基于HeAR模型的多任务框架，提升儿童呼吸音诊断准确性。
PulmoVec: A Two-Stage Stacking Meta-Learning Architecture Built on the HeAR Foundation Model for Multi-Task Classification of Pediatric Respiratory Sounds
- 用HeAR基础模型+堆叠元学习，实现呼吸音多任务分类。
- 事件级最高AUC达0.96，患者级疾病分类准确率74%。
- 适合儿科呼吸疾病智能辅助诊断研究者参考。
呼吸系统疾病是儿童发病率和死亡率的主要原因，但肺部听诊仍存在主观性强、听者间差异大的问题，尤其在儿科人群中更为显著。现有AI方法受限于小样本数据集和单任务设计。我们开发了PulmoVec，一个基于健康声学表征（HeAR）基础模型的多任务框架，用于儿童呼吸音分类。回顾性分析SPRSound数据库中1,652名患儿的24,808段事件级标注片段，训练了三个针对筛查、声音模式识别和疾病分组预测的任务特异性分类器。其交叉验证概率输出与人口统计学特征一起输入轻量梯度提升机（LightGBM）堆叠元模型，并通过集成投票将事件级预测聚合至患者层面。结果显示，在事件级，筛查模型的ROC-AUC为0.96（95% CI, 0.95–0.97），声音模式识别模型宏ROC-AUC为0.96（95% CI, 0.96–0.97），疾病分组预测模型宏ROC-AUC为0.94（95% CI, 0.93–0.94）。在患者级，疾病分组分类准确率为0.74（95% CI, 0.71–0.77），加权F1得分为0.73，宏ROC-AUC为0.91（95% CI, 0.90–0.93）。堆叠架构在所有任务上均优于基线模型。结论：PulmoVec实现了事件级声学表型与患者级临床分类的联动，展现了基于基础模型的数字听诊在儿科呼吸医学中的潜力。跨中心外部验证在不同设备和真实场景下仍至关重要。
原文摘要 · Abstract (English)
Background: Respiratory diseases are a leading cause of childhood morbidity and mortality, yet lung auscultation remains subjective and limited by inter-listener variability, particularly in pediatric populations. Existing AI approaches are further constrained by small datasets and single-task designs. We developed PulmoVec, a multi-task framework built on the Health Acoustic Representations (HeAR) foundation model for classification of pediatric respiratory sounds. Methods: In this retrospective analysis of the SPRSound database, 24,808 event-level annotated segments from 1,652 pediatric patients were analyzed. Three task-specific classifiers were trained for screening, sound-pattern recognition, and disease-group prediction. Their out-of-fold probability outputs were combined with demographic metadata in a LightGBM stacking meta-model, and event-level predictions were aggregated to the patient level using ensemble voting. Results: At the event level, the screening model achieved an ROC-AUC of 0.96 (95% CI, 0.95-0.97), the sound-pattern recognition model a macro ROC-AUC of 0.96 (95% CI, 0.96-0.97), and the disease-group prediction model a macro ROC-AUC of 0.94 (95% CI, 0.93-0.94). At the patient level, disease-group classification yielded an accuracy of 0.74 (95% CI, 0.71-0.77), a weighted F1-score of 0.73, and a macro ROC-AUC of 0.91 (95% CI, 0.90-0.93). Stacking improved performance across all tasks compared with base models alone. Conclusions: PulmoVec links event-level acoustic phenotyping with patient-level clinical classification, supporting the potential of foundation-model-based digital auscultation in pediatric respiratory medicine. Multi-center external validation across devices and real-world conditions remains essential.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。