DIAGNOSING ALZHEIMER’S DISEASE EARLY: A single brain MRI (combined with a machine learning algorithm) can determine if an individual has Alzheimer’s disease with 98 percent accuracy.
We have no simple and widely available approach to predicting Alzheimer’s disease with such high accuracy. Alzheimer’s is the most common form of dementia but can be challenging to diagnose.
Current approaches to identifying Alzheimer’s disease include cognitive tests and brain scans to search for protein deposits in the brain. Another way is to look for shrinkage in the hippocampus, a brain structure central to memory.
Can we use a single MRI with the artificial intelligence approach known as machine learning to accelerate the diagnosis process? According to a new study from Imperial College London (United Kingdom), the answer appears to be yes.
Alzheimer’s disease basics
Dementia is an overarching term for several conditions. Alzheimer’s disease (AD) is the most common form of dementia.
AD is a progressive disease that starts with mild memory loss (and sometimes leads to the inability to participate in a conversation or respond appropriately to their environment).
Alzheimer’s disease involves brain parts associated with thought regulation, memory, and language. The condition can seriously impair one’s ability to carry out the normal activities of daily living.
In the United States, about 5.8 million individuals age 65 and older live with Alzheimer’s disease. Of these individuals, 80 percent are 75 years and older. Worldwide, the incidence is 50 million.
Memory loss is the hallmark of Alzheimer’s disease, with early signs including challenges in remembering recent conversations or events. With disease progression, the memory impairments worsen, and other symptoms emerge.
At first, a person with Alzheimer’s disease may be aware of having difficulty remembering things and organizing thoughts. A family member or friend may be more likely to notice how the symptoms worsen.
DIAGNOSING Alzheimer’s EARLY with a single MRI
Early Alzheimer’s disease detection is challenging. Enter magnetic resonance imaging (MRI), paired with the artificial learning tool known as machine learning.
The researchers developed an algorithm with an MRI, an imaging tool available in most hospitals. They trained artificial intelligence to identify and assess brain features such as shape, size, and texture to predict Alzheimer’s disease using data from 783 people scanned with an MRI.
Here are the subject characteristics:
- 216 healthy controls
- 208 had mild cognitive impairment secondary to Alzheimer’s
- 181 had Alzheimer’s disease
- 94 had frontotemporal dementia
- 84 had Parkinson’s disease
DIAGNOSING ALZHEIMER’S EARLY: Study results
The algorithm identified brain shrinkage in those with early Alzheimer’s disease.
It did so with better diagnostic accuracy than current approaches, such as measuring the amount of shrinkage of the hippocampus (a key memory center in the brain) or checking spinal fluid for the substance amyloid-beta. The amyloid–beta peptide appears to play a central role in the pathology of Alzheimer’s disease.
The algorithm is accurate.
The algorithm reliably discriminated between those with or without Alzheimer’s disease (up to 98 percent accuracy) without requiring neuroradiologist input.
These excellent results compare favorably to 26 percent accuracy for standard measurements of hippocampus shrinkage and 62 percent accuracy for spinal fluid amyloid-beta measurements.
DIAGNOSING Alzheimer’s EARLY with MRI: My take
Alzheimer’s disease (AD) is the most common form of dementia. It can be devastating, impacting thinking, memory, and behavior. Unfortunately, diagnosis of AD remains challenging. Still, we know that as Alzheimer’s disease develops, the brain shrinks as cells within it die.
The new single MRI approach (paired with the artificial intelligence tool known as machine learning) can assess brain structure and function. The current study points to a simple brain MRI significantly improving our ability to identify Alzheimer’s disease earlier.
Finding early Alzheimer’s disease should facilitate the identification of patients for clinical trials of new medicines or lifestyle changes. This development heartens me.
Thank you for joining me today to explore how a single brain MRI may facilitate Alzheimer’s diagnosis.
Oh, one more thing. The good folks at the Mayo Clinic (USA) advise us when we should see a doctor: If you are concerned about your memory or other cognitive skills, please see a valued healthcare professional for a thorough evaluation.
If you have concerns about the thinking skills of a family member or friend, share your concerns and ask about going to a doctor’s appointment.
The information I provided in this blog is for educational purposes only and does not substitute for professional medical advice. Please consult a medical professional or healthcare provider if you seek medical advice, diagnoses, or treatment. I am not liable for risks or issues associated with using or acting upon the information in this blog.
