Researchers from IBM and Pfizer have published details on a new AI model that interprets written speech, which they claim can predict whether a person will develop Alzheimer's seven years before they show symptoms. The idea is attractive for its simplicity: The model's only input is a written sample from the "cookie-theft picture description task," a common cognitive test that asks participants to describe what's happening in a drawing (three guesses what the drawing is of). Researchers trained the AI to pore over participants' responses, picking up on hints of cognitive decline like repetition, misspellings, two-word sentences, and limited vocabulary. Now, hold your applause: The model is in early days, and it isn't any better than current cognitive assessments. The initial study--based on data gathered from just 270 Americans over the course of four decades--showed the AI could predict a future Alzheimer's diagnosis 70% of the time.

Alzheimer's is a crippling degenerative disease, but the answer to early diagnosis might lie in speech. I was afraid my grandmother wouldn't remember who I was the last time I saw her in person. She looked small and frail in the wheelchair but I could still see the sparkle in her eyes. Our relationship was complicated, but when she said she remembered me, none of it mattered any more. I sat by her wheelchair and tried to cram in a decade of memories and happenings.

Artificial intelligence could soon help screen for Alzheimer's disease by analyzing writing. A team from IBM and Pfizer says it has trained AI models to spot early signs of the notoriously stealthy illness by looking at linguistic patterns in word usage. Other researchers have already trained various models to look for signs of cognitive impairments, including Alzheimer's, by using different types of data, such as brain scans and clinical test results. But the latest work stands out because it used historical information from the multigenerational Framingham Heart Study, which has been tracking the health of more than 14,000 people from three generations since 1948. If the new models' ability to pick up trends in such data holds up in forward-looking studies of bigger and more diverse populations, researchers say they could predict the development of Alzheimer's a number of years before symptoms become severe enough for typical diagnostic methods to pick up.