CoChat

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Open access

The DOI matches its Crossref record; 262 of the 263 references it cites were found in a registry or an index.

Abstract

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/diagnostics12030722

Cites

262 of 262 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure A1 Typical online system for multiclass CVD risk stratification.
Figure A1 Typical online system for multiclass CVD risk stratification.CC BY · PubMed Central
Figure A2 Pseudo-code for multiclass technique.
Figure A2 Pseudo-code for multiclass technique.CC BY · PubMed Central
Figure A3 BR classifier, #Ex: Example.
Figure A3 BR classifier, #Ex: Example.CC BY · PubMed Central
Figure A4 Classifier chain functioning; P1–P4 are data points under; Ex; Ex: Example.
Figure A4 Classifier chain functioning; P1–P4 are data points under; Ex; Ex: Example.CC BY · PubMed Central
Figure A5 Label powerset transformation, Ex: Example.
Figure A5 Label powerset transformation, Ex: Example.CC BY · PubMed Central
Figure A6 Pseudo-code for multi-label technique.
Figure A6 Pseudo-code for multi-label technique.CC BY · PubMed Central
Figure A7 Pseudo-code for ensemble-based technique.
Figure A7 Pseudo-code for ensemble-based technique.CC BY · PubMed Central
Figure A8 (Top) Anatomical link between the carotid artery and aortic arch. (Bottom) Typical neural network for CVD risk stratification.
Figure A8 (Top) Anatomical link between the carotid artery and aortic arch. (Bottom) Typical neural network for CVD risk stratification.CC BY · PubMed Central
Figure 1 PRISMA model for selection of studies for CVD risk assessment.
Figure 1 PRISMA model for selection of studies for CVD risk assessment.CC BY · PubMed Central
Figure 2 Statistical distribution (a) types of CVD paradigms, (b) types of risk classes in multiclass CVD (c) ML-based CVD systems without/with feature selection, (d) # GT’s in multi-label based CVD, (e) feature selection techniques, (f) trend of the ML-based CVD publications by year.
Figure 2 Statistical distribution (a) types of CVD paradigms, (b) types of risk classes in multiclass CVD (c) ML-based CVD systems without/with feature selection, (d) # GT’s in multi-label based CVD, (e) feature selection techniques, (f) trend of the ML-based CVD publications by year.CC BY · PubMed Central
Figure 3 (a) Plaque formation in the coronary artery and (b) process of plaque rupture in coronary artery (Courtesy of AtheroPoint™, Roseville, CA, USA) [131].
Figure 3 (a) Plaque formation in the coronary artery and (b) process of plaque rupture in coronary artery (Courtesy of AtheroPoint™, Roseville, CA, USA) [131].CC BY · PubMed Central
Figure 4 Multiclass architecture for CVD risk stratification (AtheroEdge 3.0ML).
Figure 4 Multiclass architecture for CVD risk stratification (AtheroEdge 3.0ML).CC BY · PubMed Central
Figure 5 Example of multiclass architecture; CWD: Choi-William’s time-frequency distribution; TF: time-frequency.
Figure 5 Example of multiclass architecture; CWD: Choi-William’s time-frequency distribution; TF: time-frequency.CC BY · PubMed Central
Figure 6 Architecture for multi-label-based CVD risk classification using carotid ultrasound.
Figure 6 Architecture for multi-label-based CVD risk classification using carotid ultrasound.CC BY · PubMed Central
Figure 7 ECG architecture for multi-label-based CVD classification.
Figure 7 ECG architecture for multi-label-based CVD classification.CC BY · PubMed Central
Figure 8 Ensemble-based Architecture for CVD risk stratification.
Figure 8 Ensemble-based Architecture for CVD risk stratification.CC BY · PubMed Central
Figure 9 (Top) Types of performance evaluation metrics for ML-based CVD systems, (Bottom) Example of a ROC for multi-label-based CVD systems (Courtesy of AtheroPoint, Roseville, CA, USA) [84], PPV: positive predictive value; NPV: negative predictive value; FPR: false positive rate; FNR: false negative rate; BR: binary relevance; CC: classifier chain; LP: label powerset; MLARAM: multi-label adaptive resonance associative map; RakEL: random k-labelset; MLkNN: multi-label k-nearest neighbor; CVE: cardiovascular events; CAD: coronary artery disease; ACS: acute coronary syndrome; ROC: receiver operating characteristic; (a–f): different en-points used in the multi-label studies.
Figure 9 (Top) Types of performance evaluation metrics for ML-based CVD systems, (Bottom) Example of a ROC for multi-label-based CVD systems (Courtesy of AtheroPoint, Roseville, CA, USA) [84], PPV: positive predictive value; NPV: negative predictive value; FPR: false positive rate; FNR: false negative rate; BR: binary relevance; CC: classifier chain; LP: label powerset; MLARAM: multi-label adaptive resonance associative map; RakEL: random k-labelset; MLkNN: multi-label k-nearest neighbor; CVE: cardiovascular events; CAD: coronary artery disease; ACS: acute coronary syndrome; ROC: receiver operating characteristic; (a–f): different en-points used in the multi-label studies.CC BY · PubMed Central
Figure 10 Cumulative plot for (a) multiclass studies (b) multi-label studies (c) ensemble studies (d) cumulative plot for all the ML studies.
Figure 10 Cumulative plot for (a) multiclass studies (b) multi-label studies (c) ensemble studies (d) cumulative plot for all the ML studies.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Research works printed but not linked: 4

  1. Saba, L., and Suri, J.S. (2013). Multi-Detector CT Imaging: Principles, Head, Neck, and Vascular Systems, CRC Press.
  2. Lo, 2013, Generalized k-labelsets ensemble for multi-label and cost-sensitive classification, IEEE Trans. Knowl. Data Eng., 26, 1679
  3. Zuluaga, M.A., Cardoso, M.J., and Ourselin, S. (2020). Automatic right ventricle segmentation using multi-label fusion in cardiac MRI. arXiv.
  4. Puvar, 2021, Heart Disease Detection using Ensemble Learning Approach, Int. Res. J. Eng. Technol. (IRJET), 8, 2395-0072

Cited by

See all 67

Metadata

Authors
Suri, J. S., Bhagawati, M., Paul, S., Protogerou, A. D., Sfikakis, P. P., Kitas, G. D., Khanna, N. N., Ruzsa, Z., Sharma, A. M., Saxena, S., Faa, G., Laird, J. R., Johri, A. M., Kalra, M. K., Paraskevas, K. I., & Saba, L.
Affiliations
  • Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA 95661, USA
  • North Eastern Hill University (IN)
  • Research Unit Clinic, Laboratory of Pathophysiology, Department of Cardiovascular Prevention, National and Kapodistrian University of Athens, 11527 Athens, Greece
  • National and Kapodistrian University of Athens (GR)
  • University of Manchester (GB)
  • Indraprastha Apollo Hospitals (IN)
  • Department of Internal Medicines, Invasive Cardiology Division, University of Szeged, 6720 Szeged, Hungary
  • University of Virginia (US)
  • International Institute of Information Technology (IN)
  • Azienda Ospedaliero-Universitaria Cagliari (IT)
  • St. Helena Hospital (US)
  • Queen's University (CA)
  • Massachusetts General Hospital (US)
  • Department of Vascular Surgery, Central Clinic of Athens, N. Iraklio, 14122 Athens, Greece
Corresponding author
Suri, Jasjit S.
Venue
Diagnostics
Publisher
MDPI AG
Published
2022-03-16
Volume
12
Issue
3
Pages
722
ISSN
2075-4418 (ISSN-L)
OpenAlex
W4220653406
Cited by
55
References
263
Citations by year
2026: 6 · 2025: 12 · 2024: 17 · 2023: 14 · 2022: 6
FWCI
1.80
Type
journal article
Language
en
Open access
Locations
  • Diagnostics (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • SZTE Publicatio Repozitórium (University of Szeged) (acceptedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • UNICA IRIS Institutional Research Information System (University of Cagliari) (submittedVersion, other-oa)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
cardiovascular risk stratification, cardiovascular disease risk assessment, multi-class classification, multi-label classification, ensemble learning, artificial intelligence in cardiology, risk of bias, deep learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.