Columbia University Medical Center, New York, NY, United States of America; School of Nursing, Columbia University, New York, NY, United States of America.
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.
Artif Intell Med. 2023 Sep;143:102624. doi: 10.1016/j.artmed.2023.102624. Epub 2023 Jul 17.
Alzheimer's disease and related dementias (ADRD) present a looming public health crisis, affecting roughly 5 million people and 11 % of older adults in the United States. Despite nationwide efforts for timely diagnosis of patients with ADRD, >50 % of them are not diagnosed and unaware of their disease. To address this challenge, we developed ADscreen, an innovative speech-processing based ADRD screening algorithm for the protective identification of patients with ADRD. ADscreen consists of five major components: (i) noise reduction for reducing background noises from the audio-recorded patient speech, (ii) modeling the patient's ability in phonetic motor planning using acoustic parameters of the patient's voice, (iii) modeling the patient's ability in semantic and syntactic levels of language organization using linguistic parameters of the patient speech, (iv) extracting vocal and semantic psycholinguistic cues from the patient speech, and (v) building and evaluating the screening algorithm. To identify important speech parameters (features) associated with ADRD, we used the Joint Mutual Information Maximization (JMIM), an effective feature selection method for high dimensional, small sample size datasets. Modeling the relationship between speech parameters and the outcome variable (presence/absence of ADRD) was conducted using three different machine learning (ML) architectures with the capability of joining informative acoustic and linguistic with contextual word embedding vectors obtained from the DistilBERT (Bidirectional Encoder Representations from Transformers). We evaluated the performance of the ADscreen on an audio-recorded patients' speech (verbal description) for the Cookie-Theft picture description task, which is publicly available in the dementia databank. The joint fusion of acoustic and linguistic parameters with contextual word embedding vectors of DistilBERT achieved F1-score = 84.64 (standard deviation [std] = ±3.58) and AUC-ROC = 92.53 (std = ±3.34) for training dataset, and F1-score = 89.55 and AUC-ROC = 93.89 for the test dataset. In summary, ADscreen has a strong potential to be integrated with clinical workflow to address the need for an ADRD screening tool so that patients with cognitive impairment can receive appropriate and timely care.
阿尔茨海默病和相关痴呆症（ADRD）是一个迫在眉睫的公共卫生危机，影响了美国约 500 万人和 11%的老年人。尽管全美都在努力及时诊断 ADRD 患者，但仍有超过 50%的患者未被诊断，也不知道自己患有该病。为了解决这一挑战，我们开发了 ADscreen，这是一种基于语音处理的创新 ADRD 筛查算法，用于保护 ADRD 患者的身份识别。ADscreen 由五个主要组成部分组成：（i）降低背景噪音，以减少从患者语音录制中录制的背景噪音，（ii）使用患者声音的声学参数来模拟患者在语音运动规划方面的能力，（iii）使用患者语音的语言学参数来模拟患者在语义和句法语言组织方面的能力，（iv）从患者语音中提取语音和语义心理语言学线索，以及（v）构建和评估筛查算法。为了识别与 ADRD 相关的重要语音参数（特征），我们使用了联合互信息最大化（JMIM），这是一种有效的高维小样本数据集特征选择方法。使用具有将信息丰富的声学和语言学与从 DistilBERT（来自 Transformer 的双向编码器表示）获得的上下文单词嵌入向量结合的能力的三种不同机器学习（ML）架构来构建语音参数与结果变量（ADRD 存在/不存在）之间的关系。我们在可公开获取的痴呆症数据库中的 Cookie-Theft 图片描述任务中对患者语音（口头描述）的音频记录进行了 ADscreen 性能评估。联合融合声学和语言学参数与 DistilBERT 的上下文单词嵌入向量，在训练数据集上实现了 F1 得分为 84.64（标准差 [std]为 ±3.58）和 AUC-ROC 为 92.53（std 为 ±3.34），在测试数据集上实现了 F1 得分为 89.55 和 AUC-ROC 为 93.89。总之，ADscreen 具有很强的潜力与临床工作流程相结合，以满足对 ADRD 筛查工具的需求，以便认知障碍患者能够获得适当和及时的护理。
