AI Researchers Predict Alzheimer's Years Before Diagnosis (sciencedaily.com)

Slashdot reader pgmrdlm quotes Science Daily: Timely diagnosis of Alzheimer's disease is extremely important, as treatments and interventions are more effective early in the course of the disease. However, early diagnosis has proven to be challenging. Research has linked the disease process to changes in metabolism, as shown by glucose uptake in certain regions of the brain, but these changes can be difficult to recognize... Researchers trained [a] 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," Dr. Sohn said. "It was able to predict every single case that advanced to Alzheimer's disease

Comments

Re:So what do they DO about it?

[ShanghaiBill]

What do they tell the patient? "Good news! You won't start losing your marbles until six years from now?"

1. There are lifestyle changes that can delay the onset of dementia. Changes in the diet, more exercise, more social activity.

2. There is a lot of promising research, including immunotherapy, and cellular senescence. If potential dementia patients can be detected early, then this research can be directed more efficiently, and cures found sooner.

3. People can make better life plans with more information. They can update their will, set up a trust, spend more time with their grandchildren, take that long planned vacation to Outer Mongolia, or whatever.

But what percentage false positives?

[Ungrounded Lightning]

The algorithm achieved 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.

So no false negatives. But how many false positives? TFA doesn't say.

You can get 100% detection of fires by sounding the alarm continuously. But that's not very useful. Without that other number we don't know if this is useful or bull generated fertilizer.

Re:But what percentage false positives?

[ShanghaiBill]

So no false negatives. But how many false positives? TFA doesn't say.

The false positive rate is 18%.

So if the test says you don't have it, you don't have it. If it says you do have it, there is a 1 in 5 chance that you don't.

Here is the original paper

An obvious next step is to train the NN on a lot more data.

Re:And how soon does this test become available?

[ShanghaiBill]

Alzheimer's costs a LOT to deal with.

Just in America, dementia costs $277B per year. It is insane how little we spend researching treatments or cures, considering what an enormous return we would get on the investment.

Without new treatments, the number of people in America with dementia is projected to double by 2050 as the population ages.