Researchers at Boston University have developed an artificial intelligence tool that can predict with almost 80% accuracy whether someone is at risk for developing Alzheimer’s disease based on their speech patterns. This tool could potentially help identify cognitive decline early and mitigate the progression of the disease. However, the sample size used in the study was small, and experts caution that the tool should not be relied upon as the sole method for predicting Alzheimer’s.
The AI tool developed by the Boston University researchers analyzed speech patterns of 166 participants between the ages of 63 and 97 who had cognitive complaints. By combining speech-recognition tools and machine learning, the researchers were able to track connections between speech patterns and cognitive decline, based on biomarkers associated with cognitive decline. The model they developed was able to predict significant cognitive decline with 78.5% accuracy, showing promising results for the future use of such technology.
Dementia affects more than 55 million people worldwide, with up to 70% of those cases being Alzheimer’s disease. The disease is characterized by a loss of brain cells due to the toxic buildup of proteins, amyloid and tau. Common symptoms include memory loss, cognitive deficits, problems with speaking, recognition, spatial awareness, reading, or writing, and changes in personality and behavior. With no cure, treatment involves medication, lifestyle changes, and support groups for patients and caregivers.
Using artificial intelligence to detect Alzheimer’s early offers doctors and patients more options than currently available. Early intervention can slow the disease progression, provide automated and remote screening for cognitive assessments, and create personalized care plans based on predicted disease trajectories. This technology can help healthcare providers prioritize patients needing intensive monitoring, optimize resource allocation, and enhance predictive models and treatment strategies.
Although the 80% accuracy rate of the AI tool is high, there is still the potential for false positives or negatives, which could lead to undue stress or false reassurance for patients. Automating healthcare with AI tools may create issues if clinicians rely solely on predictions without considering the broader clinical context, potentially resulting in misdiagnoses. Therefore, caution is needed when using such tools to ensure they are not the sole method for predicting cognitive decline or disease progression.
While the accuracy rate of the AI tool developed by Boston University researchers is promising, experts emphasize that the tool should not be used in isolation. It should be combined with other methods, such as blood tests, to provide a more accurate and holistic picture of an individual’s cognitive health. Monitoring speech patterns over time can help establish individual baselines to understand what is normal and abnormal for a person, allowing for more personalized and effective interventions to manage the risk of developing Alzheimer’s disease.
