A Model for Estimating Biological Age From Physiological Biomarkers of Healthy Aging: Cross-sectional Study

Artificial Intelligence-Driven Biological Age Prediction Model Using Comprehensive Health Checkup Data: Development and Validation Study

Background

The global increase in life expectancy has not shown a similar rise in healthy life expectancy. Accurate assessment of biological aging is crucial for mitigating diseases and socioeconomic burdens associated with aging. Current biological age prediction models are limited by their reliance on conventional statistical methods and constrained clinical information.

Objective

This study aimed to develop and validate an aging clock model using artificial intelligence, based on comprehensive health check-up data, to predict biological age and assess its clinical relevance.

Methods

We used data from Koreans who underwent health checkups at the Seoul National University Hospital Gangnam Center as well as from the Korean Genome and Epidemiology Study. Our model incorporated 27 clinical factors and employed machine learning algorithms, including linear regression, least absolute shrinkage and selection operator, ridge regression, elastic net, random forest, support vector machine, gradient boosting, and K-nearest neighbors. Model performance was evaluated using adjusted R2 and the mean squared error (MSE) values. Shapley Additive exPlanation (SHAP) analysis was conducted to interpret the model's predictions.

Results

The Gradient Boosting model achieved the best performance with a mean (SE) MSE of 4.219 (0.14) and a mean (SE) R2 of 0.967 (0.001). SHAP analysis identified significant predictors of biological age, including kidney function markers, gender, glycated hemoglobin level, liver function markers, and anthropometric measurements. After adjusting for the chronological age, the predicted biological age showed strong associations with multiple clinical factors, such as metabolic status, body compositions, fatty liver, smoking status, and pulmonary function.

Conclusions

Our aging clock model demonstrates a high predictive accuracy and clinical relevance, offering a valuable tool for personalized health monitoring and intervention. The model's applicability in routine health checkups could enhance health management and promote regular health evaluations.

A study on the development of a fitness age prediction model: the national fitness award cohort study 2017-2021

BACKGROUND

Physical fitness is considered an important indicator of the health of the general public. In particular, the physical fitness of the older adults is an important requirement for determining the possibility of independent living. Therefore, the purpose of this study was to examine the association between chronological age and physical fitness variables in the National Fitness Award Cohort study data and to develop multiple linear regression analyses to predict fitness age using dependent variables.

METHODS

Data from 501,774 (359,303 adults, 142,471 older adults) individuals who participated in the Korea National Fitness Award Cohort Study from 2017 to 2021 were used. The physical fitness tests consisted of 5 candidate markers for adults and 6 candidate markers for the older adults to measure muscle strength, muscle endurance, cardiopulmonary endurance, flexibility, balance, and agility. Pearson's correlation and stepwise regression analyses were used to analyze the data.

RESULTS

We obtained a predicted individual fitness age values from physical fitness indicators for adults and older adults individuals, and the mean explanatory power of the fitness age for adults was [100.882 - (0.029 × VO2max) - (1.171 × Relative Grip Strength) - (0.032 × Sit-up) + (0.032 × Sit and reach) + (0.769 × Sex male = 1; female = 2)] was 93.6% (adjusted R2); additionally, the fitness age for older adults individuals was [79.807 - (0.017 × 2-min step test) - (0.203 × Grip Strength) - (0.031 × 30-s chair stand) - (0.052 × Sit and reach) + (0.985 × TUG) - (3.468 × Sex male = 1; female = 2) was 24.3% (adjusted R2).

CONCLUSIONS

We suggest the use of fitness age as a valid indicator of fitness in adults and older adults as well as a useful motivational tool for undertaking exercise prescription programs along with exercise recommendations at the national level.

A systematic review of phenotypic and epigenetic clocks used for aging and mortality quantification in humans

Aging is the leading driver of disease in humans and has profound impacts on mortality. Biological clocks are used to measure the aging process in the hopes of identifying possible interventions. Biological clocks may be categorized as phenotypic or epigenetic, where phenotypic clocks use easily measurable clinical biomarkers and epigenetic clocks use cellular methylation data. In recent years, methylation clocks have attained phenomenal performance when predicting chronological age and have been linked to various age-related diseases. Additionally, phenotypic clocks have been proven to be able to predict mortality better than chronological age, providing intracellular insights into the aging process. This review aimed to systematically survey all proposed epigenetic and phenotypic clocks to date, excluding mitotic clocks (i.e., cancer risk clocks) and those that were modeled using non-human samples. We reported the predictive performance of 33 clocks and outlined the statistical or machine learning techniques used. We also reported the most influential clinical measurements used in the included phenotypic clocks. Our findings provide a systematic reporting of the last decade of biological clock research and indicate possible avenues for future research.

The Importance of Activating Factors in Physical Activity Interventions for Older Adults Using Information and Communication Technologies: Systematic Review

Background

In an aging population, it is important to activate older adults in taking care of their own health. Increasing physical activity is one way to avoid or lessen age-related physical and mental impairments. Interest in the use of information and communication technology (ICT) tools to promote physical activity among older adults is growing considerably. Such tools are suitable for communicating activation factors-skills, knowledge, and motivation-by integrating a variety of behavior change techniques (BCTs) to enhance physical activity. Although activation factors have been incorporated into physical activity interventions using ICT, little is known about the actual integration methods used in such interventions or about the effects of activation factors on influencing behavior change.

Objective

The first aim of this study was to identify which of the activation factors were covered in physical activity-promoting ICT interventions for older adults and which BCTs were used to address them. The second objective was to classify the user interaction interfaces and delivery modes that were used to promote these activation factors.

Methods

The search engines of PubMed, Web of Science, and ScienceDirect were used to search for and identify articles examining the effectiveness of ICT interventions for promoting physical activity in older adults. References and related data were selected, extracted, and reviewed independently by 2 reviewers. The risk of bias was assessed, and any conflict was addressed by a third separate reviewer. Selected articles included older adults aged ≥55 years without pre-existing medical diseases and other physical or mental conditions that could hinder movement.

Results

In total, 368 records were retrieved, and 13 studies met all inclusion criteria. Articles differed in terms of themes, timescales, user interaction interfaces, and outcome measures; therefore, a quantitative data synthesis was not feasible. Motivation was the most promoted activation factor among all trials (33 times). An app and a smartwatch were used in the majority of intervention groups (7/20, 35%) for tracking physical activity and receiving personalized feedback based on the individual goals. Skills (25 times) and knowledge (17 times) were the next most commonly addressed activation factors. Face-to-face interaction was the most used approach to targeting users' skills, including providing instructions on how to perform a behavior and exchanging knowledge via education on the health consequences of insufficient physical activity. Overall, integrating all 3 activation factors and using multiple user interaction interfaces with a variety of delivery modes proved the most effective in improving physical activity.

Conclusions

This study highlights commonly used BCTs and preferred modes of their delivery. So far, only a limited number of available BCTs (21/102, 21%) have been integrated. Considering their effectiveness, a larger variety of BCTs that address skills, knowledge, and motivation should be exploited in future ICT interventions.

Age-Related Cognitive Decline, Focus on Microbiome: A Systematic Review and Meta-Analysis

Aging is a complex process influenced by genetics and the environment, leading to physiological decline and increased susceptibility to diseases. Cognitive decline is a prominent feature of aging, with implications for different neurodegenerative disorders. The gut microbiome has gained attention for its potential impact on health and disease, including cognitive function. This systematic review and meta-analysis aimed to investigate the relationship between the gut microbiome and cognitive function in the context of aging. Following PRISMA guidelines, a comprehensive search strategy was employed in PubMed, Scopus, and Web of Science databases. Studies exploring the role of the microbiome in cognition and neurodegenerative disorders, published between 2013 and 2023, were included. Data extraction and quality assessment were performed. Quantitative synthesis using statistical analyses was performed to examine microbial diversity and relative abundance in various cognitive conditions. Sixteen studies involving a total of 1303 participants were included in the analysis. The gut microbiota's relative abundance was different in individuals with cognitive impairments such as Alzheimer's disease, Parkinson's disease, and dementia, compared to the healthy controls. The most prevalent phyla affected were Firmicutes, Bacteroidetes, Actinobacteria, and Proteobacteria. Meta-analyses indicated substantial heterogeneity among studies focusing on Alzheimer's disease. The overall quality of evidence related to microbial analysis was moderate. The gut microbiome's role in cognitive decline and neurodegenerative disorders warrants investigation. Altered microbial abundance, particularly in specific phyla, is associated with cognitive impairments. However, variations in study findings and methodologies highlight the complexity of the relationship between the gut microbiome and cognitive function. Further studies are needed to better understand the mechanisms underlying this connection and its potential implications for aging and cognitive health.