All Articles

Using machine learning for early screening and detection of Alzheimer’s disease

News
July 15, 2022
By
Ehab Naim, MBA.

Early diagnosis of dementia patients enables early intervention that could potentially prevent or delay disease onset. Scalable, automated models can become one of the tools to do that.

Early diagnosis of dementia patients enables early intervention that could potentially prevent or delay disease onset. Alzheimer’s disease (AD) is the most common form of dementia. Despite the importance of early diagnosis, 3 in every 4 individuals with dementia have not been diagnosed yet. One possible way to overcome this problem is to devise a screening method that could be implemented in non-clinical settings.

Drawing tests are commonly used in clinical practice to screen and diagnose AD. The changes in an individual's drawing capability represent a sensitive indicator of AD and mild cognitive impairment (MCI), an early stage of dementia. An example of the drawing tools is the trail-making test, which measures the person’s processing speed and drawing ability in terms of task completion time. In clinical settings, multiple tests are utilized to enhance AD screening and diagnosis. The outcome of the drawing tests requires evaluation by clinical specialists, which may act as a barrier to early screening. Therefore, developing automated drawing tests in non-specialist settings could mend the gap.

Kobayashi et al. used several machine-learning algorithms to diagnose AD. The sample consisted of 144 participants, including patients with AD, MCI, and cognitively normal (CN) individuals. The subjects underwent seven cognitive assessment tests that evaluated global and specific cognitive domains. Then, the participants took five drawing tasks, which were later used to evaluate cognitive measures using machine learning. The objective was to determine whether the drawing features extracted from different tasks were associated with diagnostic status and cognitive measures. Also, researchers assessed the feasibility of utilizing a five-task combined model versus a single-task model in identifying and evaluating cognitive performance.

Results revealed that the model combining features from all the five drawing tasks outperformed the models based on characteristics from a single task. Regarding diagnostic categories, the five-task model achieved an accuracy of 75.2% in assessing AD, MCI, and CN. This was 7.8% higher than the best single-task performance. Also, the combined model could differentiate between AD cases and CN with an accuracy of 96.8%, higher than any single-task model. Regarding MCI and CN differentiation, the combined model achieved an accuracy of 82.2%, which was 7.6% higher than any single-task model.

The authors concluded that using a multiple-assessment approach could potentially capture different, complementary aspects of cognitive impairment. This could be used to better screen and detect AD and MCI early on, using scalable, automated models.

Source: Kobayashi M, Yamada Y, Shinkawa K, Nemoto M, Nemoto K, Arai T. Automated Early Detection of Alzheimer’s Disease by Capturing Impairments in Multiple Cognitive Domains with Multiple Drawing Tasks. Journal of Alzheimer's Disease. 2022 Jun 13(Preprint):1-5.

Early diagnosis of dementia patients enables early intervention that could potentially prevent or delay disease onset. Alzheimer’s disease (AD) is the most common form of dementia. Despite the importance of early diagnosis, 3 in every 4 individuals with dementia have not been diagnosed yet. One possible way to overcome this problem is to devise a screening method that could be implemented in non-clinical settings.

Drawing tests are commonly used in clinical practice to screen and diagnose AD. The changes in an individual's drawing capability represent a sensitive indicator of AD and mild cognitive impairment (MCI), an early stage of dementia. An example of the drawing tools is the trail-making test, which measures the person’s processing speed and drawing ability in terms of task completion time. In clinical settings, multiple tests are utilized to enhance AD screening and diagnosis. The outcome of the drawing tests requires evaluation by clinical specialists, which may act as a barrier to early screening. Therefore, developing automated drawing tests in non-specialist settings could mend the gap.

Kobayashi et al. used several machine-learning algorithms to diagnose AD. The sample consisted of 144 participants, including patients with AD, MCI, and cognitively normal (CN) individuals. The subjects underwent seven cognitive assessment tests that evaluated global and specific cognitive domains. Then, the participants took five drawing tasks, which were later used to evaluate cognitive measures using machine learning. The objective was to determine whether the drawing features extracted from different tasks were associated with diagnostic status and cognitive measures. Also, researchers assessed the feasibility of utilizing a five-task combined model versus a single-task model in identifying and evaluating cognitive performance.

Results revealed that the model combining features from all the five drawing tasks outperformed the models based on characteristics from a single task. Regarding diagnostic categories, the five-task model achieved an accuracy of 75.2% in assessing AD, MCI, and CN. This was 7.8% higher than the best single-task performance. Also, the combined model could differentiate between AD cases and CN with an accuracy of 96.8%, higher than any single-task model. Regarding MCI and CN differentiation, the combined model achieved an accuracy of 82.2%, which was 7.6% higher than any single-task model.

The authors concluded that using a multiple-assessment approach could potentially capture different, complementary aspects of cognitive impairment. This could be used to better screen and detect AD and MCI early on, using scalable, automated models.

Source: Kobayashi M, Yamada Y, Shinkawa K, Nemoto M, Nemoto K, Arai T. Automated Early Detection of Alzheimer’s Disease by Capturing Impairments in Multiple Cognitive Domains with Multiple Drawing Tasks. Journal of Alzheimer's Disease. 2022 Jun 13(Preprint):1-5.

Article reviewed by
Dr. Ana Baroni MD. Ph.D.
SCIENTIFIC & MEDICAL ADVISOR
Quality Garant
Close

Dr. Ana Baroni MD. Ph.D.

Scientific & Medical Advisor
Quality Garant

Ana has over 20 years of consultancy experience in longevity, regenerative and precision medicine. She has a multifaceted understanding of genomics, molecular biology, clinical biochemistry, nutrition, aging markers, hormones and physical training. This background allows her to bridge the gap between longevity basic sciences and evidence-based real interventions, putting them into the clinic, to enhance the healthy aging of people. She is co-founder of Origen.life, and Longevityzone. Board member at Breath of Health, BioOx and American Board of Clinical Nutrition. She is Director of International Medical Education of the American College of Integrative Medicine, Professor in IL3 Master of Longevity at Barcelona University and Professor of Nutrigenomics in Nutrition Grade in UNIR University.

DISCOVER
HealthyLongevity.guide
4.8 / 5
Professional science-based education
250+ Articles, video lectures, webinars
Community of 1000+ verified professionals
Start for Free

Read the latest articles

Article
Nutrition
Lifestyle
Longevity

When to Check a Client for Nutrient Deficiencies?

September 28, 2022

The elderly, menstruating, breastfeeding, or pregnant women, dieters, and patients with intestinal diseases and insufficient sun exposure are at an increased risk of deficiency

Jiří Kaloč
News
Diagnostics

A functional tool to assess, predict, and improve cardiovascular disease outcome

September 27, 2022

Traditional cardiovascular disease (CVD) risk factors have limited prognostic capacity in older adults (aged >65 years).

Ehab Naim, MBA.
News
Disease

Disruption of the circadian rhythm and its possible contribution to many diseases

September 23, 2022

Circadian rhythm disruption can be a generalized p-factor for mental diseases, and obsessive-compulsive disorders, among others.

Ehab Naim, MBA.
Article
Longevity
Lifestyle
Prevention

Exposome: how the environment affects our health

September 22, 2022

The exposome paradigm unites all nongenetic factors influencing health and disease, from chemicals and infectious agents to psychosocial stress.

Olena Mokshyna, PhD.
News
Diagnostics
Longevity
Medicine
Prevention

Zero-interaction technology and its potential for long-term monitoring of older adults

September 21, 2022

Population aging poses a challenge to any healthcare system. One approach to tackle this challenge is transforming the healthcare system from reactive to predictive, preventive, personalized medicine.

Ehab Naim, MBA.
Article
Longevity
Lifestyle
Body

How to Help Clients Track Longevity Progress as a Nutritionist?

September 16, 2022

Helping clients interpret the results and put value to each can make the difference between staying motivated and losing focus.

Jiří Kaloč
News
Body
Lifestyle
Prevention

Improving muscle power in older adults: Power training vs strength training

September 15, 2022

The aging process causes degenerative changes in various bodily systems, including the neuromuscular system. This decline makes daily activities like climbing stairs more challenging to perform.

Ehab Naim, MBA.
Article
Prevention

Age-related sleep disorders: you do not snooze, you lose

September 14, 2022

Sleeping well can improve overall condition, and a proper approach to sleep hygiene and maintenance is inseparable from a healthy and long life.

Olena Mokshyna, PhD.
News
Technology

More light! A novel treatment for seasonal affective disorder

September 13, 2022

Though a larger-scale clinical trial is needed, results suggest that, indeed, “more light” is beneficial for people with SAD.

Olena Mokshyna, PhD.
News
Longevity
Medicine
Pharmaceuticals

Early, pulsatile use of rapamycin promoted longevity in two preclinical models

September 9, 2022

The researchers concluded that early, brief rapamycin exposure confers geroprotective effects similar to lifelong treatment without the adverse effects of chronic dosing.

Ehab Naim, MBA.
News
Metabolism

Saturated is not always bad: findings from a newly discovered metabolite

September 7, 2022

Recent research highlighted pentadecanoic acid (PA) as an essential fatty acid needed for physiological health. 

Olena Mokshyna, PhD.
Article
Nutrition
Keto
Low carb

Should you recommend keto to your clients?

September 6, 2022

The ketogenic diet (often called keto) has gained a substantial amount of popularity in recent years. Previously, it was primarily used to treat epilepsy.

Jiří Kaloč
Article
Body
Lifestyle

Swimming: exercise with unique life-long benefits

September 20, 2022

Swimming, though another form of exercise, drastically differs from other traditional activities that require weight-bearing.

Olena Mokshyna, PhD.
News
Longevity
Metabolism
Aging
Pharmaceuticals
Supplements

Mice blood transfusions provide new insights into senescence

August 23, 2022

A single blood transfusion from older mice into younger ones resulted in cell aging, leading to liver fibrosis, renal damage, and decreased muscle strength.

Olena Mokshyna, PhD.
News
Supplements
Aging
Longevity
Nutrition
Body

Pomegranates and citrus fruits could possibly promote healthy longevity

August 23, 2022

Daily supplementation of a citrus and pomegranate complex for four weeks improved physical fitness and psychological parameters in healthy older adults.

Ehab Naim, MBA.
Article
Longevity
Prevention
Lifestyle
Interventions
Medicine

Aerobic or resistance training, or both?

August 19, 2022

Including different types of training allows to maximize the benefits and harmoniously improve an individual's state.

Olena Mokshyna, PhD.
No items found.