Enhancing Hypertension Risk Diagnosis Using a Hybrid Machine Learning Framework: Leveraging Body Composition Data.

Hypertension, widely recognized as the "silent killer," remains a leading cause of cardiovascular, renal, and neurological complications worldwide. This study proposes a dual‐scenario hybrid machine learning framework for hypertension risk prediction using noninvasive body composition features, aime...

Descripción completa

Detalles Bibliográficos
Publicado en:BioMed Research International Vol. 2026; pp. 1 - 25
Autores principales: Mirzaye, Abdul Wahid, Saadatfar, Hamid, Nematollahi, Mohammad Ali, Banerjee, Baisakhi
Formato: equations & formulas research tables/charts Journal Article
Publicado: Wiley-Blackwell 2/1/2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=191298417&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 191298417
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        23146133
        FT2T
      jtl: BioMed Research International
      issn: 23146133
      maglogo: N
    pubinfo:
      dt: 2/1/2026
      vid: 2026
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        191298417
        191298417
        191298417
        10.1155/bmri/6335947
        191298417
      ppf: 1
      ppct: 24
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: C
          – @attributes:
              type: P
      tig:
        atl: Enhancing Hypertension Risk Diagnosis Using a Hybrid Machine Learning Framework: Leveraging Body Composition Data.
      aug:
        au:
          Mirzaye, Abdul Wahid
          Saadatfar, Hamid
          Nematollahi, Mohammad Ali
          Banerjee, Baisakhi
        affil: Department of Computer Engineering,, Faculty of Electrical and Computer Engineering,, University of Birjand,, Birjand, Iran, birjand.ac.ir
      sug:
        subj:
          Hypertension Diagnosis
          Hypertension Risk Factors
          Machine Learning
          Body Composition
          Risk Assessment
          Predictive Value of Tests
          Iran
          Human
          Male
          Female
          Adult
          Middle Age
          Aged
          Descriptive Statistics
          ROC Curve
          Paired T-Tests
          Post Hoc Analysis
          Decision Trees
          Random Forest
          Boosting Machine Learning Algorithms
          Logistic Regression
          Methodological Research
          Analysis of Variance
          Age Factors
          Sex Factors
          Cluster Analysis
          Reproducibility of Results
          Sensitivity and Specificity
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Aged: 65+ years
          Male
          Female
      ab: Hypertension, widely recognized as the "silent killer," remains a leading cause of cardiovascular, renal, and neurological complications worldwide. This study proposes a dual‐scenario hybrid machine learning framework for hypertension risk prediction using noninvasive body composition features, aimed at enhancing both interpretability and predictive reliability. In Scenario 1, an unsupervised clustering analysis inspired by self‐labeling principles was performed exclusively on hypertensive individuals, where five physiological subgroups were identified via K‐Means clustering and validated using Silhouette (0.3371), Davies–Bouldin (1.0094), and Calinski–Harabasz (720.10) indices. Significant intercluster variability (p < 0.001) was observed across key indicators such as FATP, RLFATP, LLFATP, FATM, and age. Among the tested models, the support vector machine (SVM) with random oversampling achieved the best performance (accuracy = 99.08%, F1 = 98.04%, AUC = 99.98%), confirming effective subgroup discrimination. In Scenario 2, a comprehensive binary classification between healthy and hypertensive subjects was conducted using five models—ExtraTrees, KNN, SVM, Gaussian Naive Bayes, and Decision Tree—across multiple configurations. The cluster‐augmented dataset yielded the best results, with the ExtraTrees classifier achieving superior performance (accuracy = 98.23%, recall = 98.30%, precision = 98.17%, F1 = 98.23%, AUC = 99.87%). Clustering and feature selection both improved generalization, particularly for ensemble‐based learners. Overall, Scenario 2 demonstrated the highest predictive accuracy and stability, whereas Scenario 1 provided valuable interpretability through subgroup discovery. These findings highlight that integrating unsupervised clustering with supervised classification offers a robust and explainable framework for personalized hypertension risk prediction, contributing to early detection and precision healthcare.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N