Prediction of chronological and biological age from laboratory data

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

Explainable machine learning framework to predict personalized physiological aging

Attaining personalized healthy aging requires accurate monitoring of physiological changes and identifying subclinical markers that predict accelerated or delayed aging. Classic biostatistical methods most rely on supervised variables to estimate physiological aging and do not capture the full complexity of inter-parameter interactions. Machine learning (ML) is promising, but its black box nature eludes direct understanding, substantially limiting physician confidence and clinical usage. Using a broad population dataset from the National Health and Nutrition Examination Survey (NHANES) study including routine biological variables and after selection of XGBoost as the most appropriate algorithm, we created an innovative explainable ML framework to determine a Personalized physiological age (PPA). PPA predicted both chronic disease and mortality independently of chronological age. Twenty-six variables were sufficient to predict PPA. Using SHapley Additive exPlanations (SHAP), we implemented a precise quantitative associated metric for each variable explaining physiological (i.e., accelerated or delayed) deviations from age-specific normative data. Among the variables, glycated hemoglobin (HbA1c) displays a major relative weight in the estimation of PPA. Finally, clustering profiles of identical contextualized explanations reveal different aging trajectories opening opportunities to specific clinical follow-up. These data show that PPA is a robust, quantitative and explainable ML-based metric that monitors personalized health status. Our approach also provides a complete framework applicable to different datasets or variables, allowing precision physiological age estimation.

Biomarkers selection and mathematical modeling in biological age estimation

Biological age (BA) is important for clinical monitoring and preventing aging-related disorders and disabilities. Clinical and/or cellular biomarkers are measured and integrated in years using mathematical models to display an individual's BA. To date, there is not yet a single or set of biomarker(s) and technique(s) that is validated as providing the BA that reflects the best real aging status of individuals. Herein, a comprehensive overview of aging biomarkers is provided and the potential of genetic variations as proxy indicators of the aging state is highlighted. A comprehensive overview of BA estimation methods is also provided as well as a discussion of their performances, advantages, limitations, and potential approaches to overcome these limitations.

Introducing an adolescent cognitive maturity index

Children show substantial variation in the rate of physical, cognitive, and social maturation as they traverse adolescence and enter adulthood. Differences in developmental paths are thought to underlie individual differences in later life outcomes, however, there remains a lack of consensus on the normative trajectory of cognitive maturation in adolescence. To address this problem, we derive a Cognitive Maturity Index (CMI), to estimate the difference between chronological and cognitive age predicted with latent factor estimates of inhibitory control, risky decision-making and emotional processing measured with standard neuropsychological instruments. One hundred and forty-one children from the Adolescent Development Study (ADS) were followed longitudinally across three time points from ages 11-14, 13-16, and 14-18. Age prediction with latent factor estimates of cognitive skills approximated age within ±10 months (r = 0.71). Males in advanced puberty displayed lower cognitive maturity relative to peers of the same age; manifesting as weaker inhibitory control, greater risk-taking, desensitization to negative affect, and poor recognition of positive affect.

Ageing and cancer: a research gap to fill

The complex mechanisms of ageing biology are increasingly understood. Interventions to reduce or delay ageing‐associated diseases are emerging. Cancer is one of the diseases promoted by tissue ageing. A clockwise mutational signature is identified in many tumours. Ageing might be a modifiable cancer risk factor. To reduce the incidence of ageing‐related cancer and to detect the disease at earlier stages, we need to understand better the links between ageing and tumours. When a cancer is established, geriatric assessment and measures of biological age might help to generate evidence‐based therapeutic recommendations. In this approach, patients and caregivers would include the respective weight to give to the quality of life and survival in the therapeutic choices. The increasing burden of cancer in older patients requires new generations of researchers and geriatric oncologists to be trained, to properly address disease complexity in a multidisciplinary manner, and to reduce health inequities in this population of patients. In this review, we propose a series of research challenges to tackle in the next few years to better prevent, detect and treat cancer in older patients while preserving their quality of life.

All-Subset Analysis Improves the Predictive Accuracy of Biological Age for All-Cause Mortality in Chinese and U.S. Populations

BACKGROUND

Klemera-Doubal's method (KDM) is an advanced and widely applied algorithm for estimating biological age (BA), but it has no uniform paradigm for biomarker processing. This article proposed all subsets of biomarkers for estimating BAs and assessed their association with mortality to determine the most predictive subset and BA.

METHODS

Clinical biomarkers, including those from physical examinations and blood assays, were assessed in the China Health and Nutrition Survey (CHNS) 2009 wave. Those correlated with chronological age (CA) were combined to produce complete subsets, and BA was estimated by KDM from each subset of biomarkers. A Cox proportional hazards regression model was used to examine and compare each BA's effect size and predictive capacity for all-cause mortality. Validation analysis was performed in the Chinese Longitudinal Healthy Longevity Survey (CLHLS) and National Health and Nutrition Examination Survey (NHANES). KD-BA and Levine's BA were compared in all cohorts.

RESULTS

A total of 130 918 panels of BAs were estimated from complete subsets comprising 3-17 biomarkers, whose Pearson coefficients with CA varied from 0.39 to 1. The most predictive subset consisted of 5 biomarkers, whose estimated KD-BA had the most predictive accuracy for all-cause mortality. Compared with Levine's BA, the accuracy of the best-fitting KD-BA in predicting death varied among specific populations.

CONCLUSION

All-subset analysis could effectively reduce the number of redundant biomarkers and significantly improve the accuracy of KD-BA in predicting all-cause mortality.

Deep transfer learning of structural magnetic resonance imaging fused with blood parameters improves brain age prediction

Machine learning has been applied to neuroimaging data for estimating brain age and capturing early cognitive impairment in neurodegenerative diseases. Blood parameters like neurofilament light chain are associated with aging. In order to improve brain age predictive accuracy, we constructed a model based on both brain structural magnetic resonance imaging (sMRI) and blood parameters. Healthy subjects (n = 93; 37 males; aged 50–85 years) were recruited. A deep learning network was firstly pretrained on a large set of MRI scans (n = 1,481; 659 males; aged 50–85 years) downloaded from multiple open‐source datasets, to provide weights on our recruited dataset. Evaluating the network on the recruited dataset resulted in mean absolute error (MAE) of 4.91 years and a high correlation (r = .67, p <.001) against chronological age. The sMRI data were then combined with five blood biochemical indicators including GLU, TG, TC, ApoA1 and ApoB, and 9 dementia‐associated biomarkers including ApoE genotype, HCY, NFL, TREM2, Aβ40, Aβ42, T‐tau, TIMP1, and VLDLR to construct a bilinear fusion model, which achieved a more accurate prediction of brain age (MAE, 3.96 years; r = .76, p <.001). Notably, the fusion model achieved better improvement in the group of older subjects (70–85 years). Extracted attention maps of the network showed that amygdala, pallidum, and olfactory were effective for age estimation. Mediation analysis further showed that brain structural features and blood parameters provided independent and significant impact. The constructed age prediction model may have promising potential in evaluation of brain health based on MRI and blood parameters.

Personalized multicomponent exercise programs using smartphone technology among older people: protocol for a randomized controlled trial

BACKGROUND

Optimal application of the recently updated World Health Organization (WHO) guidelines for exercise in advanced age necessitates an accurate adjustment for the age-related increasing variability in biological age and fitness levels, alongside detailed recommendations across a range of motor fitness components, including balance, strength, and flexibility. We previously developed and validated a novel tool, designed to both remotely assess these fitness components, and subsequently deliver a personalized exercise program via smartphone. We describe the design of a prospective randomized control trial, comparing the effectiveness of the remotely delivered personalized multicomponent exercise program to either WHO exercise guidelines or no intervention.

METHODS

Participants (n = 300) are community dwelling, healthy, functionally independent, cognitively intact volunteers aged ≥65 at low risk for serious fall injuries, assigned using permuted block randomization (age/gender) to intervention, active-control, or control group. The intervention is an 8-week program including individually tailored exercises for upper/lower body, flexibility, strength, and balance (dynamic, static, vestibular); active-controls receive exercising counselling according to WHO guidelines; controls receive no guidance. Primary outcome is participant fitness level, operationalized as 42 digital markers generated from 10 motor fitness measures (balance, strength, flexibility); measured at baseline, mid-trial (4-weeks), trial-end (8-weeks), and follow-up (12-weeks). Target sample size is 300 participants to provide 99% power for moderate and high effect sizes (Cohen's f = 0.25, 0.40 respectively).

DISCUSSION

The study will help understand the value of individualized motor fitness assessment used to generate personalized multicomponent exercise programs, delivered remotely among older adults.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT04181983.

The Role of Big Data in Aging and Older People’s Health Research: A Systematic Review and Ecological Framework

Big data has been prominent in studying aging and older people’s health. It has promoted modeling and analyses in biological and geriatric research (like cellular senescence), developed health management platforms, and supported decision-making in public healthcare and social security. However, current studies are still limited within a single subject, rather than flourished as interdisciplinary research in the context of big data. The research perspectives have not changed, nor has big data brought itself out of the role as a modeling tool. When embedding big data as a data product, analysis tool, and resolution service into different spatial, temporal, and organizational scales of aging processes, it would present as a connection, integration, and interaction simultaneously in conducting interdisciplinary research. Therefore, this paper attempts to propose an ecological framework for big data based on aging and older people’s health research. Following the scoping process of PRISMA, 35 studies were reviewed to validate our ecological framework. Although restricted by issues like digital divides and privacy security, we encourage researchers to capture various elements and their interactions in the human-environment system from a macro and dynamic perspective rather than simply pursuing accuracy.

Personalized Exercise Programs Based upon Remote Assessment of Motor Fitness: A Pilot Study among Healthy People Aged 65 Years and Older

BACKGROUND

The World Health Organization has recently updated exercise guidelines for people aged >65 years, emphasizing the inclusion of multiple fitness components. However, without adequate recognition of individual differences, these guidelines may be applied using an approach that "one-size-fits-all." Within the shifting paradigm toward an increasingly personalized approach to medicine and health, it is apparent that fitness components display a significant age-related increase in variability. Therefore, it is both logical and necessary to perform an accurate individualized assessment of multiple fitness components prior to optimal prescription for a personalized exercise program.

OBJECTIVE

The aim of the study was to test the feasibility and effectiveness of a novel tool able to remotely assess balance, flexibility, and strength using smartphone sensors (accelerometer/gyroscope), and subsequently deliver personalized exercise programs via the smartphone.

METHODS

We enrolled 52 healthy volunteers (34 females) aged 65+ years, with normal cognition and low fall risk. Baseline data from remote smartphone fitness assessment were analyzed to generate 42 fitness digital markers (DMs), used to guide personalized exercise programs (×5/week for 6 weeks) delivered via smartphone. Programs included graded exercises for upper/lower body, flexibility, strength, and balance (dynamic, static, and vestibular). Participants were retested after 6 weeks.

RESULTS

Average age was 74.7 ± 6.4 years; adherence was 3.6 ± 1.7 exercise sessions/week. Significant improvement for pre-/posttesting was observed for 10/12 DMs of strength/flexibility for upper/lower body (sit-to-stand repetitions/duration; arm-lift duration; torso rotation; and arm extension/flexion). Balance improved significantly for 6/10 measures of tandem stance, with consistent (nonsignificant) trends observed across 20 balance DMs of tandem walk and 1 leg stance. Balance tended to improve among the 37 participants exercising ≥3/week.

DISCUSSION

These preliminary results provide a proof of concept, with high adherence and improved fitness confirming the benefits of remote fitness assessment for guiding home personalized exercise programs among healthy adults aged >65 years. Further examination of the application within a randomized control study is necessary, comparing the personalized exercise program to general guidelines among healthy older adults, as well as specific populations, such as those with frailty, deconditioning, cognitive, or functional impairment. The study tool offers the opportunity to collect big data, including additional variables, with subsequent utilization of artificial intelligence to optimize the personalized exercise program.

Biological age in healthy elderly predicts aging-related diseases including dementia

Application of biological age as a measure of an individual´s health status offers new perspectives into extension of both lifespan and healthspan. While algorithms predicting mortality and most aging-related morbidities have been reported, the major shortcoming has been an inability to predict dementia. We present a community-based cohort study of 1930 participants with a mean age of 72 years and a follow-up period of over 7 years, using two variants of a phenotypic blood-based algorithm that either excludes (BioAge1) or includes (BioAge2) neurofilament light chain (NfL) as a neurodegenerative marker. BioAge1 and BioAge2 predict dementia equally well, as well as lifespan and healthspan. Each one-year increase in BioAge1/2 was associated with 11% elevated risk (HR 1.11; 95%CI 1.08-1.14) of mortality and 7% elevated risk (HR 1.07; 95%CI 1.05-1.09) of first morbidities. We additionally tested the association of microRNAs with age and identified 263 microRNAs significantly associated with biological and chronological age alike. Top differentially expressed microRNAs based on biological age had a higher significance level than those based on chronological age, suggesting that biological age captures aspects of aging signals at the epigenetic level. We conclude that accelerated biological age for a given age is a predictor of major age-related morbidity, including dementia, among healthy elderly.

The association of proBNPage with manifestations of age-related cardiovascular, physical, and psychological impairment in community-dwelling older adults

NT-proB-type natriuretic peptide (NT-proBNP) serum concentration can be transformed by simple formulas into proBNPage, a surrogate of biological age strongly associated with chronological age, all-cause mortality, and disease count. This cross-sectional study aimed to assess whether proBNPage is also associated with other manifestations of the aging process in comparison with other variables. The study included 1117 noninstitutionalized older adults (73.1 ± 5.6 years, 537 men). Baseline measurements of serum NT-proBNP, erythrocyte sedimentation rate, hemoglobin, lymphocytes, and creatinine, which have previously been shown to be highly associated with both age and all-cause mortality, were performed. These variables were compared between subjects with and without manifestations of cardiovascular impairment (myocardial infarction (MI), stroke, peripheral artery disease (PAD), arterial revascularizations (AR)), physical impairment (long step test duration (LSTD), walking problems, falls, deficit in one or more activities of daily living), and psychological impairment (poor self-rating of health (PSRH), anxiety/depression, Mini Mental State Examination (MMSE) score < 24). ProBNPage (years) was independently associated (OR, 95% CI) with MI (1.08, 1.07-1.10), stroke (1.02, 1.00-1.05), PAD (1.04, 1.01-1.06), AR (1.06, 1.04-1.08), LSTD (1.03, 1.02-1.04), walking problems (1.02, 1.01-1.03), and PSRH (1.02, 1.01-1.02). For 5 of these 7 associations, the relationship was stronger than that of chronological age. In addition, proBNPage was univariately associated with MMSE score < 24, anxiety/depression, and falls. None of the other variables provided comparable performances. Thus, in addition to the known associations with mortality and disease count, proBNPage is also associated with cardiovascular manifestations as well as noncardiovascular manifestations of the aging process.

A high-throughput phenotyping algorithm is portable from adult to pediatric populations

OBJECTIVE

Multimodal automated phenotyping (MAP) is a scalable, high-throughput phenotyping method, developed using electronic health record (EHR) data from an adult population. We tested transportability of MAP to a pediatric population.

MATERIALS AND METHODS

Without additional feature engineering or supervised training, we applied MAP to a pediatric population enrolled in a biobank and evaluated performance against physician-reviewed medical records. We also compared performance of MAP at the pediatric institution and the original adult institution where MAP was developed, including for 6 phenotypes validated at both institutions against physician-reviewed medical records.

RESULTS

MAP performed equally well in the pediatric setting (average AUC 0.98) as it did at the general adult hospital system (average AUC 0.96). MAP's performance in the pediatric sample was similar across the 6 specific phenotypes also validated against gold-standard labels in the adult biobank.

CONCLUSIONS

MAP is highly transportable across diverse populations and has potential for wide-scale use.

Data mining of human plasma proteins generates a multitude of highly predictive aging clocks that reflect different aspects of aging

We previously identified 529 proteins that had been reported by multiple different studies to change their expression level with age in human plasma. In the present study, we measured the q-value and age coefficient of these proteins in a plasma proteomic dataset derived from 4263 individuals. A bioinformatics enrichment analysis of proteins that significantly trend toward increased expression with age strongly implicated diverse inflammatory processes. A literature search revealed that at least 64 of these 529 proteins are capable of regulating life span in an animal model. Nine of these proteins (AKT2, GDF11, GDF15, GHR, NAMPT, PAPPA, PLAU, PTEN, and SHC1) significantly extend life span when manipulated in mice or fish. By performing machine-learning modeling in a plasma proteomic dataset derived from 3301 individuals, we discover an ultra-predictive aging clock comprised of 491 protein entries. The Pearson correlation for this clock was 0.98 in the learning set and 0.96 in the test set while the median absolute error was 1.84 years in the learning set and 2.44 years in the test set. Using this clock, we demonstrate that aerobic-exercised trained individuals have a younger predicted age than physically sedentary subjects. By testing clocks associated with 1565 different Reactome pathways, we also show that proteins associated with signal transduction or the immune system are especially capable of predicting human age. We additionally generate a multitude of age predictors that reflect different aspects of aging. For example, a clock comprised of proteins that regulate life span in animal models accurately predicts age.