Runde Benjamin S, Alapati Ajit, Bazan Nicolas G
Science Engineering Research Center, The Potomac School, McLean, VA 22101, USA.
Neuroscience Center of Excellence, School of Medicine, New Orleans, LA 70112, USA.
Brain Sci. 2024 Feb 25;14(3):211. doi: 10.3390/brainsci14030211.
The development of noninvasive and cost-effective methods of detecting Alzheimer's disease (AD) is essential for its early prevention and mitigation. We optimize the detection of AD using natural language processing (NLP) of spontaneous speech through the use of audio enhancement techniques and novel transcription methodologies. Specifically, we utilized Boll Spectral Subtraction to improve audio fidelity and created transcriptions using state-of-the-art AI services-locally-based Wav2Vec and Whisper, alongside cloud-based IBM Cloud and Rev AI-evaluating their performance against traditional manual transcription methods. Support Vector Machine (SVM) classifiers were then trained and tested using GPT-based embeddings of transcriptions. Our findings revealed that AI-based transcriptions largely outperformed traditional manual ones, with Wav2Vec (enhanced audio) achieving the best accuracy and F-1 score (0.99 for both metrics) for locally-based systems and Rev AI (standard audio) performing the best for cloud-based systems (0.96 for both metrics). Furthermore, this study revealed the detrimental effects of interviewer speech on model performance in addition to the minimal effect of audio enhancement. Based on our findings, current AI transcription and NLP technologies are highly effective at accurately detecting AD with available data but struggle to classify probable AD and mild cognitive impairment (MCI), a prodromal stage of AD, due to a lack of training data, laying the groundwork for the future implementation of an automatic AD detection system.
开发无创且经济高效的阿尔茨海默病（AD）检测方法对于其早期预防和缓解至关重要。我们通过使用音频增强技术和新颖的转录方法，利用自然语言处理（NLP）对自发语音进行优化，以检测AD。具体而言，我们利用博尔谱减法来提高音频保真度，并使用基于本地的Wav2Vec和Whisper以及基于云的IBM Cloud和Rev AI等先进的人工智能服务创建转录文本，同时将它们的性能与传统的人工转录方法进行比较。然后，使用基于GPT的转录嵌入对支持向量机（SVM）分类器进行训练和测试。我们的研究结果表明，基于人工智能的转录在很大程度上优于传统的人工转录，对于基于本地的系统，Wav2Vec（增强音频）在准确率和F1分数方面表现最佳（两项指标均为0.99），而对于基于云的系统，Rev AI（标准音频）表现最佳（两项指标均为0.96）。此外，这项研究揭示了采访者语音对模型性能的不利影响以及音频增强的最小影响。基于我们的研究结果，当前的人工智能转录和NLP技术在利用现有数据准确检测AD方面非常有效，但由于缺乏训练数据，在对可能的AD和轻度认知障碍（MCI，AD的前驱阶段）进行分类时存在困难，这为未来自动AD检测系统的实施奠定了基础。
