Explainable Alzheimer's Disease Detection Using Linguistic Features from Automatic Speech Recognition.

INTRODUCTION: Alzheimer's disease (AD) is the most prevalent type of dementia and can cause abnormal cognitive function and progressive loss of essential life skills. Early screening is thus necessary for the prevention and intervention of AD. Speech dysfunction is an early onset symptom of AD patients. Recent studies have demonstrated the promise of automated acoustic assessment using acoustic or linguistic features extracted from speech. However, most previous studies have relied on manual transcription of text to extract linguistic features, which weakens the efficiency of automated assessment. The present study thus investigates the effectiveness of automatic speech recognition (ASR) in building an end-to-end automated speech analysis model for AD detection. METHODS: We implemented three publicly available ASR engines and compared the classification performance using the ADReSS-IS2020 dataset. Besides, the SHapley Additive exPlanations algorithm was then used to identify critical features that contributed most to model performance. RESULTS: Three automatic transcription tools obtained mean word error rate texts of 32%, 43%, and 40%, respectively. These automated texts achieved similar or even better results than manual texts in model performance for detecting dementia, achieving classification accuracies of 89.58%, 83.33%, and 81.25%, respectively. CONCLUSION: Our best model, using ensemble learning, is comparable to the state-of-the-art manual transcription-based methods, suggesting the possibility of an end-to-end medical assistance system for AD detection with ASR engines. Moreover, the critical linguistic features might provide insight into further studies on the mechanism of AD.

Delayed inhibition of ERK and p38 attenuates neuropathic pain without affecting motor function recovery after peripheral nerve injury.

Peripheral nerve injuries (PNIs) often result in persistent neuropathic pain, seriously affecting quality of life. Existing therapeutic interventions for PNI-induced neuropathic pain are far from satisfactory. Extracellular signal-regulated kinases (ERKs) and p38 have been found to participate in triggering and maintaining PNI-induced neuropathic pain. However, ERK and p38 also contribute to axonal regeneration and motor function recovery after PNI, making it difficult to inhibit ERK and p38 for therapeutic purposes. In this study, we simultaneously characterized neuropathic pain and motor function recovery in a mouse sciatic nerve crush injury model to identify the time window for therapeutic interventions. We further demonstrated that delayed delivery of a combination of ERK and p38 inhibitors at three weeks after PNI could significantly alleviate PNI-induced neuropathic pain without affecting motor function recovery. Additionally, the combined use of these two inhibitors could suppress pain markedly better than either inhibitor alone, possibly reducing the required dose of each inhibitor and alleviating the side effects and risks of the inhibitors when used individually.