发表机构
Luxembourg Institute of Health（卢森堡健康研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对哮喘诊断依赖传统方法、声音生物标志物缺乏临床背景整合的问题，提出多模态专家混合框架，结合声学嵌入与临床人口数据，在匹配队列上评估，模型性能优，还通过分析揭示不同症状个体特征依赖差异，支持哮喘筛查。
AI 中文摘要
哮喘在全球影响超过2.6亿人，但其诊断仍依赖肺活量测定和专家评估，限制了初级保健和资源匮乏地区的可及性。声音生物标志物提供了一种有前景的非侵入性替代方法，但先前研究大多聚焦声学特征而未整合临床背景。我们提出了一种用于哮喘检测的多模态专家混合框架，它将持续元音发声和阅读段落任务的声学嵌入与结构化临床和人口统计学数据自适应结合。该模型在来自Colive Voice研究的1218例哮喘病例和健康对照的匹配队列上进行评估。多模态模型的AUROC为0.85，Brier评分为0.17，优于单模态和双模态方法。自适应门控分析显示，呼吸症状负担较重的参与者对音频特征的依赖增加，而临床特征在症状较轻的个体中贡献更大。这些发现支持使用智能手机收集的语音记录进行可扩展且可解释的哮喘筛查。
英文摘要
Asthma affects over 260 million people worldwide, yet diagnosis remains dependent on spirometry and specialist assessment, limiting accessibility in primary care and low-resource settings. Vocal biomarkers offer a promising non-invasive alternative, but prior studies have largely focused on acoustic features without integrating clinical context. We present a multimodal Mixture-of-Experts framework for asthma identification that adaptively combines acoustic embeddings from sustained vowel phonation and reading passage tasks with structured clinical and demographic data. The model was evaluated on a matched cohort of 1,218 self-reported asthma cases and healthy controls from the Colive Voice study. The multimodal model achieved an AUROC of 0.83 and Brier score of 0.18, outperforming unimodal approaches. Exploratory analysis of the gating mechanism in asthma cases showed that greater respiratory symptom burden was associated with increased weighting of reading-passage modality and reduced weighting of sustained-vowel phonation modality. These findings support the feasibility of voice-based identification of self-reported asthma; however, independent prospective validation remains necessary before clinical use.
