Could a Multi-Marker and Machine Learning Approach Help Stratify Patients with Heart Failure?
Manuela Lotierzo1,2, Romain Bruno3, Amanda Finan-Marchi1
1PhyMedExp, Université de Montpellier, INSERM, CNRS, 34295 Montpellier, France.
Medicina (Kaunas, Lithuania)
|October 23, 2021
Summary
This study developed a machine learning strategy using routine blood tests to distinguish heart failure with preserved ejection fraction (HFpEF) from heart failure with reduced ejection fraction (HFrEF). The approach shows promise for personalized HF treatments and clinical trial recruitment.
Area of Science:
- Cardiology
- Biochemistry
- Machine Learning
Background:
- Heart failure with preserved ejection fraction (HFpEF) constitutes half of all heart failure cases.
- Currently, no specific biomarkers exist to reliably differentiate HFpEF from heart failure with reduced ejection fraction (HFrEF).
Purpose of the Study:
- To stratify heart failure patients into HFpEF and HFrEF subgroups using biochemical markers and clinical data.
- To develop a machine learning (ML) strategy for a blood-based signature to distinguish between HFpEF and HFrEF.
Main Methods:
- A cohort study included 24 HFpEF and 34 HFrEF patients.
- Routine blood tests analyzed biomarkers of renal function, heart function, inflammation, and iron metabolism.
- A machine learning strategy, employing a genetic algorithm approach, was developed using multivariate factorial discriminant analysis.
Main Results:
- Logistic regression analysis of demographic and clinical biomarkers did not significantly differentiate HFpEF and HFrEF.
- Machine learning demonstrated encouraging results with high sensitivity (75-100%) and acceptable precision (58-60%) in distinguishing the groups.
- Accuracy ranged from 64-69% across validation and test groups, with specificity between 44-55%.
Conclusions:
- Combining biochemical and clinical markers is a viable strategy for developing a computer-aided diagnostic tool for HFpEF.
- This translational approach can facilitate personalized treatment strategies and identify suitable populations for clinical trials.
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
73
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
73
01:30Heart Failure V: Medical Management
49
Medical Management of Acute Decompensated Heart Failure (ADHF)The primary goals of therapy for patients hospitalized with acute decompensated heart failure (ADHF) include:Relieving symptomsOptimizing volume statusSupporting oxygenation and ventilationMaintaining cardiac output (CO) and end-organ perfusionIdentifying and addressing the cause of ADHFPreventing complicationsProviding patient education on factors precipitating HF exacerbationPlanning for dischargeOngoing monitoring and assessment...
49
01:22Heart Failure VI: Adjunct Therapies
53
Additional therapies for treating patients with heart failure (HF) may include procedural interventions, supplemental oxygen, the management of sleep disorders, and nutritional therapy.Procedural InterventionsImplantable Cardioverter-Defibrillator: For patients at risk of life-threatening arrhythmias due to severe left ventricular dysfunction, an Implantable Cardioverter-Defibrillator (ICD) can detect and terminate these arrhythmias, preventing sudden cardiac death and improving survival rates.
53