[论文解读] Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics

Yue Pan, Xingyao Wang+7 more|arXiv (Cornell University)|Feb 23, 2026

Phonocardiography and Auscultation Techniques被引用 0

一句话总结

论文引入 Longitudinal Intra-Patient Tracking (LIPT) 与 Personalised Sequential Encoder (PSE) 以通过语音监测心力衰竭，并在HF轨迹检测和恶化预测方面超越横截面方法。

ABSTRACT

Remote monitoring of heart failure (HF) via speech signals provides a non-invasive and cost-effective solution for long-term patient management. However, substantial inter-individual heterogeneity in vocal characteristics often limits the accuracy of traditional cross-sectional classification models. To address this, we propose a Longitudinal Intra-Patient Tracking (LIPT) scheme designed to capture the trajectory of relative symptomatic changes within individuals. Central to this framework is a Personalised Sequential Encoder (PSE), which transforms longitudinal speech recordings into context-aware latent representations. By incorporating historical data at each timestamp, the PSE facilitates a holistic assessment of the clinical trajectory rather than modelling discrete visits independently. Experimental results from a cohort of 225 patients demonstrate that the LIPT paradigm significantly outperforms the classic cross-sectional approaches, achieving a recognition accuracy of 99.7% for clinical status transitions. The model's high sensitivity was further corroborated by additional follow-up data, confirming its efficacy in predicting HF deterioration and its potential to secure patient safety in remote, home-based settings. Furthermore, this work addresses the gap in existing literature by providing a comprehensive analysis of different speech task designs and acoustic features. Taken together, the superior performance of the LIPT framework and PSE architecture validates their readiness for integration into long-term telemonitoring systems, offering a scalable solution for remote heart failure management.

研究动机与目标

• 解决基于语音的HF评估中的个体差异问题。
• 开发纵向跟踪框架以监测患者内的HF轨迹。
• 设计一个 Personalised Sequential Encoder 以编码连续语音历史。
• 在住院HF患者及随访数据队列上验证该方法。

提出的方法

• 从语音任务中提取全局和帧级声学特征。
• 应用统计筛选识别与HF相关的特征（HF-voice A/B）。
• 提出 Longitudinal Intra-Patient Tracking (LIPT) 与 Personalised Sequential Encoder (PSE) 以建模患者内轨迹。
• 训练并比较横截面与纵向模型（XGBoost 和 FNN）在HF状态转移检测中的性能。
• 在多种语音任务（元音、简短句子、长句子）上评估并分析任务有效性。
• 在去代偿状态与治疗后状态以及随访再住院数据上验证该方法。

实验结果

研究问题

• RQ1 纵向建模是否能在从语音估算HF状态方面超越传统横截面方法？
• RQ2 哪些语音任务和特征集合能为HF轨迹跟踪提供最强信号？
• RQ3 Personalised Sequential Encoder 在捕捉患者内时序动态方面有多有效？
• RQ4 LIPT/PSE 方法对随访数据（包括再住院预测）的泛化程度如何？

主要发现

• LIPT 在所有架构上显著优于横截面方法，例如在选定特征集上，横截面准确率约为 69% 而纵向 FNN最高可达 81.8%。
• RASTA 帧级特征取得极高的性能；将 RASTA 与选定的全局特征结合，灵敏度约为 99.8%，特异性约为 99.7%。
• 结合帧级 RASTA 特征的 PSE 达到宏观 F1 为 99.5%（去代偿到治疗后）和 99.7% 的精确度，表明对HF轨迹变化的检测能力很强。
• 在随访评估中，基于 RASTA 的模型能有效识别再住院，AUROC 高达 0.94，然而稳定病例的假阳性率较高，需要进行校准。
• 更长、更全面的语音任务（计数 1–60）提供了最丰富的患者内纵向信息，而元音在临床上具有实用性。
• 该研究支持个性化语音建模以实现可扩展的远程HF监测的可行性，并指出校准与更广泛数据的方向。