverse populations and endorsed by the 2022 HF Guidelines to apply a risk-based framework for the prevention of HF. However, traditional risk factors included in the PCP-HF model only account for half of an individual's lifetime risk of HF; novel risk factors (e.g., adverse pregnancy outcomes, impaired lung health, COVID-19) are emerging as important risk-enhancing factors that need to be accounted for in personalized approaches to prevention. In addition to determining the role of novel risk-enhancing factors, integration of social determinants of health (SDoH) in identifying and addressing HF risk is needed to transform the current clinical paradigm for the prevention of HF. Comprehensive strategies to prevent the progression of HF must incorporate pharmacotherapies (e.g., sodium glucose co-transporter-2 inhibitors that have also been termed the "statins" of HF prevention), intensive blood pressure lowering, and heart-healthy behaviors. Future directions include investigation of novel prediction models leveraging machine learning, integration of risk-enhancing factors and SDoH, and equitable approaches to interventions for risk-based prevention of HF.

Clinical Prediction Models for Heart Failure Hospitalization in Type 2 Diabetes: A Systematic Review and Meta-Analysis

Background Clinical prediction models have been developed for hospitalization for heart failure in type 2 diabetes. However, a systematic evaluation of these models' performance, applicability, and clinical impact is absent. Methods and Results We searched Embase, MEDLINE, Web of Science, Google Scholar, and Tufts' clinical prediction registry through February 2021. Studies needed to report the development, validation, clinical impact, or update of a prediction model for hospitalization for heart failure in type 2 diabetes with measures of model performance and sufficient information for clinical use. Model assessment was done with the Prediction Model Risk of Bias Assessment Tool, and meta-analyses of model discrimination were performed. We included 15 model development and 3 external validation studies with data from 999 167 people with type 2 diabetes. Of the 15 models, 6 had undergone external validation and only 1 had low concern for risk of bias and applicability (Risk Equations for Complications of Type 2 Diabetes). Seven models were presented in a clinically useful manner (eg, risk score, online calculator) and 2 models were classified as the most suitable for clinical use based on study design, external validity, and point-of-care usability. These were Risk Equations for Complications of Type 2 Diabetes (meta-analyzed c-statistic, 0.76) and the Thrombolysis in Myocardial Infarction Risk Score for Heart Failure in Diabetes (meta-analyzed c-statistic, 0.78), which was the simplest model with only 5 variables. No studies reported clinical impact. Conclusions Most prediction models for hospitalization for heart failure in patients with type 2 diabetes have potential concerns with risk of bias or applicability, and uncertain external validity and clinical impact. Future research is needed to address these knowledge gaps.

Applications of artificial intelligence and machine learning in heart failure

Machine learning (ML) is a sub-field of artificial intelligence that uses computer algorithms to extract patterns from raw data, acquire knowledge without human input, and apply this knowledge for various tasks. Traditional statistical methods that classify or regress data have limited capacity to handle large datasets that have a low signal-to-noise ratio. In contrast to traditional models, ML relies on fewer assumptions, can handle larger and more complex datasets, and does not require predictors or interactions to be pre-specified, allowing for novel relationships to be detected. In this review, we discuss the rationale for the use and applications of ML in heart failure, including disease classification, early diagnosis, early detection of decompensation, risk stratification, optimal titration of medical therapy, effective patient selection for devices, and clinical trial recruitment. We discuss how ML can be used to expedite implementation and close healthcare gaps in learning healthcare systems. We review the limitations of ML, including opaque logic and unreliable model performance in the setting of data errors or data shift. Whilst ML has great potential to improve clinical care and research in HF, the applications must be externally validated in prospective studies for broad uptake to occur.

Utilizing Artificial Intelligence to Enhance Health Equity Among Patients with Heart Failure

Patients with heart failure (HF) are heterogeneous with various intrapersonal and interpersonal characteristics contributing to clinical outcomes. Bias, structural racism, and social determinants of health have been implicated in unequal treatment of patients with HF. Through several methodologies, artificial intelligence (AI) can provide models in HF prediction, prognostication, and provision of care, which may help prevent unequal outcomes. This review highlights AI as a strategy to address racial inequalities in HF; discusses key AI definitions within a health equity context; describes the current uses of AI in HF, strengths and harms in using AI; and offers recommendations for future directions.

Ten-Year Risk-Prediction Equations for Incident Heart Failure Hospitalizations in Chronic Kidney Disease: Findings from the Chronic Renal Insufficiency Cohort Study and the Multi-Ethnic Study of Atherosclerosis

BACKGROUND

Heart failure (HF) is a leading contributor to cardiovascular morbidity and mortality in the population with chronic kidney disease (CKD). HF risk prediction tools that use readily available clinical parameters to risk-stratify individuals with CKD are needed.

METHODS

We included Black and White participants aged 30-79 years with CKD stages 2-4 who were enrolled in the Chronic Renal Insufficiency Cohort (CRIC) study and were without self-reported cardiovascular disease. We assessed model performance of the Pooled Cohort Equations to Prevent Heart Failure (PCP-HF) to predict incident hospitalizations due to HF and refit the PCP-HF in the population with CKD by using CRIC data-derived coefficients and survival from CRIC study participants in the CKD population (PCP-HFCKD). We investigated the improvement in HF prediction with inclusion of estimated glomerular filtration rate (eGFR) and urine albumin-to-creatinine ratio (UACR) into the PCP-HFCKD equations by change in C-statistic, net reclassification improvement (NRI), and integrated discrimination improvement index (IDI). We validated the PCP-HFCKD with and without eGFR and UACR in Multi-Ethnic Study of Atherosclerosis (MESA) participants with CKD.

RESULTS

Among 2328 CRIC Study participants, 340 incident HF hospitalizations occurred over a mean follow-up of 9.5 years. The PCP-HF equations did not perform well in most participants with CKD and had inadequate discrimination and insufficient calibration (C-statistic 0.64-0.71, Greenwood-Nam-D'Agostino (GND) chi-square statistic P value < 0.05), with modest improvement and good calibration after being refit (PCP-HFCKD: C-statistic 0.61-0.78), GND chi-square statistic P value > 0.05). Addition of UACR, but not eGFR, to the refit PCP-HFCKD improved model performance in all race-sex groups (C-statistic [0.73-0.81], GND chi-square statistic P value > 0.05, delta C-statistic ranging from 0.03-0.11 and NRI and IDI P values < 0.01). External validation of the PCP-HFCKD in MESA demonstrated good discrimination and calibration.

CONCLUSIONS

Routinely available clinical data that include UACR in patients with CKD can reliably identify individuals at risk of HF hospitalizations.

Using machine learning to predict heavy drinking during outpatient alcohol treatment

BACKGROUND

Accurate clinical prediction supports the effective treatment of alcohol use disorder (AUD) and other psychiatric disorders. Traditional statistical techniques have identified patient characteristics associated with treatment outcomes. However, less work has focused on systematically leveraging these associations to create optimal predictive models. The current study demonstrates how machine learning can be used to predict clinical outcomes in people completing outpatient AUD treatment.

METHOD

We used data from the COMBINE multisite clinical trial (n = 1383) to develop and test predictive models. We identified three priority prediction targets, including (1) heavy drinking during the first month of treatment, (2) heavy drinking during the last month of treatment, and (3) heavy drinking between weekly/bi-weekly sessions. Models were generated using the random forest algorithm. We used "leave sites out" partitioning to externally validate the models in trial sites that were not included in the model training. Stratified model development was used to test for sex differences in the relative importance of predictive features.

RESULTS

Models predicting heavy alcohol use during the first and last months of treatment showed internal cross-validation area under the curve (AUC) scores ranging from 0.67 to 0.74. AUC was comparable in the external validation using data from held-out sites (AUC range = 0.69 to 0.72). The model predicting between-session heavy drinking showed strong classification accuracy in internal cross-validation (AUC = 0.89) and external test samples (AUC range = 0.80 to 0.87). Stratified analyses showed substantial sex differences in optimal feature sets.

CONCLUSION

Machine learning techniques can predict alcohol treatment outcomes using routinely collected clinical data. This technique has the potential to greatly improve clinical prediction accuracy without requiring expensive or invasive assessment methods. More research is needed to understand how best to deploy these models.

Team-based strategies to prevent heart failure

PURPOSE OF REVIEW

The burden of heart failure (HF) in the United States and worldwide is projected to rise. Prevention of HF can curb the burden of this chronic syndrome, but current approaches are limited. This review discusses team-based strategies aimed to prevent HF.

RECENT FINDINGS

Individuals at high risk for developing HF can be identified using HF risk scores, biomarkers, and cardiac imaging. Electronic medical records (EMR) can integrate clinical data to estimate HF risk and identify individuals who may benefit most from preventive therapies. Team-based interventions can lead to enhanced adherence to medications, optimization of medical management, and control of risk factors. Multifaceted interventions involve EMR-based strategies, pharmacist- and nurse-led initiatives, involvement of community personnel, polypills, and digital solutions.

SUMMARY

Team-based strategies aimed to prevent HF incorporate a broad group of personnel and tools. Despite implementation challenges, existing resources can be efficiently utilized to facilitate team-based approaches to potentially reduce the burden of HF.

The year in cardiovascular medicine 2021: heart failure and cardiomyopathies

In the year 2021, the universal definition and classification of heart failure (HF) was published that defines HF as a clinical syndrome with symptoms and/or signs caused by a cardiac abnormality and corroborated by elevated natriuretic peptide levels or objective evidence of cardiogenic congestion. This definition and the classification of HF with reduced ejection fraction (HFrEF), mildly reduced, and HF with preserved ejection fraction (HFpEF) is consistent with the 2021 ESC Guidelines on HF. Among several other new recommendations, these guidelines give a Class I indication for the use of the sodium–glucose co-transporter 2 (SGLT2) inhibitors dapagliflozin and empagliflozin in HFrEF patients. As the first evidence-based treatment for HFpEF, in the EMPEROR-Preserved trial, empagliflozin reduced the composite endpoint of cardiovascular death and HF hospitalizations. Several reports in 2021 have provided novel and detailed analyses of device and medical therapy in HF, especially regarding sacubitril/valsartan, SGLT2 inhibitors, mineralocorticoid receptor antagonists, ferric carboxymaltose, soluble guanylate cyclase activators, and cardiac myosin activators. In patients hospitalized with COVID-19, acute HF and myocardial injury is quite frequent, whereas myocarditis and long-term damage to the heart are rather uncommon.

Incorporation of natriuretic peptides with clinical risk scores to predict heart failure among individuals with dysglycaemia

AIMS

To evaluate the performance of the WATCH-DM risk score, a clinical risk score for heart failure (HF), in patients with dysglycaemia and in combination with natriuretic peptides (NPs).

METHODS AND RESULTS

Adults with diabetes/pre-diabetes free of HF at baseline from four cohort studies (ARIC, CHS, FHS, and MESA) were included. The machine learning- [WATCH-DM(ml)] and integer-based [WATCH-DM(i)] scores were used to estimate the 5-year risk of incident HF. Discrimination was assessed by Harrell's concordance index (C-index) and calibration by the Greenwood-Nam-D'Agostino (GND) statistic. Improvement in model performance with the addition of NP levels was assessed by C-index and continuous net reclassification improvement (NRI). Of the 8938 participants included, 3554 (39.8%) had diabetes and 432 (4.8%) developed HF within 5 years. The WATCH-DM(ml) and WATCH-DM(i) scores demonstrated high discrimination for predicting HF risk among individuals with dysglycaemia (C-indices = 0.80 and 0.71, respectively), with no evidence of miscalibration (GND P ≥0.10). The C-index of elevated NP levels alone for predicting incident HF among individuals with dysglycaemia was significantly higher among participants with low/intermediate (<13) vs. high (≥13) WATCH-DM(i) scores [0.71 (95% confidence interval 0.68-0.74) vs. 0.64 (95% confidence interval 0.61-0.66)]. When NP levels were combined with the WATCH-DM(i) score, HF risk discrimination improvement and NRI varied across the spectrum of risk with greater improvement observed at low/intermediate risk [WATCH-DM(i) <13] vs. high risk [WATCH-DM(i) ≥13] (C-index = 0.73 vs. 0.71; NRI = 0.45 vs. 0.17).

CONCLUSION

The WATCH-DM risk score can accurately predict incident HF risk in community-based individuals with dysglycaemia. The addition of NP levels is associated with greater improvement in the HF risk prediction performance among individuals with low/intermediate risk than those with high risk.

Improving the enrollment of women and racially/ethnically diverse populations in cardiovascular clinical trials: An ASPC practice statement

Cardiovascular disease (CVD) remains the leading cause of death for both women and men worldwide. In the United States (U.S.), there are significant disparities in cardiovascular risk factors and CVD outcomes among racial and ethnic minority populations, some of whom have the highest U.S. CVD incidence and mortality. Despite this, women and racial/ethnic minority populations remain underrepresented in cardiovascular clinical trials, relative to their disease burden and population percentage. The lack of diverse participants in trials is not only a moral and ethical issue, but a scientific concern, as it can limit application of future therapies. Providing comprehensive demographic data by sex and race/ethnicity and increasing representation of diverse participants into clinical trials are essential in assessing accurate drug response, safety and efficacy information. Additionally, diversifying investigators and clinical trial staff may assist with connecting to the language, customs, and beliefs of study populations and increase recruitment of participants from diverse backgrounds. In this review, a working group for the American Society for Preventive Cardiology (ASPC) reviewed the literature regarding the inclusion of women and individuals of diverse backgrounds into cardiovascular clinical trials, focusing on prevention, and provided recommendations of best practices for improving enrollment to be more representative of the U.S. society into trials.

Predicting Incident Heart Failure in Women With Machine Learning: The Women's Health Initiative Cohort

BACKGROUND

Heart failure (HF) is a leading cause of cardiac morbidity among women, whose risk factors differ from those in men. We used machine-learning approaches to develop risk- prediction models for incident HF in a cohort of postmenopausal women from the Women's Health Initiative (WHI).

METHODS

We used 2 machine-learning methods-Least Absolute Shrinkage and Selection Operator (LASSO) and Classification and Regression Trees (CART)-to perform variable selection on 1227 baseline WHI variables for the primary outcome of incident HF. These variables were then used to construct separate Cox proportional hazard models, and we compared these results, using receiver-operating characteristic (ROC) curve analysis, against a comparator model built using variables from the Atherosclerosis Risk in Communities (ARIC) HF prediction model. We analyzed 43,709 women who had 2222 incident HF events; median follow-up was 14.3 years.

RESULTS

LASSO selected 10 predictors, and CART selected 11 predictors. The highest correlation between selected variables was 0.46. In addition to selecting well-established predictors such as age, myocardial infarction, and smoking, novel predictors included physical function, number of pregnancies, number of previous live births and age at menopause. In ROC analysis, the CART-derived model had the highest C-statistic of 0.83 (95% confidence interval [CI], 0.81-0.85), followed by LASSO 0.82 (95% CI, 0.81-0.84) and ARIC 0.73 (95% CI, 0.70-0.76).

CONCLUSIONS

Machine-learning approaches can be used to develop HF risk-prediction models that can have better discrimination compared with an established HF risk model and may provide a basis for investigating novel HF predictors.

Prevalence and Prognostic Implications of Diabetes With Cardiomyopathy in Community-Dwelling Adults

BACKGROUND

Diabetes is associated with abnormalities in cardiac remodeling and high risk of heart failure (HF).

OBJECTIVES

The purpose of this study was to evaluate the prevalence and prognostic implications of diabetes with cardiomyopathy (DbCM) among community-dwelling individuals.

METHODS

Adults without prevalent cardiovascular disease or HF were pooled from 3 cohort studies (ARIC [Atherosclerosis Risk In Communities], CHS [Cardiovascular Health Study], CRIC [Chronic Renal Insufficiency Cohort]). Among participants with diabetes, DbCM was defined using different definitions: 1) least restrictive: ≥1 echocardiographic abnormality (left atrial enlargement, left ventricle hypertrophy, diastolic dysfunction); 2) intermediate restrictive: ≥2 echocardiographic abnormalities; and 3) most restrictive: elevated N-terminal pro-B-type natriuretic peptide levels (>125 in normal/overweight or >100 pg/mL in obese) plus ≥2 echocardiographic abnormalities. Adjusted Fine-Gray models were used to evaluate the risk of HF.

RESULTS

Among individuals with diabetes (2,900 of 10,208 included), the prevalence of DbCM ranged from 67.0% to 11.7% in the least and most restrictive criteria, respectively. Higher fasting glucose, body mass index, and age as well as worse kidney function were associated with higher risk of DbCM. The 5-year incidence of HF among participants with DbCM ranged from 8.4%-12.8% in the least and most restrictive definitions, respectively. Compared with euglycemia, DbCM was significantly associated with higher risk of incident HF with the highest risk observed for the most restrictive definition of DbCM (HR: 2.55 [95% CI: 1.69-3.86]; least restrictive criteria HR: 1.99 [95% CI: 1.50-2.65]). A similar pattern of results was observed across cohort studies, across sex and race subgroups, and among participants without hypertension or obesity.

CONCLUSIONS

Regardless of the criteria used to define cardiomyopathy, DbCM identifies a high-risk subgroup for developing HF.

Can the Addition of NT-proBNP and Glucose Measurements Improve the Prognostication of High-Sensitivity Cardiac Troponin Measurements for Patients with Suspected Acute Coronary Syndrome?

Guidelines published in 2021 have supported natriuretic peptide (NP) testing for the prognostication in patients with acute coronary syndrome (ACS) and for the diagnosis of chronic and acute heart failure (HF). Our objective was to determine if the addition of N-terminal pro B-type NP (NT-proBNP) and glucose to high-sensitivity cardiac troponin (hs-cTn) could better identify emergency department (ED) patients with potential ACS at low- and high-risk for a serious cardiovascular outcome over the next 72 h. The presentation sample in two different ED cohorts which enrolled patients with symptoms suggestive of ACS within six hours of pain onset (Cohort-1, n = 126 and Cohort-2, n = 143) that had Abbott hs-cTnI, Roche hs-cTnT, NT-proBNP and glucose were evaluated for NT-proBNP alone and combined with hs-cTn and glucose for the primary outcome (composite which included death, myocardial infarction, HF, serious arrhythmia and refractory angina) via receiver-operating characteristic (ROC) curve analyses with area under the curve (AUC) and diagnostic estimates derived. The AUC for NT-proBNP for the primary outcome was 0.68 (95% confidence interval (CI): 0.59-0.76) and 0.75 (95%CI: 0.67-0.82) in Cohort-1 and 2, respectively, with the 125 ng/L cutoff yielding a higher sensitivity (≥75%) as compared to the 300 ng/L cutoff (≥58%). Using the 125 ng/L cutoff for NT-proBNP with the published glucose and hs-cTn cutoffs for risk-stratification produced a new score (GuIDER score for Glucose, Injury and Dysfunction in the Emergency-setting for cardiovascular-Risk) and yielded higher AUCs as compared to NT-proBNP (p < 0.05). GuIDER scores of 0 and 5 using either hs-cTnI/T yielded sensitivity estimates of 100% and specificity estimates > 92% for the primary outcome. A secondary analysis assessing MI alone in the overall population (combined Cohorts 1 and 2) also achieved 100% sensitivity for MI with a GuIDER cutoff ≥ 2, ruling-out 48% (Roche) and 38% (Abbott) of the population at presentation for MI. Additional studies are needed for the GuIDER score in both the acute and ambulatory setting to further refine the utility, however, the preliminary findings reported here may present a pathway forward for inclusion of NP testing for ruling-out serious cardiac events and MI in the emergency setting.