Eligibility for cardiac resynchronization therapy in patients hospitalized with heart failure

Osmanska, Joanna; Hawkins, Nathaniel M.; Toma, Mustafa; Ignaszewski, Andrew; Virani, Sean

doi:10.1002/ehf2.12297

Cited by 8 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current clinical guidelines define specific eligibility criteria for physicians to base their CRT recommendations [ 26 ]. The increasing accuracy of computational predictions suggests that incorporating personalized model-based probabilities could benefit such recommendation criteria.…”

Section: Discussionmentioning

confidence: 99%

Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features

Haque

Stubbs

Hubig

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Cardiac Resynchronization Therapy (CRT) is a widely used, device-based therapy for patients with left ventricle (LV) failure. Unfortunately, many patients do not benefit from CRT, so there is potential value in identifying this group of non-responders before CRT implementation. Past studies suggest that predicting CRT response will require diverse variables, including demographic, biomarker, and LV function data. Accordingly, the objective of this study was to integrate diverse variable types into a machine learning algorithm for predicting individual patient responses to CRT. Methods We built an ensemble classification algorithm using previously acquired data from the SMART-AV CRT clinical trial (n = 794 patients). We used five-fold stratified cross-validation on 80% of the patients (n = 635) to train the model with variables collected at 0 months (before initiating CRT), and the remaining 20% of the patients (n = 159) were used as a hold-out test set for model validation. To improve model interpretability, we quantified feature importance values using SHapley Additive exPlanations (SHAP) analysis and used Local Interpretable Model-agnostic Explanations (LIME) to explain patient-specific predictions. Results Our classification algorithm incorporated 26 patient demographic and medical history variables, 12 biomarker variables, and 18 LV functional variables, which yielded correct prediction of CRT response in 71% of patients. Additional patient stratification to identify the subgroups with the highest or lowest likelihood of response showed 96% accuracy with 22 correct predictions out of 23 patients in the highest and lowest responder groups. Conclusion Computationally integrating general patient characteristics, comorbidities, therapy history, circulating biomarkers, and LV function data available before CRT intervention can improve the prediction of individual patient responses.

show abstract

Section: Discussionmentioning

confidence: 99%

Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features

Haque

Stubbs

Hubig

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Thus, studies performed in a different locality to this study are required to confirm our findings and may show a different eligibility rate. Indeed, the eligibility rate for CRT in different localities has been shown to vary between 6% and 22% 15,17,23 …”

Section: Discussionmentioning

confidence: 99%

How many patients with heart failure are eligible for cardiac contractility modulation therapy?

et al. 2020

View full text Add to dashboard Cite

Background Increasing evidence exists suggesting that cardiac contractility modulation therapy (CCM) improves symptoms in heart failure patients if various selection criteria are fulfilled. The aim of this study is to analyse an unselected sample of heart failure patients to establish what percentage of patients would meet the current criteria for CCM therapy. Methods All patients admitted to two district general hospitals in the UK in 2018 with a diagnosis of heart failure were audited for eligibility for CCM therapy. The selection criteria were (a) ejection fraction (EF) 25%‐45%, (b) QRS duration less than 130 ms, (c) New York Heart Association (NYHA) class 3‐4 and (d) treated for heart failure for at least 90 days and on stable medications. Exclusion criteria included: (a) significant valvular disease, (b) permanent or persistent atrial fibrillation, (c) biventricular pacing system implanted or QRS duration more than 130 ms and (4) patients not suitable for device therapy as a result of palliative treatment intent. Results A total of 475 patients were admitted with heart failure during the study period. From this group, 24 (5.1%) patients fulfilled the criteria for CCM therapy. The mean age and ejection fraction were 70.8 ± 10.2 and 32.5% ± 7.4%. The majority of patients were men (71%) and had an ischaemic cardiomyopathy (75%). If patients with atrial fibrillation were included, an additional 18 (3.8%) patients potentially may be eligible for CCM. Conclusion Only 5.1% of all patients presenting with heart failure might benefit from cardiac CCM. This is a small proportion of the overall heart failure population. However, this population has no other current option for device therapy of their condition.

show abstract

“…Whilst Cardiac Resynchronization Therapy (CRT) is as sociated with significant improvement in morbidity and mor tality in HF patients, only 16% of HF-hospitalized patients meet class I or Class IIA criteria for CRT implantation [ 36 ]. This leaves 84% currently without a cardiac device option to improve LVEF.…”

Section: Cardiac Contraction Modulationmentioning

confidence: 99%

Novel Non-pharmaceutical Advancements in Heart Failure Management: The Emerging Role of Technology

Nolan

Tan

Neil

2022

CCR

View full text Add to dashboard Cite

Purpose of Review: To summarise and discuss the implications of recent technological advances in heart failure care. Recent Findings: Heart failure remains a significant source of morbidity and mortality in the US population despite multiple classes of approved pharmacological treatments. Novel cardiac devices and technologies may offer an opportunity to improve outcomes. Baroreflex Activation Therapy and Cardiac Contractility Remodelling may improve myocardial contractility by altering neurohormonal stimulation of the heart. Implantable Pulmonary Artery Monitors and Biatrial Shunts may prevent heart failure admissions by altering the trajectory of progressive congestion. Phrenic Nerve Stimulation offers potentially effective treatment for comorbid conditions. Smartphone applications offer an intriguing strategy for improving medication adherence. Summary: Novel heart failure technologies offer promise for reducing this public health burden. Randomized controlled studies are indicated for assessing the future role of these novel therapies.

show abstract

Eligibility for cardiac resynchronization therapy in patients hospitalized with heart failure

Cited by 8 publications

References 30 publications

Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features

Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features

How many patients with heart failure are eligible for cardiac contractility modulation therapy?

Novel Non-pharmaceutical Advancements in Heart Failure Management: The Emerging Role of Technology

Contact Info

Product

Resources

About