A team of researchers at the University of California San Francisco has developed a groundbreaking method using artificial intelligence to detect early signs of Alzheimer’s disease up to seven years before symptoms manifest. This innovative approach, utilizing a tool known as Scalable Precision Medicine Oriented Knowledge Engine (SPOKE), analyzes patterns and molecular targets in patients to identify potential indicators for therapy.
By examining over 5 million electronic health records in the UCSF database, researchers pinpointed 2,996 individuals with Alzheimer’s who had undergone evaluations at the Memory and Aging Center. With expert-level clinical diagnoses, the AI system was able to predict the onset of the disease with 72% accuracy, highlighting the influence of high cholesterol and osteoporosis as key risk factors for Alzheimer’s development.
Lead author Alice Tang, an MD/PhD student at UCSF, emphasized the significance of using AI on routine clinical data to not only detect risk early on but also to gain insights into the underlying biology behind Alzheimer’s. The study outlining these findings was recently published in Nature Aging, shedding light on additional risk factors such as hypertension, vitamin D deficiency, and specific conditions like erectile dysfunction and enlarged prostates in men.
The researchers plan to expand this methodology to identify other diseases like lupus and endometriosis, underscoring the potential of AI in revolutionizing healthcare by predicting and preventing illnesses before they fully manifest.