Fujifilm develops artificial intelligence tech for predicting Alzheimer’s progression

JAPAN – Fujifilm Corporation has developed artificial intelligence technology that can predict whether patients with mild cognitive impairment will develop Alzheimer’s disease (AD) within two years.

According to a press release, the AI Technology for AD Progression Prediction has been found to have high generalizability, accurately predicting patients who would progress to AD even across cohorts.

Fujifilm’s advanced image recognition technologies were used to create the AI predictive technology. Atrophy patterns seen on 3D Medical Resonance Imaging (MRI) brain images were extracted and calculated using AI and deep tech from the hippocampus and the anterior temporal lobe, both of which are strongly correlated with the progression of AD.

The progression of Alzheimer’s disease can be predicted based on these patterns.

The technology was trained on patient data from the North American-Disease Alzheimer’s Neuroimaging Initiative (NA-ADNI), the world’s largest Alzheimer’s disease research project. Other clinical data, such as cognitive test scores, were also used in the study.


The technology was found to have a prediction accuracy of 88 percent and 84 percent, respectively, when using data from North American and Japanese cohort patient groups from the NA-ADNI and J-ADNI projects.

The findings of a study conducted by Fujifilm in collaboration with Japan’s National Center of Neurology and Psychiatry (NCNP) were published in the journal npj Digital Medicine.

Last month, some of the world’s largest pharmaceutical companies tackling Alzheimer’s disease and related dementias collaborated make the best use of the truly massive amounts of digital data that can be gathered from patients as the companies look to track their progress.

Big Pharma players such as Biogen, Eisai, Eli Lilly, and Merck plan to establish a core set of digital measurements that can be used in clinical trials as part of a collaboration led by the nonprofit Digital Medicine Society.

Researchers from Boston University and Oregon Health & Science University, as well as the Alzheimer’s Drug Discovery Foundation, will join them.

Global dementia burden

The number of dementia patients worldwide is expected to increase to approximately 139 million by 2050, up from approximately 55 million today. Alzheimer’s disease, the most common cause of dementia, is also expected to increase.

Despite recent advances in Alzheimer’s disease treatment, many clinical trials have failed due to the low percentage of patients who progress from mild cognitive impairment to AD within two years, and many of these patients remain unchanged even when given a placebo.

Fujifilm and National Center of Neurology and Psychiatry intend to address these limitations and contribute to an accurate assessment of the efficacy of drug candidates for the treatment of Alzheimer’s disease.

Moving forward, the partners hope to predict the rate at which patients will progress to Alzheimer’s disease and investigate the possibility of increasing the success rate of their clinical trials.

They intend to achieve this by excluding patient participants who do not progress to Alzheimer’s disease and narrowing the distribution of progression speed between the control and treatment groups.

They also intend to conduct additional clinical trials in the near future.

Furthermore, the organizations intend to apply the AI technology’s algorithms to brain images and clinical data from various mental and neural diseases, with the hope that it will be able to predict prognoses and treatment responses.

Alzheimer’s Research UK launched a similar initiative two years ago to improve the detection of neurodegenerative diseases such as Alzheimer’s.

It aimed to create and test a diagnostic wearable device capable of detecting disease markers.

BrainCheck, based in the United States, received US$10 million in Series B funding last November, with the proceeds intended to be used to accelerate the adoption of its mobile and web-based platform for assessing cognitive decline and screening for dementia.

Liked this article? Sign up to receive our regular email newsletters, focused on Africa and World’s healthcare industry, directly into your inbox. SUBSCRIBE HERE

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.