The voice of decompensation: an explainable machine learning approach to assessing heart failure severity.

Aims Heart failure (HF) is characterized by high morbidity and frequent hospital readmissions, highlighting the need for scalable out-of-hospital monitoring to support post-discharge nursing care. We aimed to (i) develop a HF-tailored, user-friendly voice task set suitable for remote monitoring; (ii...

Descripción completa

Detalles Bibliográficos
Publicado en:European Journal of Cardiovascular Nursing Vol. 25; no. 3; pp. 607 - 617
Autores principales: Yang, Yi, Zhao, Bochao, Ying, Dire, Han, Ping, Wang, Ying, Liu, Keyao, Gao, Zhenyue, Zhang, Sen, Xiao, Wendong, Wan, Qiaoqin
Formato: pictorial research tables/charts Journal Article
Publicado: Oxford University Press / USA Apr2026
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=195378296&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 195378296
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        14745151
        KJC
      jtl: European Journal of Cardiovascular Nursing
      issn: 14745151
      maglogo: N
    pubinfo:
      dt: Apr2026
      vid: 25
      iid: 3
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        195378296
        195378296
        195378296
        10.1093/eurjcn/zvag003
        195378296
      ppf: 607
      ppct: 10
      formats:
      tig:
        atl: The voice of decompensation: an explainable machine learning approach to assessing heart failure severity.
      aug:
        au:
          Yang, Yi
          Zhao, Bochao
          Ying, Dire
          Han, Ping
          Wang, Ying
          Liu, Keyao
          Gao, Zhenyue
          Zhang, Sen
          Xiao, Wendong
          Wan, Qiaoqin
        affil: School of Nursing, Peking University, No. 38, Xueyuan Road, Haidian District, Beijing 100083, China
      sug:
        subj:
          Heart Failure Diagnosis
          Severity of Illness Evaluation
          Machine Learning Utilization
          Telemetry
          Smartphone Utilization
          Speech Acoustics
          Task Performance and Analysis
          Human
          Funding Source
          China
          Tertiary Health Care
          Male
          Female
          Middle Age
          Aged
          Aged, 80 and Over
          Multicenter Studies
          Nonexperimental Studies
          Audiorecording
          Descriptive Statistics
          ROC Curve
          Sensitivity and Specificity
          Boosting Machine Learning Algorithms
          Pearson's Correlation Coefficient
          Spearman's Rank Correlation Coefficient
          Paired T-Tests
          Wilcoxon Rank Sum Test
          Data Analysis Software
          Cardiovascular Nursing
          Middle Aged: 45-64 years
          Aged: 65+ years
          Aged, 80 & over
          Male
          Female
      ab: Aims Heart failure (HF) is characterized by high morbidity and frequent hospital readmissions, highlighting the need for scalable out-of-hospital monitoring to support post-discharge nursing care. We aimed to (i) develop a HF-tailored, user-friendly voice task set suitable for remote monitoring; (ii) identify HF-related acoustic markers and build explainable voice-based models; and (iii) evaluate the accuracy of smartphone recordings for clinical monitoring. Methods and results In this multicentre observational study, patients hospitalized with acute heart failure (AHF) were recruited at four centres. Voice recordings were obtained with professional devices and common smartphones (Apple, Huawei, Vivo). Eleven speech tasks were evaluated, and 11 acoustic feature categories were extracted [e.g. Mel frequency cepstrum coefficients (MFCCs), chroma, spectral, glottal features]. Two XGBoost models were trained to classify clinical status from admission to discharge and from mid-hospitalization to discharge; models were interpreted with Shapley Additive Explanations (SHAP). Four tasks were selected for the final model. The admission-to-discharge model achieved 0.76 accuracy, 0.86 sensitivity, 0.65 specificity, and an area under the ROC curve (AUC) of 0.77. The mid-hospitalization-to-discharge model showed 0.81 accuracy, 0.89 sensitivity, 0.71 specificity, and an AUC of 0.80. Shapley Additive Explanations analysis revealed vocal improvements corresponding to clinical recovery, characterized by transitions from unstable, noisy voice patterns to more stable, harmonic-rich, brighter, and stronger vocal expressions. Cross-device comparison demonstrated high consistency among recordings across different smartphone brands, supporting the feasibility of mobile-based voice data collection. Conclusion We developed an explainable, high-performing voice-based HF monitoring model deployable via smartphones. The approach is non-invasive, low-burden, and feasible for integration into nurse-coordinated post-discharge monitoring and remote triage.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N