Performance of risk models to predict mortality risk for patients with heart failure: evaluation in an integrated health system.

BACKGROUND: Referral of patients with heart failure (HF) who are at high mortality risk for specialist evaluation is recommended. Yet, most tools for identifying such patients are difficult to implement in electronic health record (EHR) systems. OBJECTIVE: To assess the performance and ease of implementation of Machine learning Assessment of RisK and EaRly mortality in Heart Failure (MARKER-HF), a machine-learning model that uses structured data that is readily available in the EHR, and compare it with two commonly used risk scores: the Seattle Heart Failure Model (SHFM) and Meta-Analysis Global Group in Chronic (MAGGIC) Heart Failure Risk Score. DESIGN: Retrospective, cohort study. PARTICIPANTS: Data from 6764 adults with HF were abstracted from EHRs at a large integrated health system from 1/1/10 to 12/31/19. MAIN MEASURES: One-year survival from time of first cardiology or primary care visit was estimated using MARKER-HF, SHFM, and MAGGIC. Discrimination was measured by the area under the receiver operating curve (AUC). Calibration was assessed graphically. KEY RESULTS: Compared to MARKER-HF, both SHFM and MAGGIC required a considerably larger amount of data engineering and imputation to generate risk score estimates. MARKER-HF, SHFM, and MAGGIC exhibited similar discriminations with AUCs of 0.70 (0.69-0.73), 0.71 (0.69-0.72), and 0.71 (95% CI 0.70-0.73), respectively. All three scores showed good calibration across the full risk spectrum. CONCLUSIONS: These findings suggest that MARKER-HF, which uses readily available clinical and lab measurements in the EHR and required less imputation and data engineering than SHFM and MAGGIC, is an easier tool to identify high-risk patients in ambulatory clinics who could benefit from referral to a HF specialist.

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

Background: Most risk prediction models are confined to specific medical conditions, thus limiting their application to general medical populations. Objectives: The MARKER-HF (Machine learning Assessment of RisK and EaRly mortality in Heart Failure) risk model was developed in heart failure (HF) patients. We assessed the ability of MARKER-HF to predict 1-year mortality in a large community-based hospital registry database including patients with and without HF. Methods: This study included 41,749 consecutive patients who underwent echocardiography in a tertiary referral hospital (4,640 patients with and 37,109 without HF). Patients without HF were further subdivided into those with (n = 22,946) and without cardiovascular disease (n = 14,163) and also into cohorts based on recent acute coronary syndrome or history of atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, hypertension, or malignancy. Results: The median age of the 41,749 patients was 65 years, and 56.2% were male. The receiver operated area under the curves for MARKER-HF prediction of 1-year mortality of patients with HF was 0.729 (95% CI: 0.706-0.752) and for patients without HF was 0.770 (95% CI: 0.760-0.780). MARKER-HF prediction of mortality was consistent across subgroups with and without cardiovascular disease and in patients diagnosed with acute coronary syndrome, atrial fibrillation, chronic obstructive pulmonary disease, chronic kidney disease, diabetes mellitus, or hypertension. Patients with malignancy demonstrated higher mortality at a given MARKER-HF score than did patients in the other groups. Conclusions: MARKER-HF predicts mortality for patients with HF as well as for patients suffering from a variety of diseases.

Improving clinical trial efficiency using a machine learning-based risk score to enrich study populations.

AIMS: Prognostic enrichment strategies can make trials more efficient, although potentially at the cost of diminishing external validity. Whether using a risk score to identify a population at increased mortality risk could improve trial efficiency is uncertain. We aimed to assess whether Machine learning Assessment of RisK and EaRly mortality in Heart Failure (MARKER-HF), a previously validated risk score, could improve clinical trial efficiency. METHODS AND RESULTS: Mortality rates and association of MARKER-HF with all-cause death by 1 year were evaluated in four community-based heart failure (HF) and five HF clinical trial cohorts. Sample size required to assess effects of an investigational therapy on mortality was calculated assuming varying underlying MARKER-HF risk and proposed treatment effect profiles. Patients from community-based HF cohorts (n = 11 297) had higher observed mortality and MARKER-HF scores than did clinical trial patients (n = 13 165) with HF with either reduced ejection fraction (HFrEF) or preserved ejection fraction (HFpEF). MARKER-HF score was strongly associated with risk of 1-year mortality both in the community (hazard ratio [HR] 1.48, 95% confidence interval [CI] 1.44-1.52) and clinical trial cohorts with HFrEF (HR 1.41, 95% CI 1.30-1.54), and HFpEF (HR 1.74, 95% CI 1.53-1.98), per 0.1 increase in MARKER-HF. Using MARKER-HF to identify patients for a hypothetical clinical trial assessing mortality reduction with an intervention, enabled a reduction in sample size required to show benefit. CONCLUSION: Using a reliable predictor of mortality such as MARKER-HF to enrich clinical trial populations provides a potential strategy to improve efficiency by requiring a smaller sample size to demonstrate a clinical benefit.

An upset to the standard model.

Latest measurement of the W boson digs at the most important theory in particle physics.

A machine learning risk score predicts mortality across the spectrum of left ventricular ejection fraction.

AIMS: Heart failure (HF) guideline recommendations categorize patients according to left ventricular ejection (LVEF). Mortality risk, however, varies considerably within each category and the likelihood of death in an individual patient is often uncertain. Accurate assessment of mortality risk is an important component in the decision-making process for many therapies. In this report, we assess the accuracy of MARKER-HF, a recently described machine learning-based risk score, in predicting mortality of patients in the three guideline-defined HF categories and its ability to distinguish risk of death for patients within each category. METHODS AND RESULTS: MARKER-HF was used to calculate mortality risk in a hospital-based cohort of 4064 patients categorized into groups with reduced, mid-range, or preserved LVEF. MARKER-HF was substantially more accurate than LVEF in predicting mortality and was highly accurate in all three HF categories, with c-statistics ranging between 0.83 to 0.89. Moreover, MARKER-HF accurately discriminated between patients at high, intermediate and low levels of mortality risk within each of the three categories of HF used by guidelines. CONCLUSIONS: MARKER-HF accurately predicts mortality in patients within the three categories of HF used in guidelines for management recommendations and it discriminates between magnitude of risk of patients in each category. MARKER-HF mortality risk prediction should be helpful to providers in making recommendations regarding the advisability of therapies designed to mitigate this risk, particularly when they are costly or associated with adverse events, and for patients and their families in making future plans.

Improving risk prediction in heart failure using machine learning.

BACKGROUND: Predicting mortality is important in patients with heart failure (HF). However, current strategies for predicting risk are only modestly successful, likely because they are derived from statistical analysis methods that fail to capture prognostic information in large data sets containing multi-dimensional interactions. METHODS AND RESULTS: We used a machine learning algorithm to capture correlations between patient characteristics and mortality. A model was built by training a boosted decision tree algorithm to relate a subset of the patient data with a very high or very low mortality risk in a cohort of 5822 hospitalized and ambulatory patients with HF. From this model we derived a risk score that accurately discriminated between low and high-risk of death by identifying eight variables (diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width). This risk score had an area under the curve (AUC) of 0.88 and was predictive across the full spectrum of risk. External validation in two separate HF populations gave AUCs of 0.84 and 0.81, which were superior to those obtained with two available risk scores in these same populations. CONCLUSIONS: Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.