Share on Pinterest A newly developed algorithm may detect early signs of Alzheimer’s. Westend61/Getty Images

Written by Robby Berman on September 20, 2021 — Fact checked by Anna Guildford, Ph.D.

• Mild cognitive impairment (MCI) often precedes the development of Alzheimer’s disease.
• Functional MRI (fMRI) scans can capture subtle signs of MCI, but they are difficult to interpret.
• Lithuanian researchers have developed a deep learning algorithm that identified MCI in a small study.

One of the first indicators of incipient Alzheimer’s disease (AD) is the development of MCI. Subtle, hard-to-detect changes in the brain accompany MCI as the condition advances.

Now, a study from researchers at Kaunas University of Technology (KTU) in Lithuania presents a newly developed deep-learning computer algorithm that can accurately detect and differentiate the stages of MCI from fMRI scans.

The algorithm can identify MCI and its stages with more than 99% accuracy.

MCI is a transitional state between normal age-related cognitive decline and dementia. It does not always progress to AD, but it often does, and the early detection of AD may allow people who have it to benefit more from treatment.

“Medical professionals all over the world attempt to raise awareness of an early Alzheimer’s diagnosis, which provides the affected with a better chance of benefiting from treatment,” says the study’s chief researcher Dr. Rytis Maskeliūnas.

Claire Sexton, DPhil, who is director of scientific programs and outreach at the Alzheimer’s Association and was not involved in the research, told Medical News Today:

“An early and accurate diagnosis can have emotional, social, and medical benefits, enabling individuals to make legal, financial, and care plans, explore treatment options, and participate in clinical trials.”

The study, which KTU Ph.D. student Modupe Odusami led, appears in the journal MDPI.

Accurate algorithmic detection

Although it is possible to recognize MCI manually in fMRI images, this is a time-consuming task that requires detailed knowledge. As such, it is an ideal candidate for automation using deep learning. Deep learning is a type of computer algorithm that can learn how to detect patterns in data that may be too small or obscure for humans to recognize easily.

Working with collaborators in artificial intelligence, the KTU researchers modified a well-known existing algorithm, ResNet 18, to fine-tune it for detecting MCI.

After the training process, the researchers tested the algorithm by classifying fMRI scans from 138 individuals.

The scans depicted six cognitive stages, starting at healthy control and moving through MCI to AD. In differentiating between early MCI and AD, the algorithm was 99.99% accurate. It was also 99.95% accurate in distinguishing between late MCI and AD, and between MCI and early MCI.

Dr. Maskeliūnas notes:

“Although this was not the first attempt to diagnose the early onset of Alzheimer’s from similar data, our main breakthrough is the accuracy of the algorithm.”

“Obviously,” says Dr. Maskeliūnas, “such high numbers are not indicators of true real life performance, but we’re working with medical institutions to get more data.”

MNT asked Dr. Maskeliūnas about his expectations for the real world accuracy of the algorithm. He responded, “I’d say a reliable 85+% would still be of benefit for a medical professional, reducing [their] workload on the analysis of data.”

“At this stage,” he said, “we’re working on fine-tuning algorithms, and despite having some result on a controlled dataset gathered by others, it is very likely that we’ll still have to rework it to account for variations in real life-ish data.”

Dr. Sexton suggested that it is too early to confirm the algorithm’s value, saying:

“This is an interesting but small (25 participants with Alzheimer’s) study. As a result, we cannot draw any conclusions yet about the proposed new diagnostic technique.”

Says Dr. Sexton on the algorithm: “Replication of these results in larger, more diverse study groups is needed to evaluate its potential.”

The algorithm’s future

Dr. Maskeliūnas foresees the development of an algorithm-based app that doctors could use to identify MCI in people at risk of AD. They could then direct these individuals to treatment.

He is also interested in the potential for incorporating the team’s algorithm into a self-check system that includes other early diagnostic methods currently under investigation. Examples of these other methods are eye movement tracking, face reading, and voice analysis.

According to Dr. Sexton, such novel technologies “are still being investigated. Some are being incorporated into trials now, though as exploratory, to gather additional data from larger scale studies. Bottom line: While they are definitely advancing in terms of their use, they are not yet in clinical use.”

In the KTU press release, Dr. Maskeliūnas says: “We need to make the most of data. That’s why our research group focuses on the European open science principle, so anyone can use our knowledge and develop it further. I believe that this principle contributes greatly to societal advancement.”

Dr. Maskeliūnas concludes:

“Technologies can make medicine more accessible and cheaper. Although they will never — or at least not soon — truly replace the medical professional, technologies can encourage seeking timely diagnosis and help.”

• Medical Innovation
• Alzheimer’s / Dementia
• Medical Devices / Diagnostics
• Neurology / Neuroscience

Is Alzheimer’s disease hereditary?

• Is Alzheimer’s hereditary?
• Risk factors for Alzheimer’s disease
• Early signs and symptoms
• Summary

Alzheimer’s disease is a chronic, progressive condition that impairs memory, thinking, and movement. Some research suggests that a person is at increased risk for developing Alzheimer’s Disease if a relative has the disorder.

Alzheimer’s disease is the most common cause of dementia. Dementia can severely impact an individual’s ability to think, make judgments, and carry out everyday tasks.

Doctors have been aware of Alzheimer’s for many years, but many aspects of the condition and a possible cure remain unknown.

The causes of Alzheimer’s are unclear.

Current research suggests that multiple factors may contribute to the development of Alzheimer’s. One of these is genetics or heredity.

Genetic factors may also impact how a doctor prescribes medications to treat Alzheimer’s disease.

Is Alzheimer’s hereditary?

Share on Pinterest Some genes can increase the risk of Alzheimer’s disease or even directly cause it.

Scientists describe genetic risks for Alzheimer’s in terms of two factors: Risk genes and deterministic genes.

When a person has risk genes, it means they have an increased chance of developing a disease. For example, a woman with the BRCA1 and BRCA2 genes has a higher risk of developing breast cancer.

Deterministic genes may directly cause a disease to develop.

Scientists have found several risk and deterministic genes for Alzheimer’s.

Risk genes

Several genes present a risk for Alzheimer’s. The gene with the most significant connection to Alzheimer’s risk is the apolipoprotein E-E4 gene (APOE-e4).

According to the Alzheimer’s Association, an estimated 20–25 percent of people with this gene may go on to have Alzheimer’s disease.

A person who inherits the APOE-e4 gene from both parents has a higher risk of developing Alzheimer’s disease than a person who inherits the gene from only one.

Having the gene may also mean that a person displays symptoms at an earlier age and receive an earlier diagnosis.

Other genes may have effects on late-onset Alzheimer’s and its development. Scientists need to do more research to learn how these genes increase Alzheimer’s risk.

Several of these genes regulate certain factors in the brain, such as inflammation and the way that nerve cells communicate.

While every person inherits an APOE gene of some form, the APOE-e3 and APOE-e2 genes have no association Trusted Source with Alzheimer’s disease. APOE-e2 might even provide protective effects on the brain against the disease.

Deterministic genes

Researchers have identified three specific deterministic genes that may cause Alzheimer’s disease:

• amyloid precursor protein (APP)
• presenilin-1 (PS-1)
• presenilin-2 (PS-2)

These genes are responsible for an excessive buildup of amyloid-beta peptide. This is a toxic protein that clumps together in the brain. This buildup causes the nerve cell damage and death that is characteristic of Alzheimer’s disease.

However, not all people with early-onset Alzheimer’s have these genes. A person with these genes who develops Alzheimer’s has a rare type known as familial Alzheimer’s disorder.

According to the Alzheimer’s Association, familial Alzheimer’s represents less than 5 percent of all cases in the world.

According to the Association, Alzheimer’s caused by deterministic genes typically occurs before the age of 65 years. It can sometimes develop in people who are in their 40s and 50s.

Effect of genes in other types of dementia

Some types of dementia have links to other genetic malformations.

Huntington’s disease, for example, alters chromosome 4, which can lead to progressive dementia. Huntington’s disease is a dominant genetic condition. This means that if either parent has the condition, they can pass on the gene to their offspring and they will develop the disease.

Symptoms of Huntington’s disease do not usually become evident until a person reaches 30–50 years of age. This can make it difficult for doctors to predict or diagnose before a person has children and passes on the gene.

Researchers think that dementia with Lewy bodies or Parkinson’s dementia may also have a genetic component. However, they also believe that other factors outside of genetics might play a role in the development of these conditions.

Risk factors for Alzheimer’s disease

Researchers have identified several risk factors for Alzheimer’s disease.

These include:

• Age: The most significant risk factor for Alzheimer’s disease is age. People over 65 years of age are more likely to develop Alzheimer’s than younger people. By 85 years of age, the Alzheimer’s Association estimate that 1 in 3 people have the condition.
• Family history: Having a close relative with Alzheimer’s disease increases the risk of developing it.
• Head trauma: People with previous instances of severe head trauma, such as from a motor vehicle accident or contact sports, appear to be at higher risk of developing Alzheimer’s disease.
• Heart health: Health problems in the heart or blood vessels may increase the chance of developing Alzheimer’s disease. Examples include high blood pressure, stroke, diabetes, heart disease, and high cholesterol. These can damage blood vessels in the brain, impacting Alzheimer’s disease risk.

Early signs and symptoms

Share on Pinterest Alzheimer’s can lead to difficulty recognizing people.

Alzheimer’s disease usually involves a gradual loss of memory and brain function.

Early symptoms may include periods of forgetfulness or memory loss. Over time, a person may experience confusion or disorientation in familiar settings, including in the home.

Other symptoms could include:

• changes in mood or personality
• confusion about time or place
• difficulty with routine tasks, such as doing laundry or cooking
• difficulty recognizing common objects
• difficulty recognizing people
• frequently misplacing objects and belongings

The aging process might naturally impair a person’s memory, but Alzheimer’s disease leads to more consistent periods of forgetfulness.

Over time, a person with Alzheimer’s may need an increasing amount of assistance with daily living, such as brushing teeth, getting dressed, and cutting food.

They may also experience agitation, restlessness, personality withdrawals, and speech problems.

According to the National Institutes of Health, the survival rate for a person with Alzheimer’s disease is usually 8 to 10 years after the first appearance of symptoms.

As people with advanced Alzheimer’s cannot care for themselves or may no longer recognize the importance of eating, common causes of death include malnutrition, body wasting, or pneumonia.

When to see a doctor

Seeking medical assistance for a person who demonstrates these symptoms is vital, even though the discussion might be a difficult one. A doctor can rule out other diseases that might cause dementia, such as a urinary tract infection or brain tumor.

Before an appointment, family members should make a list of any medications the person with symptoms is currently taking. The doctor can review the list and make sure dementia symptoms are not side effects of current medications.

Keep a journal of noticeable symptoms as they develop over time to help a doctor establish potential patterns.

Although genetic testing that can detect the genes that have links to Alzheimer’s disease is available, doctors do not generally recommend this testing for late-onset diseases.

The presence of the genes does not necessarily mean that a person will have the condition. Testing could cause unnecessary worry, anxiety, and fear.

However, a person with a family history of early-onset Alzheimer’s may wish to pursue genetic testing. Most doctors will recommend meeting with a genetic counselor beforehand to discuss the pros and cons of genetic testing, and how they can interpret the results.

Sometimes, a doctor may recommend genetic testing when people show early Alzheimer’s symptoms, as this may dictate possible treatments and potential for therapeutic drug trials.

Summary

Alzheimer’s disease has links to a number of genes. Some, such as the APOE-e4 gene, increase the risk of developing the disease but do not always lead to an Alzheimer’s diagnosis.

Others, such as the APP gene, directly cause the disease to develop. However, this is a rare type known as familial Alzheimer’s that occurs in less than 5 percent of people with the disease.

Researchers are currently undertaking some large-scale studies on Alzheimer’s disease and its links to heredity.

People who would like to contribute to the body of knowledge could contact researchers from the National Institute on Aging, who sponsor the Alzheimer’s disease genetics study.

The study, which will run until the year 2021, tracks information on people with more than two relatives who received an Alzheimer’s diagnosis after the age of 65 years old.