AI Tool Predicts Alzheimer's More Than 6 Years Ahead of Diagnosis

A study published in Radiology determined a new artificial intelligence (AI) system can predict Alzheimer's disease (AD) onset more than six years ahead with 100 percent accuracy, reports Radiology Business . The AI algorithm to predict the AD onset on a database of 2,109 independent fluorine 18-fluorodeoxyglucose positron emission tomography studies logged in the Alzheimer's Disease Neuroimaging Initiative between 2005 and 2017. The program was trained using 90 percent of the dataset and tested on the remaining 10 percent. It was then tested on 40 scans that the algorithm was completely unfamiliar with, realizing 82 percent specificity and 100 percent sensitivity an average of 75.8 months, or 6.3 years, prior to a final AD diagnosis. "Furthermore, in predicting the final diagnosis of AD on the independent test set, it outperformed three radiology readers in the receiver operating characteristic space, with statistical significance," the researchers noted. "With further validation with larger and more diverse datasets, this algorithm may be able to augment radiologist reader performance and improve the prediction of AD diagnosis, providing an opportunity for early intervention."