Deep biomarkers of human aging: Application of deep neural networks to biomarker development

Frailty and biological age. Which best describes our aging and longevity?

Frailty and Biological Age are two closely related concepts; however, frailty is a multisystem geriatric syndrome that applies to elderly subjects, whereas biological age is a gerontologic way to describe the rate of aging of each individual, which can be used from the beginning of the aging process, in adulthood. If frailty reaches less consensus on the definition, it is a term much more widely used than this of biological age, which shows a clearer definition but is scarcely employed in social and medical fields. In this review, we suggest that this Biological Age is the best to describe how we are aging and determine our longevity, and several examples support our proposal.

Targeting the epigenetically older individuals for geroprotective trials: the use of DNA methylation clocks

Chronological age is the most important risk factor for the incidence of age-related diseases. The pace of ageing determines the magnitude of that risk and can be expressed as biological age. Targeting fundamental pathways of human aging with geroprotectors has the potential to lower the biological age and therewith prolong the healthspan, the period of life one spends in good health. Target populations for geroprotective interventions should be chosen based on the ageing mechanisms being addressed and the expected effect of the geroprotector on the primary outcome. Biomarkers of ageing, such as DNA methylation age, can be used to select populations for geroprotective interventions and as a surrogate outcome. Here, the use of DNA methylation clocks for selecting target populations for geroprotective intervention is explored.

Higher blood biochemistry-based biological age developed by advanced deep learning techniques is associated with frailty in geriatric rehabilitation inpatients: RESORT

BACKGROUND

Accelerated biological ageing is a major underlying mechanism of frailty development. This study aimed to investigate if the biological age measured by a blood biochemistry-based ageing clock is associated with frailty in geriatric rehabilitation inpatients.

METHODS

Within the REStORing health of acutely unwell adulTs (RESORT) cohort, patients' biological age was measured by an ageing clock based on completed data of 30 routine blood test variables measured at rehabilitation admission. The delta of biological age minus chronological age (years) was calculated. Ordinal logistic regression and multinomial logistic regression were performed to evaluate the association of the delta of ages with frailty assessed by the Clinical Frailty Scale. Effect modification of Cumulative Illness Rating Scale (CIRS) score was tested.

RESULTS

A total of 1187 geriatric rehabilitation patients were included (median age: 83.4 years, IQR: 77.7-88.5; 57.4 % female). The biochemistry-based biological age was strongly correlated with chronological age (Spearman r = 0.883). After adjustment for age, sex and primary reasons for acute admission, higher biological age (per 1 year higher in delta of ages) was associated with more severe frailty at admission (OR: 1.053, 95 % CI:1.012-1.096) in patients who had a CIRS score of <12 not in patients with a CIRS score >12. The delta of ages was not associated with frailty change from admission to discharge. The specific frailty manifestations as cardiac, hematological, respiratory, renal, and endocrine conditions were associated with higher biological age.

CONCLUSION

Higher biological age was associated with severe frailty in geriatric rehabilitation inpatients with less comorbidity burden.

Association between biological aging and diabetic retinopathy

The impact of aging on diabetic retinopathy (DR) remains underestimated. The current study aimed to investigate the association between biological aging and DR, in contrast to chronological age (CA). Using the National Health and Nutrition Survey data from 2005 to 2008. Biological aging was evaluated through the biological age (BA) and phenotypic age (PA), which were calculated from clinical markers. DR was identified in participants with diabetes mellitus (DM) when they exhibited one or more retinal microaneurysms or retinal blot hemorrhages under retinal imaging, with or without the presence of more severe lesions. Survey-weighted multivariable logistic regression was performed, and the regression model was further fitted using restricted cubic splines. The discriminatory capability and clinical utility of the model were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Based on weighted analyses, of the 3100 participants included in this study, of which 162 had DR. In the adjusted model, BA (odds ratio [OR] = 1.12, 95% CI, 1.06-1.18) and PA (OR = 1.11, 95% CI, 1.07-1.14) were associated with DR, while CA was not significantly (OR = 1.01, 95% CI, 0.99-1.03). Narrowing the analysis to DM participants and adjusting for factors like insulin showed similar results. ROC and DCA analyses indicate that BA/PA predicted DR better than CA and offer greater clinical utility. The positive association between BA/PA and DR was consistent across subgroups despite potential interactions. Biological aging heightens DR risk, with BA/PA showing a stronger association than CA. Our findings underscored the importance of timely anti-aging interventions for preventing DR.

The association between blood biological age at rehabilitation admission and physical activity during rehabilitation in geriatric inpatients: RESORT

Geriatric rehabilitation inpatients have high levels of sedentary behaviour (SB) and low levels of physical activity (PA). Biological age predicted by blood biomarkers is indicative of adverse outcomes. The objective was to determine the association between blood biological age at rehabilitation admission and levels of SB and PA during rehabilitation in geriatric inpatients. Inpatients admitted to geriatric rehabilitation wards at the Royal Melbourne Hospital (Melbourne, Australia) from October 22, 2019, to March 29, 2020, in the REStORing health of acute unwell adulTs (RESORT) observational cohort were included. Blood biological age was predicted using SenoClock-BloodAge, a hematological ageing clock. Patients wore an inertial sensor to measure SB and PA. Logistic regression analyses were conducted. A total of 111 patients (57.7% female) with mean age 83.3 ± 7.5 years were included in the analysis. The mean blood biological age was 82.7 ± 8.4 years. Patients with 1-year higher blood biological age had higher odds of having high SB measured as non-upright time greater than 23 h/day (odds ratio (OR): 1.050, 95% confidence interval (CI): 1.000-1.102). Individuals having 1-year higher age deviation trended towards lower odds of having high levels of PA measured as stepping time greater than 7.4 min/day (OR: 0.916, CI: 0.836-1.005) and as greater than 19.5 sit-to-stand transitions/day (OR: 0.915, CI: 0.836-1.002). In conclusion, higher biological age was associated with higher levels of SB and trended towards lower PA. Incorporating blood biological age could facilitate resource allocation and the development of more tailored rehabilitation plans.

Deep neural network-estimated age using optical coherence tomography predicts mortality

The concept of biological age has emerged as a measurement that reflects physiological and functional decline with ageing. Here we aimed to develop a deep neural network (DNN) model that predicts biological age from optical coherence tomography (OCT). A total of 84,753 high-quality OCT images from 53,159 individuals in the UK Biobank were included, among which 12,631 3D-OCT images from 8,541 participants without any reported medical conditions at baseline were used to develop an age prediction model. For the remaining 44,618 participants, OCT age gap, the difference between the OCT-predicted age and chronological age, was calculated for each participant. Cox regression models assessed the association between OCT age gap and mortality. The DNN model predicted age with a mean absolute error of 3.27 years and showed a strong correlation of 0.85 with chronological age. After a median follow-up of 11.0 years (IQR 10.9-11.1 years), 2,429 deaths (5.44%) were recorded. For each 5-year increase in OCT age gap, there was an 8% increased mortality risk (hazard ratio [HR] = 1.08, CI:1.02-1.13, P = 0.004). Compared with an OCT age gap within ± 4 years, OCT age gap less than minus 4 years was associated with a 16% decreased mortality risk (HR = 0.84, CI: 0.75-0.94, P = 0.002) and OCT age gap more than 4 years showed an 18% increased risk of death incidence (HR = 1.18, CI: 1.02-1.37, P = 0.026). OCT imaging could serve as an ageing biomarker to predict biological age with high accuracy and the OCT age gap, defined as the difference between the OCT-predicted age and chronological age, can be used as a marker of the risk of mortality.

Towards personalized nicotinamide mononucleotide (NMN) supplementation: Nicotinamide adenine dinucleotide (NAD) concentration

Nicotinamide mononucleotide (NMN) is a precursor of nicotinamide adenine dinucleotide (NAD), which declines with age. Supplementation of NMN has been shown to improve blood NAD concentration. However, the optimal NMN dose remains unclear. This is a post-hoc analysis of a double-blinded clinical trial involving 80 generally healthy adults aged 40-65 years. The participants received a placebo or daily 300 mg, 600 mg, or 900 mg NMN for 60 days. Blood NAD concentration, blood biological age, homeostatic model assessment for insulin resistance, 6-minute walk test, and 36-item short-form survey (SF-36) were measured at baseline and after supplement. A significant dose-dependent increase in NAD concentration change (NADΔ) was observed following NMN supplementation, with a large coefficient of variation (29.2-113.3%) within group. The increase in NADΔ was associated with an improvement in the walking distance of 6-minute walk test and the SF-36 score. The median effect dose of NADΔ for the 6-minute walk test and SF-36 score was 15.7 nmol/L (95% CI: 10.9-20.5 nmol/L) and 13.5 nmol/L (95% CI; 10.5-16.5 nmol/L), respectively. Because of the high interindividual variability of the NADΔ after NMN supplementation, monitoring NAD concentration can provide valuable insights for tailoring personalized dosage regimens and optimizing NMN utilization.

Application of AI in biological age prediction

The development of anti-aging interventions requires quantitative measurement of biological age. Machine learning models, known as "aging clocks," are built by leveraging diverse aging biomarkers that vary across lifespan to predict biological age. In addition to traditional aging clocks harnessing epigenetic signatures derived from bulk samples, emerging technologies allow the biological age estimating at single-cell level to dissect cellular diversity in aging tissues. Moreover, imaging-based aging clocks are increasingly employed with the advantage of non-invasive measurement, making it suitable for large-scale human cohort studies. To fully capture the features in the ever-growing multi-modal and high-dimensional aging-related data and uncover disease associations, deep-learning based approaches, which are effective to learn complex and non-linear relationships without relying on pre-defined features, are increasingly applied. The use of big data and AI-based aging clocks has achieved high accuracy, interpretability and generalizability, guiding clinical applications to delay age-related diseases and extend healthy lifespans.

The biological age model for evaluating the degree of aging in centenarians

BACKGROUND

Biological age (BA) has been used to assess individuals' aging conditions. However, few studies have evaluated BA models' applicability in centenarians.

METHODS

Important organ function examinations were performed in 1798 cases of the longevity population (80∼115 years old) in Hainan, China. Eighty indicators were selected that responded to nutritional status, cardiovascular function, liver and kidney function, bone metabolic function, endocrine system, hematological system, and immune system. BA models were constructed using multiple linear regression (MLR), principal component analysis (PCA), Klemera and Doubal method (KDM), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and light gradient boosting machine (lightGBM) methods. A tenfold crossover validated the efficacy of models.

RESULTS

A total of 1398 participants were enrolled, of whom centenarians accounted for 49.21%. Seven aging markers were obtained, including estimated glomerular filtration rate, albumin, pulse pressure, calf circumference, body surface area, fructosamine, and complement 4. Eight BA models were successfully constructed, namely MLR, PCA, KDM1, KDM2, RF, SVM, XGBoost and lightGBM, which had the worst R2 of 0.45 and the best R2 of 0.92. The best R2 for cross-validation was KDM2 (0.89), followed by PCA (0.62).

CONCLUSION

In this study, we successfully applied eight methods, including traditional methods and machine learning, to construct models of biological age, and the performance varied among the models.

Accurate estimation of biological age and its application in disease prediction using a multimodal image Transformer system

Aging in an individual refers to the temporal change, mostly decline, in the body's ability to meet physiological demands. Biological age (BA) is a biomarker of chronological aging and can be used to stratify populations to predict certain age-related chronic diseases. BA can be predicted from biomedical features such as brain MRI, retinal, or facial images, but the inherent heterogeneity in the aging process limits the usefulness of BA predicted from individual body systems. In this paper, we developed a multimodal Transformer-based architecture with cross-attention which was able to combine facial, tongue, and retinal images to estimate BA. We trained our model using facial, tongue, and retinal images from 11,223 healthy subjects and demonstrated that using a fusion of the three image modalities achieved the most accurate BA predictions. We validated our approach on a test population of 2,840 individuals with six chronic diseases and obtained significant difference between chronological age and BA (AgeDiff) than that of healthy subjects. We showed that AgeDiff has the potential to be utilized as a standalone biomarker or conjunctively alongside other known factors for risk stratification and progression prediction of chronic diseases. Our results therefore highlight the feasibility of using multimodal images to estimate and interrogate the aging process.

The ticking of aging clocks

Computational models that measure biological age and aging rate regardless of chronological age are called aging clocks. The underlying counting mechanisms of the intrinsic timers of these clocks are still unclear. Molecular mediators and determinants of aging rate point to the key roles of DNA damage, epigenetic drift, and inflammation. Persistent DNA damage leads to cellular senescence and the senescence-associated secretory phenotype (SASP), which induces cytotoxic immune cell infiltration; this further induces DNA damage through reactive oxygen and nitrogen species (RONS). I discuss the possibility that DNA damage (or the response to it, including epigenetic changes) is the fundamental counting unit of cell cycles and cellular senescence, that ultimately accounts for cell composition changes and functional decline in tissues, as well as the key intervention points.

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.

ResnetAge: A Resnet-Based DNA Methylation Age Prediction Method

Aging is a significant contributing factor to degenerative diseases such as cancer. The extent of DNA methylation in human cells indicates the aging process and screening for age-related methylation sites can be used to construct epigenetic clocks. Thereby, it can be a new aging-detecting marker for clinical diagnosis and treatments. Predicting the biological age of human individuals is conducive to the study of physical aging problems. Although many researchers have developed epigenetic clock prediction methods based on traditional machine learning and even deep learning, higher prediction accuracy is still required to match the clinical applications. Here, we proposed an epigenetic clock prediction method based on a Resnet neuro networks model named ResnetAge. The model accepts 22,278 CpG sites as a sample input, supporting both the Illumina 27K and 450K identification frameworks. It was trained using 32 public datasets containing multiple tissues such as whole blood, saliva, and mouth. The Mean Absolute Error (MAE) of the training set is 1.29 years, and the Median Absolute Deviation (MAD) is 0.98 years. The Mean Absolute Error (MAE) of the validation set is 3.24 years, and the Median Absolute Deviation (MAD) is 2.3 years. Our method has higher accuracy in age prediction in comparison with other methylation-based age prediction methods.

ExplaiNAble BioLogical Age (ENABL Age): an artificial intelligence framework for interpretable biological age

BACKGROUND

Biological age is a measure of health that offers insights into ageing. The existing age clocks, although valuable, often trade off accuracy and interpretability. We introduce ExplaiNAble BioLogical Age (ENABL Age), a computational framework that combines machine-learning models with explainable artificial intelligence (XAI) methods to accurately estimate biological age with individualised explanations.

METHODS

To construct the ENABL Age clock, we first predicted an age-related outcome (eg, all-cause or cause-specific mortality), and then rescaled these predictions to estimate biological age, using UK Biobank and National Health and Nutrition Examination Survey (NHANES) datasets. We adapted existing XAI methods to decompose individual ENABL Ages into contributing risk factors. For broad accessibility, we developed two versions: ENABL Age-L, based on blood tests, and ENABL Age-Q, based on questionnaire characteristics. Finally, we validated diverse ageing mechanisms captured by each ENABL Age clock through genome-wide association studies (GWAS) association analyses.

FINDINGS

Our ENABL Age clock was significantly correlated with chronological age (r=0·7867, p<0·0001 for UK Biobank; r=0·7126, p<0·0001 for NHANES). These clocks distinguish individuals who are healthy (ie, their ENABL Age is lower than their chronological age) from those who are unhealthy (ie, their ENABL Age is higher than their chronological age), predicting mortality more effectively than existing clocks. Groups of individuals who were unhealthy showed approximately three to 12 times higher log hazard ratio than healthy groups, as per ENABL Age. The clocks achieved high mortality prediction power with an area under the receiver operating characteristic curve of 0·8179 for 5-year mortality and 0·8115 for 10-year mortality on the UK Biobank dataset, and 0·8935 for 5-year mortality and 0·9107 for 10-year mortality on the NHANES dataset. The individualised explanations that revealed the contribution of specific characteristics to ENABL Age provided insights into the important characteristics for ageing. An association analysis with risk factors and ageing-related morbidities and GWAS results on ENABL Age clocks trained on different mortality causes showed that each clock captures distinct ageing mechanisms.

INTERPRETATION

ENABL Age brings an important leap forward in the application of XAI for interpreting biological age clocks. ENABL Age also carries substantial potential in practical settings, assisting medical professionals in untangling the complexity of ageing mechanisms, and potentially becoming a valuable tool in informed clinical decision-making processes.

FUNDING

National Science Foundation and National Institutes of Health.

Organ aging signatures in the plasma proteome track health and disease

Animal studies show aging varies between individuals as well as between organs within an individual1-4, but whether this is true in humans and its effect on age-related diseases is unknown. We utilized levels of human blood plasma proteins originating from specific organs to measure organ-specific aging differences in living individuals. Using machine learning models, we analysed aging in 11 major organs and estimated organ age reproducibly in five independent cohorts encompassing 5,676 adults across the human lifespan. We discovered nearly 20% of the population show strongly accelerated age in one organ and 1.7% are multi-organ agers. Accelerated organ aging confers 20-50% higher mortality risk, and organ-specific diseases relate to faster aging of those organs. We find individuals with accelerated heart aging have a 250% increased heart failure risk and accelerated brain and vascular aging predict Alzheimer's disease (AD) progression independently from and as strongly as plasma pTau-181 (ref. 5), the current best blood-based biomarker for AD. Our models link vascular calcification, extracellular matrix alterations and synaptic protein shedding to early cognitive decline. We introduce a simple and interpretable method to study organ aging using plasma proteomics data, predicting diseases and aging effects.

LensAge index as a deep learning-based biological age for self-monitoring the risks of age-related diseases and mortality

Age is closely related to human health and disease risks. However, chronologically defined age often disagrees with biological age, primarily due to genetic and environmental variables. Identifying effective indicators for biological age in clinical practice and self-monitoring is important but currently lacking. The human lens accumulates age-related changes that are amenable to rapid and objective assessment. Here, using lens photographs from 20 to 96-year-olds, we develop LensAge to reflect lens aging via deep learning. LensAge is closely correlated with chronological age of relatively healthy individuals (R2 > 0.80, mean absolute errors of 4.25 to 4.82 years). Among the general population, we calculate the LensAge index by contrasting LensAge and chronological age to reflect the aging rate relative to peers. The LensAge index effectively reveals the risks of age-related eye and systemic disease occurrence, as well as all-cause mortality. It outperforms chronological age in reflecting age-related disease risks (p < 0.001). More importantly, our models can conveniently work based on smartphone photographs, suggesting suitability for routine self-examination of aging status. Overall, our study demonstrates that the LensAge index may serve as an ideal quantitative indicator for clinically assessing and self-monitoring biological age in humans.

Central obesity and its association with retinal age gap: insights from the UK Biobank study

BACKGROUND

Conflicting evidence exists on the association between ageing and obesity. Retinal age derived from fundus images has been validated as a novel biomarker of ageing. In this study, we aim to investigate the association between different anthropometric phenotypes based on body mass index (BMI) and waist circumference (WC) and the retinal age gap (retinal age minus chronological age).

METHODS

A total of 35,550 participants with BMI, WC and qualified retinal imaging data available were included to investigate the association between anthropometric groups and retinal ageing. Participants were stratified into 7 different body composition groups based on BMI and WC (Normal-weight/Normal WC, Overweight/Normal WC, Mild obesity/Normal WC, Normal-weight/High WC, Overweight/High WC, Mild obesity/High WC, and Severe obesity/High WC). Linear regression and logistic regression models were fitted to investigate the association between the seven anthropometric groups and retinal age gap as continuous and categorical outcomes, respectively.

RESULTS

A total of 35,550 participants (55.6% females) with a mean age 56.8 ± 8.04 years were included in the study. Individuals in the Overweight/High WC, Mild obesity/High WC and Severe obesity/High WC groups were associated with an increase in the retinal age gap, compared with those in the Normal Weight/Normal WC group (β = 0.264, 95% CI: 0.105-0.424, P =0.001; β = 0.226, 95% CI: 0.082-0.371, P = 0.002; β = 0.273, 95% CI: 0.081-0.465, P = 0.005; respectively) in fully adjusted models. Similar findings were noted in the association between the anthropometric groups and retinal ageing process as a categorical outcome.

CONCLUSION

A significant positive association exists between central obesity and accelerated ageing indexed by retinal age gaps, highlighting the significance of maintaining a healthy body shape.

An efficient machine learning framework to identify important clinical features associated with pulmonary embolism

A misdiagnosis of pulmonary embolism (PE) can have severe consequences such as disability or death. It's crucial to accurately identify key clinical features of PE in clinical practice to promptly identify potential PE patients who may present asymptomatically, and to prevent misdiagnosing PE as asthma exacerbation in patients with symptoms like dyspnea or chest pain. However, reliably identifying these important features can be challenging due to many factors influencing the likelihood of PE development in complex fashions (e.g., the interactions among these factors). To address this difficulty, we presented an effective framework using the deep neural network (DNN) model and the permutation-based feature importance test (PermFIT) procedure, i.e., PermFIT-DNN. We applied the PermFIT-DNN framework to the analysis of data from a PE study for asthma exacerbation patients. Our analysis results show that the PermFIT-DNN framework can robustly identify key features for classifying PE status. The important features identified can also aid in accurately predicting the PE risk.

Associations between Differential Aging and Lifestyle, Environment, Current, and Future Health Conditions: Findings from Canadian Longitudinal Study on Aging

INTRODUCTION

An aging population will bring a pressing challenge for the healthcare system. Insights into promoting healthy longevity can be gained by quantifying the biological aging process and understanding the roles of modifiable lifestyle and environmental factors, and chronic disease conditions.

METHODS

We developed a biological age (BioAge) index by applying multiple state-of-art machine learning models based on easily accessible blood test data from the Canadian Longitudinal Study of Aging (CLSA). The BioAge gap, which is the difference between BioAge index and chronological age, was used to quantify the differential aging, i.e., the difference between biological and chronological age, of the CLSA participants. We further investigated the associations between the BioAge gap and lifestyle, environmental factors, and current and future health conditions.

RESULTS

BioAge gap had strong associations with existing adverse health conditions (e.g., cancers, cardiovascular diseases, diabetes, and kidney diseases) and future disease onset (e.g., Parkinson's disease, diabetes, and kidney diseases). We identified that frequent consumption of processed meat, pork, beef, and chicken, poor outcomes in nutritional risk screening, cigarette smoking, exposure to passive smoking are associated with positive BioAge gap ("older" BioAge than expected). We also identified several modifiable factors, including eating fruits, legumes, vegetables, related to negative BioAge gap ("younger" BioAge than expected).

CONCLUSIONS

Our study shows that a BioAge index based on easily accessible blood tests has the potential to quantify the differential biological aging process that can be associated with current and future adverse health events. The identified risk and protective factors for differential aging indicated by BioAge gap are informative for future research and guidelines to promote healthy longevity.

Small immunological clocks identified by deep learning and gradient boosting

Background

The aging process affects all systems of the human body, and the observed increase in inflammatory components affecting the immune system in old age can lead to the development of age-associated diseases and systemic inflammation.

Results

We propose a small clock model SImAge based on a limited number of immunological biomarkers. To regress the chronological age from cytokine data, we first use a baseline Elastic Net model, gradient-boosted decision trees models, and several deep neural network architectures. For the full dataset of 46 immunological parameters, DANet, SAINT, FT-Transformer and TabNet models showed the best results for the test dataset. Dimensionality reduction of these models with SHAP values revealed the 10 most age-associated immunological parameters, taken to construct the SImAge small immunological clock. The best result of the SImAge model shown by the FT-Transformer deep neural network model has mean absolute error of 6.94 years and Pearson ρ = 0.939 on the independent test dataset. Explainable artificial intelligence methods allow for explaining the model solution for each individual participant.

Conclusions

We developed an approach to construct a model of immunological age based on just 10 immunological parameters, coined SImAge, for which the FT-Transformer deep neural network model had proved to be the best choice. The model shows competitive results compared to the published studies on immunological profiles, and takes a smaller number of features as an input. Neural network architectures outperformed gradient-boosted decision trees, and can be recommended in the further analysis of immunological profiles.

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.

Artificial intelligence for the prevention and prediction of colorectal neoplasms

BACKGROUND

Colonoscopy is a useful as a cancer screening test. However, in countries with limited medical resources, there are restrictions on the widespread use of endoscopy. Non-invasive screening methods to determine whether a patient requires a colonoscopy are thus desired. Here, we investigated whether artificial intelligence (AI) can predict colorectal neoplasia.

METHODS

We used data from physical exams and blood analyses to determine the incidence of colorectal polyp. However, these features exhibit highly overlapping classes. The use of a kernel density estimator (KDE)-based transformation improved the separability of both classes.

RESULTS

Along with an adequate polyp size threshold, the optimal machine learning (ML) models' performance provided 0.37 and 0.39 Matthews correlation coefficient (MCC) for the datasets of men and women, respectively. The models exhibit a higher discrimination than fecal occult blood test with 0.047 and 0.074 MCC for men and women, respectively.

CONCLUSION

The ML model can be chosen according to the desired polyp size discrimination threshold, may suggest further colorectal screening, and possible adenoma size. The KDE feature transformation could serve to score each biomarker and background factors (health lifestyles) to suggest measures to be taken against colorectal adenoma growth. All the information that the AI model provides can lower the workload for healthcare providers and be implemented in health care systems with scarce resources. Furthermore, risk stratification may help us to optimize the efficiency of resources for screening colonoscopy.

Stress, diet, exercise: Common environmental factors and their impact on epigenetic age

Epigenetic aging clocks have gained significant attention as a tool for predicting age-related health conditions in clinical and research settings. They have enabled geroscientists to study the underlying mechanisms of aging and assess the effectiveness of anti-aging therapies, including diet, exercise and environmental exposures. This review explores the effects of modifiable lifestyle factors' on the global DNA methylation landscape, as seen by aging clocks. We also discuss the underlying mechanisms through which these factors contribute to biological aging and provide comments on what these findings mean for people willing to build an evidence-based pro-longevity lifestyle.

Role of endogenous and exogenous antioxidants in risk of six cancers: evidence from the Mendelian randomization study

Background: Although oxidative stress is known to contribute to cancer, and endogenous and exogenous antioxidants are thought to prevent tumorigenesis by suppressing oxidative stress-induced DNA damage, antioxidants have also been reported to show negative effects on tumor formation, necessitating characterization of the causal associations between antioxidants and cancer risk. Methods: In this study, Mendelian randomization (MR) analysis, primarily inverse-variance weighted MR, was used to assess the causal effect of six endogenous and five exogenous diet-derived antioxidants on the risk of six cancers. MR-Egger intercept test and Cochran's Q statistic were utilized to assess pleiotropy and heterogeneity, respectively. Results: For endogenous antioxidants, a bidirectional two-sample MR analysis was conducted. Our findings suggested that serum albumin has a negative causal association with the risk of prostate cancer [odds ratio (OR) = 0.78, 95% confidence interval (CI): 0.68-0.91, p = 0.001]. The risks of the six cancers showed no significant associations with endogenous antioxidants in the converse MR analysis. For exogenous antioxidants, the unidirectional two-sample MR analysis exhibited a nominal relationship between the serum retinol level and non-small-cell lung cancer risk (OR = 0.29, 95% CI: 0.11-0.76, p = 0.011). Conclusions: Thus, our study revealed the protective effects of genetic susceptibility to high circulating albumin levels on prostate cancer, providing potential targeted interventions for prostate cancer prevention.

Precious1GPT: multimodal transformer-based transfer learning for aging clock development and feature importance analysis for aging and age-related disease target discovery

Aging is a complex and multifactorial process that increases the risk of various age-related diseases and there are many aging clocks that can accurately predict chronological age, mortality, and health status. These clocks are disconnected and are rarely fit for therapeutic target discovery. In this study, we propose a novel approach to multimodal aging clock we call Precious1GPT utilizing methylation and transcriptomic data for interpretable age prediction and target discovery developed using a transformer-based model and transfer learning for case-control classification. While the accuracy of the multimodal transformer is lower within each individual data type compared to the state of art specialized aging clocks based on methylation or transcriptomic data separately it may have higher practical utility for target discovery. This method provides the ability to discover novel therapeutic targets that hypothetically may be able to reverse or accelerate biological age providing a pathway for therapeutic drug discovery and validation using the aging clock. In addition, we provide a list of promising targets annotated using the PandaOmics industrial target discovery platform.

Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

BACKGROUND

Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity.

OBJECTIVE

This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers.

METHODS

This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed.

RESULTS

This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials.

CONCLUSION

mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.

Discovering small-molecule senolytics with deep neural networks

The accumulation of senescent cells is associated with aging, inflammation and cellular dysfunction. Senolytic drugs can alleviate age-related comorbidities by selectively killing senescent cells. Here we screened 2,352 compounds for senolytic activity in a model of etoposide-induced senescence and trained graph neural networks to predict the senolytic activities of >800,000 molecules. Our approach enriched for structurally diverse compounds with senolytic activity; of these, three drug-like compounds selectively target senescent cells across different senescence models, with more favorable medicinal chemistry properties than, and selectivity comparable to, those of a known senolytic, ABT-737. Molecular docking simulations of compound binding to several senolytic protein targets, combined with time-resolved fluorescence energy transfer experiments, indicate that these compounds act in part by inhibiting Bcl-2, a regulator of cellular apoptosis. We tested one compound, BRD-K56819078, in aged mice and found that it significantly decreased senescent cell burden and mRNA expression of senescence-associated genes in the kidneys. Our findings underscore the promise of leveraging deep learning to discover senotherapeutics.

Biomarkers of aging

Aging biomarkers are a combination of biological parameters to (i) assess age-related changes, (ii) track the physiological aging process, and (iii) predict the transition into a pathological status. Although a broad spectrum of aging biomarkers has been developed, their potential uses and limitations remain poorly characterized. An immediate goal of biomarkers is to help us answer the following three fundamental questions in aging research: How old are we? Why do we get old? And how can we age slower? This review aims to address this need. Here, we summarize our current knowledge of biomarkers developed for cellular, organ, and organismal levels of aging, comprising six pillars: physiological characteristics, medical imaging, histological features, cellular alterations, molecular changes, and secretory factors. To fulfill all these requisites, we propose that aging biomarkers should qualify for being specific, systemic, and clinically relevant.

Using Inflammatory Biological Age To Evaluate the Preventing Aging Effect of a Polyphenol-Probiotic-Enhanced Dietary Pattern in Adults Aged 50 Years and Older

A high-compliance dietary intervention was conducted for 2 weeks in adults aged 50 years and older to investigate the preventing aging effects of a polyphenol-probiotic-enhanced diet (P-diet) by using inflammatory biological age (IBA). Following the P-diet, levels of interleukin-6 (IL-6), IL-10, and C-reactive protein were reduced. These effects were accompanied by a significant increase in the richness of Lactobacillus and Bifidobacterium and decrease in CAG_56, as well as an increase in butyrate and acetate and decrease in lysine, uracil, and valine. We optimized a model by a back propagation artificial neural network to evaluate the degree of aging, with an R² of 0.68. After the P-diet intervention, IBA was younger than chronological age and the inflammatory aging potential (Δage) was observably reduced by 90.12%, with change in Δage having a direct negative association with Akkermansia. Overall, P-diet may alleviate chronic low-grade inflammation and thus prevent the procession of inflammatory aging.

A deep neural network framework to derive interpretable decision rules for accurate traumatic brain injury identification of infants

OBJECTIVE

We aimed to develop a robust framework to model the complex association between clinical features and traumatic brain injury (TBI) risk in children under age two, and identify significant features to derive clinical decision rules for triage decisions.

METHODS

In this retrospective study, four frequently used machine learning models, i.e., support vector machine (SVM), random forest (RF), deep neural network (DNN), and XGBoost (XGB), were compared to identify significant clinical features from 24 input features associated with the TBI risk in children under age two under the permutation feature importance test (PermFIT) framework by using the publicly available data set from the Pediatric Emergency Care Applied Research Network (PECARN) study. The prediction accuracy was determined by comparing the predicted TBI status with the computed tomography (CT) scan results since CT scan is the gold standard for diagnosing TBI.

RESULTS

At a significance level of [Formula: see text], DNN, RF, XGB, and SVM identified 9, 1, 2,  and 4 significant features, respectively. In a comparison of accuracy (Accuracy), the area under the curve (AUC), and the precision-recall area under the curve (PR-AUC), the permutation feature importance test for DNN model was the most powerful framework for identifying significant features and outperformed other methods, i.e., RF, XGB, and SVM, with Accuracy, AUC, and PR-AUC as 0.915, 0.794, and 0.974, respectively.

CONCLUSION

These results indicate that the PermFIT-DNN framework robustly identifies significant clinical features associated with TBI status and improves prediction performance. The findings could be used to inform the development of clinical decision tools designed to inform triage decisions.

Contribution of A-to-I RNA editing, M6A RNA Methylation, and Alternative Splicing to physiological brain aging and neurodegenerative diseases

Aging is a physiological and progressive phenomenon in all organisms' life cycle, characterized by the accumulation of degenerative processes triggered by several alterations within molecular pathways. These changes compromise cell fate, resulting in the loss of functions in tissues throughout the body, including the brain. Physiological brain aging has been linked to structural and functional alterations, as well as to an increased risk of neurodegenerative diseases. Post-transcriptional RNA modifications modulate mRNA coding properties, stability, translatability, expanding the coding capacity of the genome, and are involved in all cellular processes. Among mRNA post-transcriptional modifications, the A-to-I RNA editing, m6A RNA Methylation and Alternative Splicing play a critical role in all the phases of a neuronal cell life cycle and alterations in their mechanisms of action significantly contribute to aging and neurodegeneration. Here we review our current understanding of the contribution of A-to-I RNA editing, m6A RNA Methylation, and Alternative Splicing to physiological brain aging process and neurodegenerative diseases.

Retinal age gap as a predictive biomarker for mortality risk

AIM

To develop a deep learning (DL) model that predicts age from fundus images (retinal age) and to investigate the association between retinal age gap (retinal age predicted by DL model minus chronological age) and mortality risk.

METHODS

A total of 80 169 fundus images taken from 46 969 participants in the UK Biobank with reasonable quality were included in this study. Of these, 19 200 fundus images from 11 052 participants without prior medical history at the baseline examination were used to train and validate the DL model for age prediction using fivefold cross-validation. A total of 35 913 of the remaining 35 917 participants had available mortality data and were used to investigate the association between retinal age gap and mortality.

RESULTS

The DL model achieved a strong correlation of 0.81 (p<0·001) between retinal age and chronological age, and an overall mean absolute error of 3.55 years. Cox regression models showed that each 1 year increase in the retinal age gap was associated with a 2% increase in risk of all-cause mortality (hazard ratio (HR)=1.02, 95% CI 1.00 to 1.03, p=0.020) and a 3% increase in risk of cause-specific mortality attributable to non-cardiovascular and non-cancer disease (HR=1.03, 95% CI 1.00 to 1.05, p=0.041) after multivariable adjustments. No significant association was identified between retinal age gap and cardiovascular- or cancer-related mortality.

CONCLUSIONS

Our findings indicate that retinal age gap might be a potential biomarker of ageing that is closely related to risk of mortality, implying the potential of retinal image as a screening tool for risk stratification and delivery of tailored interventions.

Biological age models based on a healthy Han Chinese population

BACKGROUND

Biological age (BA) may reflect the actual aging state in humans better than chronological age (CA). The study aimed to construct BA models suitable for the Chinese Han population by selecting appropriate aging markers and evaluation methods.

METHODS

A total of 1207 individuals (21∼91 years) from the Han Chinese population in Beijing were examined for essential organ functions, and 156 cardiovascular, pulmonary function, and atherosclerotic indices and clinical and genetic factors were used as candidate markers of aging. BA models were constructed using multiple linear regression (MLR), principal component analysis (PCA), and the Klemera and Doubal method (KDM). Models were internally and externally validated using cross-validation and disease populations.

RESULTS

Nine aging markers were selected. Two MLR, three PCA, and three KDM models were successfully constructed. External validation showed that the difference between CA and BA was most significant in the PCA3 and KDM2 models, while there was no significant difference in the MLR1 and MLR2 models; the fitted lines for BA in the disease population were higher than those in the healthy population in the MLR1, MLR2, KDM1, and KDM2 models, while the other models showed the opposite.

CONCLUSIONS

Based on a healthy population in Beijing, nine markers representing multiple organ/system functions were screened from the candidate markers, eight methods were successfully used to construct BA models, and the KDM2 model was found to potentially be more appropriate for assessing BA in the Chinese Han population.

Association between the Inflammatory Potential of the Diet and Biological Aging: A Cross-Sectional Analysis of 4510 Adults from the Moli-Sani Study Cohort

Chronological age (CA) may not accurately reflect the health status of an individual. Rather, biological age (BA) or hypothetical underlying "functional" age has been proposed as a relevant indicator of healthy aging. Observational studies have found that decelerated biological aging or Δage (BA-CA) is associated with a lower risk of disease and mortality. In general, CA is associated with low-grade inflammation, a condition linked to the risk of the incidence of disease and overall cause-specific mortality, and is modulated by diet. To address the hypothesis that diet-related inflammation is associated with Δage, a cross-sectional analysis of data from a sub-cohort from the Moli-sani Study (2005-2010, Italy) was performed. The inflammatory potential of the diet was measured using the Energy-adjusted Dietary Inflammatory Index (E-DII^TM) and a novel literature-based dietary inflammation score (DIS). A deep neural network approach based on circulating biomarkers was used to compute BA, and the resulting Δage was fit as the dependent variable. In 4510 participants (men 52.0%), the mean of CA (SD) was 55.6 y (±11.6), BA 54.8 y (±8.6), and Δage -0.77 (±7.7). In a multivariable-adjusted analysis, an increase in E-DII^TM and DIS scores led to an increase in Δage (β = 0.22; 95%CI 0.05, 0.38; β = 0.27; 95%CI 0.10, 0.44, respectively). We found interaction for DIS by sex and for E-DII^TM by BMI. In conclusion, a pro-inflammatory diet is associated with accelerated biological aging, which likely leads to an increased long-term risk of inflammation-related diseases and mortality.

Digital Health: Today's Solutions and Tomorrow's Impact

Artificial intelligence (AI) is becoming an indispensable tool to augment decision making in different health care settings and by various members of the patient pathway, including the patient. AI provides the ability to optimize data to bring clinical decision support for clinicians and laboratorians and/or empower patients to actively participate in their own health care. Though there are many examples of AI in health care, the exact role of AI and digital health solutions is still taking shape. Although AI will not replace the clinician, those who do not adopt AI may in time, be left behind.

Blood Markers of Biological Age Evaluates Clinic Complex Medical Spa Programs

BACKGROUND

Kivach Clinic has developed a special medical spa program to prevent aging-related conditions in metabolic, cardio-vascular, and neurological states. Spa programs modify diet, physical activity, and lymphatic drainage, as it deteriorates with aging. We investigated its influence on the blood markers of biological age of patients during their stay to objectify the potential of spa treatment for influencing the risk of age-related events.

METHODS

The artificial deep learning model Aging.ai 3.0 was based on blood parameters. The change in the biological age of 43 patients was assessed after their 14-day spa treatment at Kivach Clinic.

RESULTS

Biological age decreased in 29 patients (median decrease: 8 years, mean: 8.83 years), increased in 10 patients (median increase: 3 years, mean: 5.33 years) and remained unchanged in 4 patients. Overall mean values for the entire patient group were as follows: median value was -3 years, and mean was -4.79 ± 1.2 years (p-value = 0.00025, t-test).

CONCLUSIONS

The capability of specially selected medical spa treatment to reduce human biological age (assessed by Aging.AI 3.0) has been established.

Progress in biological age research

Biological age (BA) is a common model to evaluate the function of aging individuals as it may provide a more accurate measure of the extent of human aging than chronological age (CA). Biological age is influenced by the used biomarkers and standards in selected aging biomarkers and the statistical method to construct BA. Traditional used BA estimation approaches include multiple linear regression (MLR), principal component analysis (PCA), Klemera and Doubal's method (KDM), and, in recent years, deep learning methods. This review summarizes the markers for each organ/system used to construct biological age and published literature using methods in BA research. Future research needs to explore the new aging markers and the standard in select markers and new methods in building BA models.

A pan-tissue DNA-methylation epigenetic clock based on deep learning

Several age predictors based on DNA methylation, dubbed epigenetic clocks, have been created in recent years, with the vast majority based on regularized linear regression. This study explores the improvement in the performance and interpretation of epigenetic clocks using deep learning. First, we gathered 142 publicly available data sets from several human tissues to develop AltumAge, a neural network framework that is a highly accurate and precise age predictor. Compared to ElasticNet, AltumAge performs better for within-data set and cross-data set age prediction, being particularly more generalizable in older ages and new tissue types. We then used deep learning interpretation methods to learn which methylation sites contributed to the final model predictions. We observe that while most important CpG sites are linearly related to age, some highly-interacting CpG sites can influence the relevance of such relationships. Using chromatin annotations, we show that the CpG sites with the highest contribution to the model predictions were related to gene regulatory regions in the genome, including proximity to CTCF binding sites. We also found age-related KEGG pathways for genes containing these CpG sites. Lastly, we performed downstream analyses of AltumAge to explore its applicability and compare its age acceleration with Horvath’s 2013 model. We show that our neural network approach predicts higher age acceleration for tumors, for cells that exhibit age-related changes in vitro, such as immune and mitochondrial dysfunction, and for samples from patients with multiple sclerosis, type 2 diabetes, and HIV, among other conditions. Altogether, our neural network approach provides significant improvement and flexibility compared to current epigenetic clocks for both performance and model interpretability.

Biological Age Predictors: The Status Quo and Future Trends

There is no single universal biomarker yet to estimate overall health status and longevity prospects. Moreover, a consensual approach to the very concept of aging and the means of its assessment are yet to be developed. Markers of aging could facilitate effective health control, more accurate life expectancy estimates, and improved health and quality of life. Clinicians routinely use several indicators that could be biomarkers of aging. Duly validated in a large cohort, models based on a combination of these markers could provide a highly accurate assessment of biological age and the pace of aging. Biological aging is a complex characteristic of chronological age (usually), health-to-age concordance, and medically estimated life expectancy. This study is a review of the most promising techniques that could soon be used in routine clinical practice. Two main selection criteria were applied: a sufficient sample size and reliability based on validation. The selected biological age calculators were grouped according to the type of biomarker used: (1) standard clinical and laboratory markers; (2) molecular markers; and (3) epigenetic markers. The most accurate were the calculators, which factored in a variety of biomarkers. Despite their demonstrated effectiveness, most of them require further improvement and cannot yet be considered for use in standard clinical practice. To illustrate their clinical application, we reviewed their use during the COVID-19 pandemic.

An evaluation of aging measures: from biomarkers to clocks

With the increasing number of aged population and growing burden of healthy aging demands, a rational standard for evaluation aging is in urgent need. The advancement of medical testing technology and the prospering of artificial intelligence make it possible to evaluate the biological status of aging from a more comprehensive view. In this review, we introduced common aging biomarkers and concluded several famous aging clocks. Aging biomarkers reflect changes in the organism at a molecular or cellular level over time while aging clocks tend to be more of a generalization of the overall state of the organism. We expect to construct a framework for aging evaluation measurement from both micro and macro perspectives. Especially, population-specific aging clocks and multi-omics aging clocks may better fit the demands to evaluate aging in a comprehensive and multidimensional manner and make a detailed classification to represent different aging rates at tissue/organ levels. This framework will promisingly provide a crucial basis for disease diagnosis and intervention assessment in geroscience.

Unsupervised learning of aging principles from longitudinal data

Age is the leading risk factor for prevalent diseases and death. However, the relation between age-related physiological changes and lifespan is poorly understood. We combined analytical and machine learning tools to describe the aging process in large sets of longitudinal measurements. Assuming that aging results from a dynamic instability of the organism state, we designed a deep artificial neural network, including auto-encoder and auto-regression (AR) components. The AR model tied the dynamics of physiological state with the stochastic evolution of a single variable, the "dynamic frailty indicator" (dFI). In a subset of blood tests from the Mouse Phenome Database, dFI increased exponentially and predicted the remaining lifespan. The observation of the limiting dFI was consistent with the late-life mortality deceleration. dFI changed along with hallmarks of aging, including frailty index, molecular markers of inflammation, senescent cell accumulation, and responded to life-shortening (high-fat diet) and life-extending (rapamycin) treatments.

A machine learning-based data mining in medical examination data: a biological features-based biological age prediction model

Background

Biological age (BA) has been recognized as a more accurate indicator of aging than chronological age (CA). However, the current limitations include: insufficient attention to the incompleteness of medical data for constructing BA; Lack of machine learning-based BA (ML-BA) on the Chinese population; Neglect of the influence of model overfitting degree on the stability of the association results.

Methods and results

Based on the medical examination data of the Chinese population (45–90 years), we first evaluated the most suitable missing interpolation method, then constructed 14 ML-BAs based on biomarkers, and finally explored the associations between ML-BAs and health statuses (healthy risk indicators and disease). We found that round-robin linear regression interpolation performed best, while AutoEncoder showed the highest interpolation stability. We further illustrated the potential overfitting problem in ML-BAs, which affected the stability of ML-Bas’ associations with health statuses. We then proposed a composite ML-BA based on the Stacking method with a simple meta-model (STK-BA), which overcame the overfitting problem, and associated more strongly with CA (r = 0.66, P < 0.001), healthy risk indicators, disease counts, and six types of disease.

Conclusion

We provided an improved aging measurement method for middle-aged and elderly groups in China, which can more stably capture aging characteristics other than CA, supporting the emerging application potential of machine learning in aging research.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04966-7.

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

Psychological factors substantially contribute to biological aging: evidence from the aging rate in Chinese older adults

We have developed a deep learning aging clock using blood test data from the China Health and Retirement Longitudinal Study, which has a mean absolute error of 5.68 years. We used the aging clock to demonstrate the connection between the physical and psychological aspects of aging. The clock detects accelerated aging in people with heart, liver, and lung conditions. We demonstrate that psychological factors, such as feeling unhappy or being lonely, add up to 1.65 years to one’s biological age, and the aggregate effect exceeds the effects of biological sex, living area, marital status, and smoking status. We conclude that the psychological component should not be ignored in aging studies due to its significant impact on biological age.

Clinlabomics: leveraging clinical laboratory data by data mining strategies

The recent global focus on big data in medicine has been associated with the rise of artificial intelligence (AI) in diagnosis and decision-making following recent advances in computer technology. Up to now, AI has been applied to various aspects of medicine, including disease diagnosis, surveillance, treatment, predicting future risk, targeted interventions and understanding of the disease. There have been plenty of successful examples in medicine of using big data, such as radiology and pathology, ophthalmology cardiology and surgery. Combining medicine and AI has become a powerful tool to change health care, and even to change the nature of disease screening in clinical diagnosis. As all we know, clinical laboratories produce large amounts of testing data every day and the clinical laboratory data combined with AI may establish a new diagnosis and treatment has attracted wide attention. At present, a new concept of radiomics has been created for imaging data combined with AI, but a new definition of clinical laboratory data combined with AI has lacked so that many studies in this field cannot be accurately classified. Therefore, we propose a new concept of clinical laboratory omics (Clinlabomics) by combining clinical laboratory medicine and AI. Clinlabomics can use high-throughput methods to extract large amounts of feature data from blood, body fluids, secretions, excreta, and cast clinical laboratory test data. Then using the data statistics, machine learning, and other methods to read more undiscovered information. In this review, we have summarized the application of clinical laboratory data combined with AI in medical fields. Undeniable, the application of Clinlabomics is a method that can assist many fields of medicine but still requires further validation in a multi-center environment and laboratory.

Optimized Metabotype Definition Based on a Limited Number of Standard Clinical Parameters in the Population-Based KORA Study

The aim of metabotyping is to categorize individuals into metabolically similar groups. Earlier studies that explored metabotyping used numerous parameters, which made it less transferable to apply. Therefore, this study aimed to identify metabotypes based on a set of standard laboratory parameters that are regularly determined in clinical practice. K-means cluster analysis was used to group 3001 adults from the KORA F4 cohort into three clusters. We identified the clustering parameters through variable importance methods, without including any specific disease endpoint. Several unique combinations of selected parameters were used to create different metabotype models. Metabotype models were then described and evaluated, based on various metabolic parameters and on the incidence of cardiometabolic diseases. As a result, two optimal models were identified: a model composed of five parameters, which were fasting glucose, HDLc, non-HDLc, uric acid, and BMI (the metabolic disease model) for clustering; and a model that included four parameters, which were fasting glucose, HDLc, non-HDLc, and triglycerides (the cardiovascular disease model). These identified metabotypes are based on a few common parameters that are measured in everyday clinical practice. These metabotypes are cost-effective, and can be easily applied on a large scale in order to identify specific risk groups that can benefit most from measures to prevent cardiometabolic diseases, such as dietary recommendations and lifestyle interventions.

A simplified prediction model for end-stage kidney disease in patients with diabetes

This study aimed to develop a simplified model for predicting end-stage kidney disease (ESKD) in patients with diabetes. The cohort included 2549 individuals who were followed up at Kyushu University Hospital (Japan) between January 1, 2008 and December 31, 2018. The outcome was a composite of ESKD, defined as an eGFR < 15 mL min⁻¹ [1.73 m]⁻², dialysis, or renal transplantation. The mean follow-up was 5.6 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm$$\end{document}± 3.7 years, and ESKD occurred in 176 (6.2%) individuals. Both a machine learning random forest model and a Cox proportional hazard model selected eGFR, proteinuria, hemoglobin A1c, serum albumin levels, and serum bilirubin levels in a descending order as the most important predictors among 20 baseline variables. A model using eGFR, proteinuria and hemoglobin A1c showed a relatively good performance in discrimination (C-statistic: 0.842) and calibration (Nam and D’Agostino \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\chi$$\end{document}χ² statistic: 22.4). Adding serum albumin and bilirubin levels to the model further improved it, and a model using 5 variables showed the best performance in the predictive ability (C-statistic: 0.895, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\chi$$\end{document}χ² statistic: 7.7). The accuracy of this model was validated in an external cohort (n = 5153). This novel simplified prediction model may be clinically useful for predicting ESKD in patients with diabetes.

Factors associated with early biological aging in older people with HIV

Advances and availability of antiretroviral treatment has enabled a longer life expectancy for HIV population. However, with its chronicity, premature aging challenges the management of people living with HIV. This study, conducted between 2018-2020, aimed to identify an association between risk factors and premature aging, using the biological age estimated by artificial intelligence (AI) based on deep learning (Aging 3.0). This was a cross-sectional, analytical study, involving older people living with HIV (OPLHIV), 66.1% of whom were men. Premature aging was identified in 67.8%. The presence of cannabis and diabetes were significant (p = 0.045 and p = 0.042, respectively). For current and nadir CD4 + cell counts, participants were divided into groups comparing biological age (BA) and chronological age (CA). Just one group presented no premature aging, whereas the group with premature aging was subdivided into BA > CA up to 4 years and BA > CA in 5 or more years. In conclusion, premature aging was present in most of the OPLHIV. The use of cannabis was self-reported in those with higher BAs and those with a lower BA presented a higher prevalence of diabetes. Factors directly linked to HIV infection, lower current and nadir CD4 + counts were associated with premature aging.

Optimizing future well-being with artificial intelligence: self-organizing maps (SOMs) for the identification of islands of emotional stability

In this article, we present a deep learning model of human psychology that can predict one’s current age and future well-being. We used the model to demonstrate that one’s baseline well-being is not the determining factor of future well-being, as posited by hedonic treadmill theory. Further, we have created a 2D map of human psychotypes and identified the regions that are most vulnerable to depression. This map may be used to provide personalized recommendations for maximizing one’s future well-being.