Nov 7, 2018

Artificial intelligence predicts Alzheimer's

Artificial intelligence (AI) technology improves the ability of brain imaging to predict Alzheimer's disease. Early diagnosis of Alzheimer's disease has proven to be challenging.


Research has linked the progression of Alzheimer's disease to changes in metabolism, as shown by glucose uptake in certain regions of the brain, but these changes can be difficult to recognize.

Implications for Patient Care
  • A deep learning algorithm can be used to improve the accuracy of predicting the diagnosis of Alzheimer disease from fluorine 18 fluorodeoxyglucose PET of the brain.
  • A deep learning algorithm can be used as an early prediction tool for Alzheimer disease, especially in conjunction with other biochemical and imaging tests, thereby providing an opportunity for early therapeutic intervention.


By Alzheimer's Reading Room

Purpose
To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither.

"If we diagnose Alzheimer's disease when all the symptoms have manifested, the brain volume loss is so significant that it's too late to intervene,"

"If we can detect Alzheimer's earlier, this could lead to better ways to slow down or even halt the disease process."


Dr. Benjamin Franc, University of California in San Francisco (UCSF), was interested in applying deep learning, a type of Artificial Intelligence in which machines learn by example much like humans do, to find changes in brain metabolism predictive of Alzheimer's disease.

Subscribe to the Alzheimer's Reading Room
Email:

"Differences in the pattern of glucose uptake in the brain are very subtle and diffuse. People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process." said study co-author Jae Ho Sohn
  • Researchers trained the deep learning algorithm on a special imaging technology known as 18-F-fluorodeoxyglucose positron emission tomography (FDG-PET).
  • In an FDG-PET scan, FDG, a radioactive glucose compound, is injected into the blood. PET scans can then measure the uptake of FDG in brain cells, an indicator of metabolic activity.

The researchers had access to data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), a major multi-site study focused on clinical trials to improve prevention and treatment of this disease.

The ADNI dataset included more than 2,100 FDG-PET brain images from 1,002 patients.

Researchers trained the deep learning algorithm on 90 percent of the dataset and then tested it on the remaining 10 percent of the dataset. Through deep learning, the algorithm was able to teach itself metabolic patterns that corresponded to Alzheimer's disease.


Finally, the researchers tested the algorithm on an independent set of 40 imaging exams from 40 patients that it had never studied.
  • The algorithm achieved 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.

"We were very pleased with the algorithm's performance. It was able to predict every single case that advanced to Alzheimer's disease." ~ Dr.Jae Ho Sohn.


He did caution that their independent test set was small and needs further validation with a larger multi-institutional prospective study,

Dr. Sohn said that the algorithm could be a useful tool to complement the work of radiologists--especially in conjunction with other biochemical and imaging tests--in providing an opportunity for early therapeutic intervention of Alzheimer's.
  • Future research directions include training the deep learning algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps and tangles in the brain that are markers specific to Alzheimer's disease, according to UCSF's Youngho Seo, Ph.D., who served as one of the faculty advisers of the study.
"If FDG-PET with AI can predict Alzheimer's disease this early, beta-amyloid plaque and tau protein PET imaging can possibly add another dimension of important predictive power," he said.

Conclusion
By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.

Related Articles

Alzheimer's Clock Draw Test -- Detect the Signs of Alzheimer's Early

Can An Undetected Urinary Tract Infection Can Kill an Alzheimer's Patient

Alzheimer's Care Using the Brain to Create Happiness

Learn More from Our Award Winning Knowledge Base - Topics Pages

My mom has dementia and is mean

How do you talk and communicate effectively with a dementia patient

How to live with someone who has Alzheimer's

The Award Winning Alzheimer’s Reading Room Knowledge Base is considered to be the highest quality, deepest collection, of information on Alzheimer’s and dementia in the world. Ranked #1 by Healthline for 7 straight years (2012-2018).

Need Help? Search Our Award Winning Knowledge Base for Answers to Your Questions About Alzheimer's and Dementia

Originally published in the Alzheimer's Reading Room

Citation

"A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain". Radiology, 2018; 180958 DOI: 10.1148/radiol.2018180958"

Drs. Sohn, Franc, and Seo and Ms. Ding were Michael G. Kawczynski, M.S., Hari Trivedi, M.D., Roy Harnish, M.S., Nathaniel W. Jenkins, M.S., Dmytro Lituiev, Ph.D., Timothy P. Copeland, M.P.P., Mariam S. Aboian, M.D., Ph.D., Carina Mari Aparici, M.D., Spencer C. Behr, M.D., Robert R. Flavell, M.D., Ph.D., Shih-Ying Huang, Ph.D., Kelly A. Zalocusky, Ph.D., Lorenzo Nardo, Ph.D., Randall A. Hawkins, M.D., Ph.D., Miguel Hernandez Pampaloni, M.D., Ph.D., and Dexter Hadley, M.D., Ph.D.