文献速递认知障碍与痴呆

基层诊疗对话声学分析用于认知障碍筛查

Acoustic Analysis of Primary Care Patient-Clinician Conversations to Screen for Cognitive Impairment.
PubMed 文献 · JAMA Neurol · 2026-01-01

该诊断研究纳入966名55岁及以上、无痴呆或轻度认知障碍记录的患者,对基层门诊医患对话录音提取30秒语音片段的声学特征并用机器学习识别认知障碍。基于Whisper特征的模型表现最佳,AUROC为0.733,外部验证结果相似;用于筛查时灵敏度68.2%、特异度63.6%。

要点

  • 常规基层门诊对话录音可被动提取声学特征用于认知障碍筛查。
  • Whisper衍生特征模型表现最佳,外部验证AUROC为0.727。
  • 筛查灵敏度68.2%、特异度63.6%,阳性预测值30.4%。

核心结论

  • 机器学习模型基于简短临床对话的声学特征可识别认知障碍,支持在基层诊疗中开展被动语音筛查的可行性。

主要发现

  • Whisper衍生声学特征模型表现最佳,AUROC 0.733(95%CI 0.714-0.752),Fmax[CI] 0.502(95%CI 0.471-0.533)。
  • 外部验证性能相似,AUROC 0.727(95%CI 0.714-0.740),Fmax[CI] 0.459(95%CI 0.441-0.477)。
  • 模型解释显示音高、时序和变异性特征为关键预测因子。
  • 筛查时阳性预测值30.4%(95%CI 28.7%-32.1%),灵敏度68.2%(95%CI 61.8%-74.6%),特异度63.6%(95%CI 59.8%-67.4%)。

关键数值与推荐

  • 认知障碍定义:蒙特利尔认知评估得分低于年龄和教育校正常模1.0个标准差或以上。
  • 认知障碍患病率为21%。

临床怎么用

  • 在基层门诊常规问诊中可被动录音并提取声学特征辅助识别认知障碍高危患者。
  • 筛查阳性者仍需进一步认知评估确认,因阳性预测值有限。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

IMPORTANCE: Cognitive impairment (CI) is often underdetected in primary care due to time and resource constraints. Passive analysis of clinical dialogue may offer an accessible approach for screening. OBJECTIVE: To assess whether audio recordings of patient-physician dialogue during routine primary care visits can be used to identify CI using acoustic speech features and machine learning (ML). DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study, conducted from August 2020 through December 2021 among older primary care patients, involved audio recording primary care visits using a microphone and portable device. An external validation cohort was recruited in a separate city to assess reproducibility of findings. Analysis was performed from January 2025 through June 2025. The study was conducted in primary care practices in New York, New York, with additional participants recruited from primary care practices in Chicago, Illinois, for validation. Eligible patients were recruited from primary care practices during routine visits with no prior diagnosis of mild CI or dementia. The study included English-speaking patients aged 55 years and older without documented history of dementia or mild CI. For validation, patients meeting the same eligibility criteria were recruited from primary care practices in Chicago. EXPOSURE: Multiple 30-second speech segments were extracted from recordings. Acoustic features were derived using foundation models (Whisper, HuBERT, wav2vec 2.0) and expert-defined methods (eGeMAPS, prosody). MAIN OUTCOMES AND MEASURES: The primary outcome, CI, was defined as Montreal Cognitive Assessment score 1.0 or more standard deviations below age- and education-adjusted norms. ML classifiers were trained to predict CI status from audio recordings. Area under the receiver operating characteristic curve (AUROC) and maximum F1 score (Fmax) were calculated for identifying participants with CI. RESULTS: The study included 787 English-speaking patients aged 55 years and older without documented history of dementia or mild CI and an additional 179 patients meeting the same eligibility criteria for validation. In total, 966 participants were recruited, among whom 530 (55%) were female, mean (SD) age was 67.2 (8.1) years, and CI prevalence was 21%. Models using Whisper-derived acoustic features performed best (AUROC, 0.733; 95% CI, 0.714-0.752; Fmax[CI], 0.502; 95% CI, 0.471-0.533). Results generalized to the external site with similar performance (AUROC, 0.727; 95% CI, 0.714-0.740; Fmax[CI], 0.459; 95% CI, 0.441-0.477). Model interpretation identified pitch, timing, and variability features as key predictors. When used for screening, the algorithm achieved positive predictive value of 30.4% (95% CI, 28.7%-32.1%), sensitivity of 68.2% (95% CI, 61.8%-74.6%), and specificity of 63.6% (95% CI, 59.8%-67.4%) on the holdout cohort. CONCLUSIONS AND RELEVANCE: In this diagnostic study, ML models trained on acoustic features from brief clinical conversations identified CI with high accuracy. These findings support the feasibility of passive, speech-based screening during routine primary care.

来源:JAMA Neurol,查看原文。版权归原作者所有。

引用

  1. Colonel JT, Becker J, Chan L, et al. Acoustic Analysis of Primary Care Patient-Clinician Conversations to Screen for Cognitive Impairment. JAMA Neurol. 2026. PMID: 42295801. doi:10.1001/jamaneurol.2026.1868

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。