Summary of Voice Dataset Used for ML.

Recent developments in artificial intelligence (AI) have introduced new technologies that can aid in detecting cognitive decline. This study developed a voice-based AI model that screens for cognitive decline using only a short conversational voice sample. The process involved collecting voice samples, applying machine learning (ML), and confirming accuracy through test data. The AI model extracts multiple voice features from the collected voice data to detect potential signs of cognitive impairment. Data labeling for ML was based on Mini-Mental State Examination scores: scores of 23 or lower were labeled as “cognitively declined (CD),” while scores above 24 were labeled as “cognitively normal (CN).” A fully coupled neural network architecture was employed for deep learning, using voice samples from 263 patients. Twenty voice samples, each comprising a one-minute conversation, were used for accuracy evaluation. The developed AI model achieved an accuracy of 0.950 in discriminating between CD and CN individuals, with a sensitivity of 0.875, specificity of 1.000, and an average area under the curve of 0.990. This voice AI model shows promise as a cognitive screening tool accessible via mobile devices, requiring no specialized environments or equipment, and can help detect CD, offering individuals the opportunity to seek medical attention.人工智能（Artificial Intelligence，AI）领域的最新进展催生了可辅助认知衰退检测的新型技术。本研究开发了一款基于语音的人工智能模型，仅通过简短的会话语音样本即可筛查认知衰退状况。该研究流程涵盖语音样本采集、机器学习（Machine Learning，ML）应用，以及通过测试数据验证模型准确性。该人工智能模型从采集的语音数据中提取多维度语音特征，以识别认知功能受损的潜在征兆。机器学习的标签标注基于简易精神状态检查表（Mini-Mental State Examination，MMSE）得分：得分≤23分的样本被标注为"认知衰退组（Cognitively Declined，CD）"，得分＞24分的样本则被标注为"认知正常组（Cognitively Normal，CN）"。本研究采用全耦合神经网络架构开展深度学习，共使用了263名患者的语音样本。另外选取20份每份时长为1分钟的会话语音样本用于模型准确性评估。所开发的人工智能模型在区分认知衰退组与认知正常组个体时，准确率达到0.950，灵敏度为0.875，特异度为1.000，平均曲线下面积为0.990。该语音人工智能模型具备成为可通过移动设备访问的认知筛查工具的潜力，无需专用环境或设备即可使用，能够辅助检测认知衰退，为患者提供及时就医的契机。