A registry-based algorithm to predict ejection fraction in patients with heart failure

Development and validation of algorithms to predict left ventricular ejection fraction class from healthcare claims data

AIMS

The use of large medical or healthcare claims databases is very useful for population-based studies on the burden of heart failure (HF). Clinical characteristics and management of HF patients differ according to categories of left ventricular ejection fraction (LVEF), but this information is often missing in such databases. We aimed to develop and validate algorithms to identify LVEF in healthcare databases where the information is lacking.

METHODS AND RESULTS

Algorithms were built by machine learning with a random forest approach. Algorithms were trained and reinforced using the French national claims database [Système National des Données de Santé (SNDS)] and a French HF registry. Variables were age, gender, and comorbidities, which could be identified by medico-administrative code-based proxies, Anatomical Therapeutic Chemical codes for drug delivery, International Classification of Diseases (Tenth Revision) coding for hospitalizations, and administrative codes for any other type of reimbursed care. The algorithms were validated by cross-validation and against a subset of the SNDS that includes LVEF information. The areas under the receiver operating characteristic curve were 0.84 for the algorithm identifying LVEF ≤ 40% and 0.79 for the algorithms identifying LVEF < 50% and ≥50%. For LVEF ≤ 40%, the reinforced algorithm identified 50% of patients in the validation dataset with a positive predictive value of 0.88 and a specificity of 0.96. The most important predictive variables were delivery of HF medication, sex, age, hospitalization, and testing for natriuretic peptides with different orders of positive or negative importance according to the LVEF category.

CONCLUSIONS

The algorithms identify reduced or preserved LVEF in HF patients within a nationwide healthcare claims database with high positive predictive value and low rates of false positives.

Misuse of multinomial logistic regression in stroke related health research: A systematic review of methodology

Multinomial logistic regression (MLR) is often used to model the association between a nominal outcome variable and one or more covariates. The results of MLR are interpreted as relative risk ratios (RRR) and warrant a more coherent interpretation than ordinary logistic regression. Some authors compare the results of MLR to ordinal logistic regression (OLR), irrespective of the fact that these estimate different quantities. We aim to investigate the time trends in the use and misuse of MLR in studies including stroke patients, specifically the extent to which (1) the results are denoted as anything other than RRR, (2) comparisons are made of results with results of OLR and (3) results have been interpreted coherently. Secondarily, we examine the use of model validation techniques in studies with predictive aims. We searched EMBASE and PubMed for articles using MLR on populations of stroke patients. Identified studies were screened, and information pertaining to our aims was extracted. A total of 285 articles were identified through a systematic literature search, and 68 of these were included in the review. Of these, 60 articles (88%) did not denote exponentiated coefficients of MLR as relative risk ratios but rather some other measure. Additionally, 63 articles (93%) interpreted the results of MLR in a non-coherent manner. Two articles attempted to compare MLR results with those of OLR. Nine studies attempted to use MLR for predictive means, and three used relevant validation techniques. From these findings, it is clear that the interpretation of MLR is often suboptimal.

Incidence and prevalence of heart failure in England: a descriptive analysis of linked primary and secondary care data - the PULSE study

BACKGROUND

Heart failure (HF) is associated with high morbidity and mortality, yet data on HF subtype (HF with reduced ejection fraction [HFrEF] and preserved ejection fraction [HFpEF]) in broad populations are lacking. Additionally, it is unknown whether current HF incidence and prevalence rates are consistent with historical data. Here, we estimate the incidence and prevalence of HF in England and describe the characteristics of patients with HF, both overall and by subtype.

METHODS

This was a non-interventional cohort study based on data from the UK Clinical Practice Research Datalink (CPRD), linked to Hospital Episode Statistics data and Office for National Statistics mortality data. Patients aged ≥ 18 years who were registered in the CPRD Aurum database between 1^st January 2015 and 31^st December 2019 formed the base cohort, from which patients with a recorded chronic HF diagnosis (historical or incident) from 2015-2019 contributed to the incidence and prevalence calculations.

RESULTS

The eligible denominator over the study period comprised 11,414,490 patients, from which 383,896 patients with HF were included as prevalent or incident HF cases. From 2015 to 2019, the incidence rate of newly diagnosed HF increased from 4.1/1,000 person-years to 4.9/1,000 person-years, and HF prevalence increased from 2.1% to 2.4%. Phenotype data were available for 100,224 (26.1%) patients, of which 68,780 patients had HFrEF and 31,444 had HFpEF (HFrEF/HFpEF ratio: 70.1%/29.9%). Comorbidity levels were high and broadly similar across HF subgroups.

CONCLUSIONS

Primary care recording of HF subtype is suboptimal, with more than 7/10 patients with HF lacking subtype data. In patients with a recorded subtype (n = 100,224), a HFrEF/HFpEF ratio of 70%/30% was observed. Comorbidity levels were high regardless of subtype. Between 2015 and 2019, we observed modest but consistent increases in the incidence and prevalence of chronic HF in adults, in line with historical data.

Use of Guideline-Directed Medical Therapy in Patients Aged ≥ 65 Years After the Diagnosis of Heart Failure: A Canadian Population-Based Study

Background

Guideline-directed medical therapy (GDMT) improves clinical outcomes in patients with heart failure with reduced ejection fraction (HFrEF). Despite its proven efficacy, GDMT is underutilized in clinical practice. The current study examines GDMT utilization after incident hospitalization for HF to promote medication initiation, and titration to target dosing within a reasonable time period.

Methods

This observational study identified 66,372 patients with HFrEF who were aged ≥ 65 years and had an incident HF hospitalization, using administrative health data (2013-2018). GDMT (angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, angiotensin receptor-neprilysin inhibitors, β-blockers (BB), and mineralocorticoid receptor antagonists ) received within the 6 months after hospitalization was evaluated by monitoring therapy combinations, optimal dosing (proportion receiving ≥ 50% of the target dose for these inhibitors and blockers, and any dose of MRA), and maximal and last dose assessed, and by use of a GDMT intensity score.

Results

Among patients with HFrEF, 4768 (7.2%) were on no therapy, 17,184 (25.9%), were on monotherapy, 30,912 (46.6%) were on dual therapy, and 13,508 (20.4%) were on triple therapy. Only 8747 (13.2%) and 5484 (8.3%) achieved optimal GDMT based on the maximum dose and the last dispensed dose, respectively, within 6 months postdischarge. Finally, 38,869 (58.6%) achieved < 50% of the maximum intensity score, 23,006 (34.7%) achieved between 50% and 74% of the maximum intensity score, and 4497 (6.8%) achieved a score that was ≥ 75% of the maximum intensity score.

Conclusions

Current pharmacologic management for patients with HFrEF does not align with the Canadian guidelines. Given this gap in care, innovative strategies to optimize care in patients with HFrEF are needed.

Empagliflozin in Heart Failure With Predicted Preserved Versus Reduced Ejection Fraction: Data From the EMPA-REG OUTCOME Trial

BACKGROUND

In the EMPA-REG OUTCOME trial, ejection fraction (EF) data were not collected. In the subpopulation with heart failure (HF), we applied a new predictive model for EF to determine the effects of empagliflozin in HF with predicted reduced (HFrEF) vs preserved (HFpEF) EF vs no HF.

METHODS AND RESULTS

We applied a validated EF predictive model based on patient baseline characteristics and treatments to categorize patients with HF as being likely to have HF with mid-range EF (HFmrEF)/HFrEF (EF <50%) or HFpEF (EF ≥50%). Cox regression was used to assess the effect of empagliflozin vs placebo on cardiovascular death/HF hospitalization (HHF), cardiovascular and all-cause mortality, and HHF in patients with predicted HFpEF, HFmrEF/HFrEF and no HF. Of 7001 EMPA-REG OUTCOME patients with data available for this analysis, 6314 (90%) had no history of HF. Of the 687 with history of HF, 479 (69.7%) were predicted to have HFmrEF/HFrEF and 208 (30.3%) to have HFpEF. Empagliflozin's treatment effect was consistent in predicted HFpEF, HFmrEF/HFrEF and no-HF for each outcome (HR [95% CI] for the primary outcome 0.60 [0.31-1.17], 0.79 [0.51-1.23], and 0.63 [0.50-0.78], respectively; P interaction = 0.62).

CONCLUSIONS

In EMPA-REG OUTCOME, one-third of the patients with HF had predicted HFpEF. The benefits of empagliflozin on HF and mortality outcomes were consistent in nonHF, predicted HFpEF and HFmrEF/HFrEF.

Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class

Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest.

OBJECTIVE

To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVEF), by using available data from Electronic Health Records (EHR).

SUBJECTS AND METHODS

2854 subjects over 25 years old with a diagnosis of HF and LVEF, measured by echocardiography, were selected to develop an algorithm to predict patients with reduced EF using supervised analysis. The performance of the developed algorithm was tested in heart failure patients from Primary Care. To select the most influentual variables, the LASSO algorithm setting was used, and to tackle the issue of one class exceeding the other one by a large amount, we used the Synthetic Minority Oversampling Technique (SMOTE). Finally, Random Forest (RF) and XGBoost models were constructed.

RESULTS

The full XGBoost model obtained the maximum accuracy, a high negative predictive value, and the highest positive predictive value. Gender, age, unstable angina, atrial fibrillation and acute myocardial infarct are the variables that most influence EF value. Applied in the EHR dataset, with a total of 25,594 patients with an ICD-code of HF and no regular follow-up in cardiology clinics, 6170 (21.1%) were identified as pertaining to the reduced EF group.

CONCLUSION

The obtained algorithm was able to identify a number of HF patients with reduced ejection fraction, who could benefit from a protocol with a strong possibility of success. Furthermore, the methodology can be used for studies using data extracted from the Electronic Health Records.

External validation of a claims-based model to predict left ventricular ejection fraction class in patients with heart failure

Background

Ejection fraction (EF) is an important prognostic factor in heart failure (HF), but administrative claims databases lack information on EF. We previously developed a model to predict EF class from Medicare claims. Here, we evaluated the performance of this model in an external validation sample of commercial insurance enrollees.

Methods

Truven MarketScan claims linked to electronic medical records (EMR) data (IBM Explorys) containing EF measurements were used to identify a cohort of US patients with HF between 01-01-2012 and 10-31-2019. By applying the previously developed model, patients were classified into HF with reduced EF (HFrEF) or preserved EF (HFpEF). EF values recorded in EMR data were used to define gold-standard HFpEF (LVEF ≥45%) and HFrEF (LVEF<45%). Model performance was reported in terms of overall accuracy, positive predicted values (PPV), and sensitivity for HFrEF and HFpEF.

Results

A total of 7,001 HF patients with an average age of 71 years were identified, 1,700 (24.3%) of whom had HFrEF. An overall accuracy of 0.81 (95% CI: 0.80–0.82) was seen in this external validation sample. For HFpEF, the model had sensitivity of 0.96 (95%CI, 0.95–0.97) and PPV of 0.81 (95% CI, 0.81–0.82); while for HFrEF, the sensitivity was 0.32 (95%CI, 0.30–0.34) and PPV was 0.73 (95%CI, 0.69–0.76). These results were consistent with what was previously published in US Medicare claims data.

Conclusions

The successful validation of the Medicare claims-based model provides evidence that this model may be used to identify patient subgroups with specific EF class in commercial claims databases as well.

A registry-based algorithm to predict ejection fraction in patients with heart failure

Aims

Left ventricular ejection fraction (EF) is required to categorize heart failure (HF) [i.e. HF with preserved (HFpEF), mid‐range (HFmrEF), and reduced (HFrEF) EF] but is often not captured in population‐based cohorts or non‐HF registries. The aim was to create an algorithm that identifies EF subphenotypes for research purposes.

Methods and results

We included 42 061 HF patients from the Swedish Heart Failure Registry. As primary analysis, we performed two logistic regression models including 22 variables to predict (i) EF≥ vs. <50% and (ii) EF≥ vs. <40%. In the secondary analysis, we performed a multivariable multinomial analysis with 22 variables to create a model for all three separate EF subphenotypes: HFrEF vs. HFmrEF vs. HFpEF. The models were validated in the database from the CHECK‐HF study, a cross‐sectional survey of 10 627 patients from the Netherlands. The C‐statistic (discrimination) was 0.78 [95% confidence interval (CI) 0.77–0.78] for EF ≥50% and 0.76 (95% CI 0.75–0.76) for EF ≥40%. Similar results were achieved for HFrEF and HFpEF in the multinomial model, but the C‐statistic for HFmrEF was lower: 0.63 (95% CI 0.63–0.64). The external validation showed similar discriminative ability to the development cohort.

Conclusions

Routine clinical characteristics could potentially be used to identify different EF subphenotypes in databases where EF is not readily available. Accuracy was good for the prediction of HFpEF and HFrEF but lower for HFmrEF. The proposed algorithm enables more effective research on HF in the big data setting.