What happened
Worcester Polytechnic Institute (WPI) researchers, led by Assistant Research Professor Ben Nephew, developed an AI model predicting Alzheimer's disease with 93% accuracy. The team analysed more than 800 brain scans from individuals aged 69 to 84, encompassing healthy subjects, those with mild cognitive impairment, and diagnosed Alzheimer's patients. This AI specifically improved differentiation of mild cognitive impairment, a stage where symptoms are less severe, from healthy individuals. The research, published in the journal Neuroscience, aims to inform clinical decisions and advance personalised medicine, rather than making direct diagnoses.
Why it matters
Early Alzheimer's detection offers a critical window for effective treatment and personalised prevention strategies. For healthcare providers and medical researchers, this AI's 93% accuracy in identifying mild cognitive impairment provides a mechanism to inform clinical pathways before severe symptoms manifest. While not a diagnostic tool, its capability to differentiate early-stage cognitive decline from healthy ageing could refine patient stratification for trials and interventions. Founders in health tech should note the emphasis on informing, not replacing, clinical judgment, shaping future AI-assisted diagnostic support systems.
Subscribe for Weekly Updates
Stay ahead with our weekly AI and tech briefings, delivered every Tuesday.
