The news: Electronics company Fujifilm developed AI tech that can predict whether mild cognitive impairment will progress to Alzheimer’s disease in two years.

How it works: The AI algorithm is trained on 3D MRI brain images and cognitive test scores (as a measure of cognitive impairment). It correlates imaging and cognitive health data with brain imaging patterns that are strongly indicative of Alzheimer’s.

• Fujifilm’s study found that its AI tech has 84% prediction accuracy for its Japanese patient cohort and 88% accuracy for its North American cohort.

Why it matters: The prevalence of Alzheimer’s disease is growing. Predictive AI solutions could help catch it at an early stage.

Early detection can give patients a better chance at benefiting from treatment and participating in clinical trials. Predictive AI can also be useful in driving clinical trials success. This will bring researchers one step closer to an effective Alzheimer's treatment.