The Auditory Brainstem Response Diagnoses Alzheimer-Like Disease in the 5xFAD Mouse Model

Area of Science:

• Neuroscience
• Biomarkers
• Machine Learning

Background:

• Early Alzheimer's disease (AD) diagnosis is crucial for personalized treatment.
• Auditory processing deficits are common in mild cognitive impairment, a precursor to AD.
• The diagnostic potential of auditory processing for AD remains underexplored.

Purpose of the Study:

• To investigate the efficacy of auditory brainstem response (ABR) measurements as a diagnostic biomarker for early-stage Alzheimer's disease (AD).
• To explore the utility of machine learning algorithms in interpreting ABR data for AD diagnosis.
• To identify potential neural correlates of auditory deficits in AD.

Main Methods:

• Utilized amyloidosis mouse models exhibiting memory decline.
• Recorded auditory brainstem responses (ABR) to auditory stimuli.
• Applied machine learning algorithms to ABR data for disease diagnosis.
• Conducted histological analyses to correlate neural changes with behavioral and auditory findings.

Main Results:

• Machine learning successfully diagnosed disease based on ABR changes in mice with amyloidosis and memory decline.
• Analysis indicated that upper auditory pathway structures, such as the inferior colliculus, are likely sources of auditory defects.
• Neuroinflammation and plaque deposition in these regions correlated temporally with memory loss.

Conclusions:

• Auditory brainstem response (ABR) measurements show promise as a rapid, low-cost, noninvasive biomarker for early Alzheimer's disease (AD) detection.
• Machine learning interpretation of ABR data can facilitate reliable AD diagnosis.
• Further evaluation of ABR as an adjunct diagnostic tool for early-stage AD is warranted.