scholarly journals A Machine Learning Approach for Chronic Heart Failure Diagnosis

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1863
Author(s):  
Dafni K. Plati ◽  
Evanthia E. Tripoliti ◽  
Aris Bechlioulis ◽  
Aidonis Rammos ◽  
Iliada Dimou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Chronic Heart Failure ◽  
Class Imbalance ◽  
Failure Diagnosis ◽  
Laboratory Findings ◽  
Incremental Value ◽  
Single Feature ◽  
Machine Learning Approach ◽  
Heart Failure Diagnosis

The aim of this study was to address chronic heart failure (HF) diagnosis with the application of machine learning (ML) approaches. In the present study, we simulated the procedure that is followed in clinical practice, as the models we built are based on various combinations of feature categories, e.g., clinical features, echocardiogram, and laboratory findings. We also investigated the incremental value of each feature type. The total number of subjects utilized was 422. An ML approach is proposed, comprising of feature selection, handling class imbalance, and classification steps. The results for HF diagnosis were quite satisfactory with a high accuracy (91.23%), sensitivity (93.83%), and specificity (89.62%) when features from all categories were utilized. The results remained quite high, even in cases where single feature types were employed.

Chronic heart failure diagnosis: biomarkers

ESC CardioMed ◽  
2018 ◽  
pp. 1778-1781
Author(s):  
Christian Mueller
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Natriuretic Peptide ◽  
Natriuretic Peptides ◽  
Point Of Care ◽  
Failure Diagnosis ◽  
Central Laboratory ◽  
Important Advance ◽  
Cardiac Stress ◽  
Heart Failure Diagnosis

Natriuretic peptides including B-type natriuretic peptide (BNP), N-terminal (NT)-proBNP, and midregional pro-atrial natriuretic peptide (MR-proANP) are the biomarkers of choice in the diagnosis of heart failure. Assays measuring either BNP, NT-proBNP, or MR-proANP are widely available and run on large analysers operating in the central laboratory or as point-of-care options. Natriuretic peptides are considered quantitative markers of haemodynamic cardiac stress and therefore quantitative markers of heart failure itself. The clinical introduction of natriuretic peptides constitutes the most important advance in the diagnosis of heart failure in the last decade.

Chronic heart failure diagnosis: biomarkers

ESC CardioMed ◽  
2018 ◽  
pp. 1778-1781
Author(s):  
Christian Mueller
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Natriuretic Peptide ◽  
Natriuretic Peptides ◽  
Point Of Care ◽  
Failure Diagnosis ◽  
Central Laboratory ◽  
Important Advance ◽  
Cardiac Stress ◽  
Heart Failure Diagnosis

Natriuretic peptides including B-type natriuretic peptide (BNP), N-terminal (NT)-proBNP, and midregional pro-atrial natriuretic peptide (MR-proANP) are the biomarkers of choice in the diagnosis of heart failure. Assays measuring either BNP, NT-proBNP, or MR-proANP are widely available and run on large analysers operating in the central laboratory or as point-of-care options. Natriuretic peptides are considered quantitative markers of haemodynamic cardiac stress and therefore quantitative markers of heart failure itself. The clinical introduction of natriuretic peptides constitutes the most important advance in the diagnosis of heart failure in the last decade.

Chronic heart failure diagnosis: biomarkers

ESC CardioMed ◽  
2018 ◽  
pp. 1778-1781
Author(s):  
Christian Mueller
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Natriuretic Peptide ◽  
Natriuretic Peptides ◽  
Point Of Care ◽  
Failure Diagnosis ◽  
Central Laboratory ◽  
Important Advance ◽  
Cardiac Stress ◽  
Heart Failure Diagnosis

Natriuretic peptides including B-type natriuretic peptide (BNP), N-terminal (NT)-proBNP, and midregional pro-atrial natriuretic peptide (MR-proANP) are the biomarkers of choice in the diagnosis of heart failure. Assays measuring either BNP, NT-proBNP, or MR-proANP are widely available and run on large analysers operating in the central laboratory or as point-of-care options. Natriuretic peptides are considered quantitative markers of haemodynamic cardiac stress and therefore quantitative markers of heart failure itself. The clinical introduction of natriuretic peptides constitutes the most important advance in the diagnosis of heart failure in the last decade.

scholarly journals High Intraindividual Variation of B-Type Natriuretic Peptide (BNP) and Amino-Terminal proBNP in Patients with Stable Chronic Heart Failure

2004 ◽  
Vol 50 (11) ◽  
pp. 2052-2058 ◽  
Author(s):  
Sanne Bruins ◽  
M Rebecca Fokkema ◽  
Jeroen W P Römer ◽  
Mike J L DeJongste ◽  
Fey P L van der Dijs ◽  
...  
Keyword(s):  
Heart Failure ◽  
New York ◽  
Chronic Heart Failure ◽  
Natriuretic Peptide ◽  
Heart Association ◽  
Failure Diagnosis ◽  
Treatment Optimization ◽  
Intraindividual Variation ◽  
Amino Terminal ◽  
Heart Failure Diagnosis

Abstract Background: Plasma B-type natriuretic peptide (BNP) and N-terminal proBNP (NT-proBNP) are promising markers for heart failure diagnosis, prognosis, and treatment. Insufficient data on the intraindividual biological variation (CVi) of BNP and NT-proBNP hamper interpretation of changes in concentration on disease progression or treatment optimization. We therefore investigated CVi values in stable heart failure patients. Methods: We recruited 43 patients with stable chronic heart failure living in Curaçao (22 males, 21 females; median age, 63 years; range, 20–86 years; New York Heart Association classes I–III). Samples were collected for within-day CVi (n = 6; every 2 h starting at 0800), day-to-day CVi (n = 5; samples collected between 0800 and 1000 on 5 consecutive days), and week-to-week CVi (n = 6; samples collected between 0800 and 1000 on the same day of the week for 6 consecutive weeks). NT-proBNP (Roche) and BNP (Abbott) were measured by immunoassay. Results: Median (range) concentrations were 134 (0–1630) ng/L (BNP) and 570 (17–5048) ng/L (NT-proBNP). Analytical variation, week-to-week CVi, and reference change values were 8.4%, 40%, and 113% (BNP), and 3.0%, 35%, and 98% (NT-proBNP). Week-to week CVis were inversely related to median BNP concentrations. Week-to week CVis for BNP were 44% (BNP ≤350 ng/L) and 30% (BNP >350 ng/L). Both BNP and NT-proBNP increased between 0800 and 1000. Median NT-proBNP/BNP ratios were inversely related to median BNP concentrations. Conclusions: The high CVis hamper interpretation of changes in BNP and NT-proBNP concentrations and may partly explain their poor diagnostic values in chronic heart failure. Easily modifiable determinants to lower CVi have not been identified. The value of BNP and NT-proBNP for chronic heart failure diagnosis, and especially for follow-up and treatment optimization of individuals, remains largely to be established.

Forced expiratory volume in one second: Predicting return to work within 3months after chronic heart failure diagnosis

2016 ◽  
Vol 203 ◽  
pp. 798-799 ◽  
Author(s):  
Piera Boschetto ◽  
Alice Vaccari ◽  
Rita Groccia ◽  
Enrico Casimirri ◽  
Mariarita Stendardo ◽  
...  
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Return To Work ◽  
Forced Expiratory Volume ◽  
Failure Diagnosis ◽  
Heart Failure Diagnosis

scholarly journals Machine learning analysis of metabolomic biomarkers for diagnosis of heart failure

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
C Coorey ◽  
O Tang ◽  
J.Y.H Yang ◽  
G Figtree
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Prediction Model ◽  
Failure Diagnosis ◽  
Cardiac Biomarkers ◽  
Support Vector ◽  
Private Company ◽  
Model Based ◽  
Cardiovascular Assessment ◽  
Heart Failure Diagnosis

Abstract Background There is emerging evidence that the pathophysiological mechanisms of heart failure are associated with alterations in serum metabolites. Such metabolomic signatures may be useful for heart failure diagnosis, stratification and prognosis. Purpose To evaluate the utility of including metabolomic biomarkers in addition to traditional cardiac biomarkers in a machine learning prediction model of heart failure diagnosis in the well-characterised Canagliflozin Cardiovascular Assessment Study (CANVAS) cohort. Methods A subgroup of the CANVAS/CANVAS-R study cohort was analysed. 101 metabolites in plasma were measured by HPLC (HILIC)-mass spectrometry. A 10-times 5-fold cross-validated support vector machine model with radial basis kernel function was constructed to predict heart failure diagnosis using traditional biomarkers alone and using the combination of traditional biomarkers and metabolomic biomarkers. Model performance and variable importance were both evaluated by area under the curve (AUC) of the receiver operating characteristics (ROC) curve. Results are shown as mean ± standard deviation. Results 967 patients (of which 402 patients had heart failure) were included in the analysis with 341 females, mean age 63±8 years and mean body mass index (BMI) 33±5 kg/m2. All patients had diabetes mellitus with mean HbA1c 8.2±0.9%. The prediction model based on only traditional biomarkers had mean AUC 72±3% and the prediction model based on both traditional biomarkers and metabolomic biomarkers had mean AUC 80±3%. The top metabolomic biomarkers for predicting heart failure were threonine, L-homoserine, creatine and deoxyadenosine. Conclusion Metabolomic biomarkers improved diagnostic performance of a heart failure prediction model and captured variation not encompassed by traditional cardiac biomarkers. FUNDunding Acknowledgement Type of funding sources: Private company. Main funding source(s): Janssen Research and Development

Chronic heart failure - diagnosis

2002 ◽  
Vol 127 (20) ◽  
pp. 1083-1088 ◽  
Author(s):  
M Kindermann ◽  
I Janzen ◽  
B Hennen ◽  
M Böhm
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Failure Diagnosis ◽  
Heart Failure Diagnosis
Sign in / Sign up

Export Citation Format

Share Document