A test commonly used to diagnose aphasia is helping researchers detect early signs of Alzheimer’s disease. While their findings have no impact on aphasia caused by a stroke or traumatic brain injury, the research could be of interest to people diagnosed with primary progressive aphasia (PPA). Alzheimer’s disease is not PPA, and in the past, we’ve outline the differences. But both are neurological diseases that include the deterioration of brain tissue.

How an Aphasia Test Played a Role

Psychology Today reported on the study being conducted in partnership between IBM Research and Pfizer. Researchers are using linguistics (the study of language) “as a marker for early detection of Alzheimer’s disease.”


To train the machines to detect those language changes, the researchers used data collected from the Framingham Heart Study, which included the use of the Boston Aphasia Diagnostic Examination—”a widely used cognitive test used to assess aphasia, a disorder that impairs speech and communication abilities, and increasingly for dementia as well.”


Researchers culled out a group of 80 from the study, looking at 40 individuals who went on to develop Alzheimer’s disease and 40 who did not, though all were cognitively normal during the data collection period. Differences in linguistic activity helped the researchers to train the machine to detect certain markers.

Amazing Results

The researchers found that “the machine learning model could predict Alzheimer’s disease with 70 percent accuracy when using linguistic variables.”


Moreover, “scientists have opened the door to the possibility of non-invasive, easy-to-administer diagnostic tests based on linguistics for early detection of Alzheimer’s disease in the future.”


At this stage, we don’t yet have information on whether this algorithm could also predict or diagnose PPA, or whether the research could be applied to other neurodegenerative disorders in a future study.