Various researchers around the globe are developing ways to detect Alzheimer"s Disease as early as possible. After all, early detection is crucial when it comes to Alzheimer’s. it can give people time to undergo treatment to slow down the effects of the condition. It can also give them time to arrange things such as their finances and legal affairs.
Some researchers decided to focus on blood and cerebrospinal fluid tests. Others focused their efforts on developing equipment that can look for early signs. One team of researchers went a whole different path. The path of AI.
How does AI help predict Alzheimer’s Disease?
This team of researchers are from the University of Bari which is in Italy. They developed an algorithm that can spot tiny structural changes in the brain. The disease causes these changes. The AI can predict these changes up to 10 years before symptoms become visible.
These researchers trained their AI to the task. They did this by feeding it 67 MRI scans. 38 scans from Alzheimer"s patients and 29 from healthy controls. The researchers divided the scans into small regions.
They then had their AI analyze the neuronal connectivity between. After training was done, they tested the algorithm by having it process brain scans from 148 subjects. Overall, 48 scans were those who had the disease while were scans of people who suffered from mild cognitive impairment and eventually developed full-blown Alzheimer"s.
The AI had an 86% accuracy when it came to detecting the disease. it was able to detect mild cognitive impairment 84 percent of the time. This makes it a potentially effective tool for early diagnosis. The downside to the research was that the scans were limited to the ones in USC LA"s Alzheimer"s Disease Neuroimaging Initiative database. With further development, the AI could become more accurate and reliable.