Published: 2025/12/10 22:50:55

AI Model Shows Promise in Early Alzheimer’s Disease Detection

A new artificial intelligence (AI) model developed by researchers at the University of California,San Francisco (UCSF) demonstrates significant potential in identifying individuals at higher risk of developing Alzheimer’s disease. The model analyzes electronic health record data too predict the likelihood of an Alzheimer’s diagnosis, potentially enabling earlier intervention adn improved patient outcomes.

How the AI Model Works

The UCSF team trained the AI model using data from over 16,000 patients within the University of California Health system. The model considers a range of factors present in electronic health records, including demographics, diagnoses, medications, and laboratory results, to assess an individual’s risk. Unlike conventional diagnostic methods that frequently enough rely on cognitive testing and brain imaging after symptoms appear, this AI model aims to identify risk before significant cognitive decline occurs. The research was originally published in December 2023.

The Importance of early Detection

Early identification of Alzheimer’s risk is becoming increasingly critical with the advancements in Alzheimer’s treatments. New therapies, such as anti-amyloid antibodies like lecanemab (Leqembi) and donanemab, are most effective when administered in the early stages of the disease, before extensive brain damage has occurred. Lifestyle interventions, including diet, exercise, and cognitive training, can also play a role in slowing disease progression when implemented early.

“The ability to identify high-risk individuals proactively allows clinicians to offer more timely evaluations and consider preventative strategies,” explains Dr. Chi-Hua Chang, a lead researcher on the project and a professor of clinical pharmacy at UCSF. “This is particularly crucial as we see more disease-modifying treatments become available.”

addressing Disparities in Diagnosis

A key focus of the research is to address the significant underdiagnosis of Alzheimer’s disease in underrepresented populations. Studies have shown that racial and ethnic minorities are ofen diagnosed later in the disease process, limiting their access to potentially beneficial treatments. the UCSF model is designed to ensure equitable predictions across diffrent demographic groups, potentially reducing these disparities.

“by ensuring equitable predictions across populations,our model can help remedy significant underdiagnosis in underrepresented populations,” Chang said. “It has the potential to address disparities in alzheimer’s diagnosis.”

Next Steps: Validation and Implementation

The research team is now working to validate the model prospectively in partnering health systems. This involves testing the model’s performance on new data to assess its generalizability and clinical utility in real-world settings. Triumphant validation will pave the way for potential implementation of the AI tool in routine clinical care.

Key Takeaways

• An AI model developed by UCSF can predict Alzheimer’s risk using electronic health record data.
• Early detection is crucial for maximizing the benefits of new Alzheimer’s treatments and lifestyle interventions.
• The model aims to address disparities in Alzheimer’s diagnosis among underrepresented populations.
• Further validation is underway to assess the model’s performance in diverse healthcare settings.