Biological Age Estimation From the Age Gap Using Deep Learning Integrating Morbidity and Mortality: Model Development and Validation Study

Background Transthoracic echocardiography (TTE) is increasingly used by point-of-care ultrasound (POCUS) devices. Age and sex can be estimated by artificial intelligence (AI) based on various sources. The current study aimed to test whether deep learning (DL) networks could be trained to predict a patient's age and sex using a TTE. We hypothesized that DL-predicted age would be superior to chronological age in predicting long-term survival. Methods The analysis was based on 122,014 unique patients who underwent TTE evaluation between 2007 and 2021 at large tertiary medical center. Survival data were available for all subjects from the National Population Register. Three mutually exclusive cohorts were used for training (N=76,342[62%]), validation (N=22,825[19%]) and testing (N=22,847[19%]). A fourth cohort (N=650), from a different hospital, was used for external validation. The testing cohort was used to evaluate the accuracy in estimating age and sex. We divided the patients into two mutually exclusive groups; (1) the patients whose machine-estimated age was ≥ 5 years of their chronological age (20% of the cohort), (2) all other patients. A multivariate Cox regression model was used to investigate the association between age estimation and chronological age with overall survival. Results The final test cohort included 18,447 unique patients, of whom 10,640 (58%) were men with a median age of 66 (IQR 54-76). The machine learning model was able to estimate age with an average error of 4.9 years, a Root Mean Square Error (RMSE) of 6.3 and a Pearson correlation coefficient (r) of 0.922. Sex was estimated as a probabilistic value with total accuracy of 96.1% and an area under the curve (AUC) of 0.993. Consistent results were obtained with external validation from a different hospital (RMSE = 7.04, (r)=0.897 and an AUC of 0.988). During a median follow-up of 4.3 (IQR, 2.1-6.3) years, 5147 (27.9%) patients died. A multivariate Cox regression model with adjustment for age, sex, and ejection fraction demonstrated that age prediction ≥ 5 years of chronological age was associated with an independent and significant 48% increased risk of death during follow-up (95% CI 1.38-1.59, p<0.001). When machine’s age prediction was used as a continuous variable in the same model, each year above the chronological age was associated with an independent and significant 8% increased risk of death (95% CI 1.05-1.10, p<0.001). Similarly, a higher probability of male sex among female subjects was also associated with a significant 63% increased risk of death in the same model (95% CI 1.38-1.92, p<0.001). Conclusions Applying AI to the standard TTE allows the prediction of a patient's sex and estimation of age. Machine-based estimation is an independent predictor of overall survival and, with further evaluation, can be used for risk stratification and estimation of biological age at the point of care.Kaplan-Meier survival curve by delta-ageKaplan-Meier survival curve by sex

Predictors and incidence of health status deterioration in patients with early atrial fibrillation

The continued development in methylome analysis has enabled a more precise assessment of DNA methylation, but treatment of target tissue prior to analysis may affect DNA analysis. Prediction of age based on methylation levels in the genome (DNAmAge) has gained much interest in disease predisposition (biological age estimation), but also in chronological donor age estimation in crime case samples. Various epigenetic clocks were designed to predict the age. However, it remains unknown how the storage of the tissues affects the DNAmAge estimation. In this study, we investigated the storage method impact of DNAmAge by the comparing the DNAmAge of the two commonly used storage methods, freezing and formalin-fixation and paraffin-embedding (FFPE) to DNAmAge of fresh tissue. This was carried out by comparing paired heart tissue samples of fresh tissue, samples stored by freezing and FFPE to chronological age and whole blood samples from the same individuals. Illumina EPIC beadchip array was used for methylation analysis and the DNAmAge was evaluated with the following epigenetic clocks: Horvath, Hannum, Levine, Horvath skin+blood clock (Horvath2), PedBE, Wu, BLUP, EN, and TL. We observed differences in DNAmAge among the storage conditions. FFPE samples showed a lower DNAmAge compared to that of frozen and fresh samples. Additionally, the DNAmAge of the heart tissue was lower than that of the whole blood and the chronological age. This highlights caution when evaluating DNAmAge for FFPE samples as the results were underestimated compared with fresh and frozen tissue samples. Furthermore, the study also emphasizes the need for a DNAmAge model based on heart tissue samples for an accurate age estimation.

The Relationship Between Anemia, Change in Hematocrit Over Time and Change in Health Status in Patients With Heart Failure After Myocardial Infarction

Health status assessment and remaining useful life prediction of aero-engine based on BiGRU and MMoE

BackgroundBrain age – an image derived measure from structural brain images on T1 weighted scans may reveal information on Alzheimer’s risk. We have previously shown that increased abdominal adipose tissue relates to brain atrophy. We evaluated the links between abdominal adipose tissue and brain age.MethodA total of 1,164 healthy participants from four sites (mean chronological age 55.17 ± 12.37 years, 52% women; 48% men; 39% non‐white) were scanned on 1.5T MR machines with a whole‐body protocol. Whole body sequences utilized in the quantitative analyses of abdominal fat were coronal T1 were used to segment visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) segmentation. In this process, a nnU‐Net model was used for fully supervised segmentation and ITK‐SNAP was used for manual annotation. Brain age was computed using a regression‐based 3D Simple Fully Convolutional Network. The model was trained on in‐house T1‐weighted MRI scans collected from 5,500 healthy individuals, aged 18 to 89 years. Brain age gap (BAG) was computed by subtracting chronological age from brain age. Bivariate correlations between VAT and SAT to chronological and brain age were done with partial correlations adjusted for sex with brain age. VAT and SAT were normalized to total abdominal body fat volume. Chronological age was not adjusted for in brain age models to avoid collinearity.ResultMean brain age exceeded chronological age (mean brain age = 56.04 ± 12.65, mean BAG = 0.69) and were highly correlated (r=0.94, p <.001). VAT and SAT were positively related to increased chronological age (VAT: r=0.2780, p = 5.477e‐20; r=0.0924, p = 0.002817) and increased brain age (VAT: r=0.2806, p = 2.42e‐20; SAT: r=0.0947, p = 0.002189) with VAT being more closely linked to age than SAT. This did not change when adjusting for sex in separate partial correlations between VAT and SAT for brain age (VAT: rp = r=0.2948, p = 2.247e‐22; SAT: r=0.1070, p = 0.0005353). No statistically significant link was noted with VAT, SAT, and BAG.ConclusionBoth VAT and SAT are linked to chronological and brain age with VAT being more strongly linked. VAT may be a key target for modifying brain age and Alzheimer’s risk.

Artificial intelligence (AI) algorithms in 12-lead electrocardiogram (ECG) provides promising age prediction methods. This study investigated whether the discrepancy between ECG-derived AI-predicted age (AI-ECG age) and chronological age, termed electrocardiographic aging (ECG aging), is associated with atrial fibrillation (AF) risk. An AI-ECG age prediction model was developed using a large-scale dataset (1 533 042 ECGs from 689 639 participants) and validated with six independent and multi-national datasets (737 133 ECGs from 330 794 participants). The AI-ECG age gap was calculated across two South Korean cohorts [mean (standard deviation) follow-up: 4.1 (4.3) years for 111 483 participants and 6.1 (3.8) years for 37 517 participants], one UK cohort [3.0 (1.6) years; 40 973 participants], and one US cohort [12.9 (8.6) years; 90 639 participants]. Participants were classified into two groups: normal group (age gap < 7 years) and ECG-aged group (age gap ≥ 7 years). The predictive capability of ECG aging for new- and early-onset AF risk was assessed. The mean AI-ECG ages were 51.9 (16.2), 47.4 (12.5), 68.4 (7.8), and 56.7 (14.6) years with age gaps of .0 (6.8), -.1 (6.0), 4.7 (8.7), and -1.4 (8.9) years in the two South Korean, UK, and US cohorts, respectively. In the ECG-aged group, increased risks of new-onset AF were observed with hazard ratios (95% confidence intervals) of 2.50 (2.24-2.78), 1.89 (1.46-2.43), 1.90 (1.55-2.33), and 1.76 (1.67-1.86) in the two South Korean, UK, and US cohorts, respectively. For early-onset AF, odds ratios were 2.89 (2.47-3.37), 1.94 (1.39-2.70), 1.58 (1.06-2.35), and 1.79 (1.62-1.97) in these cohorts compared with the normal group. The AI-derived ECG aging was associated with the risk of new- and early-onset AF, suggesting its potential utility to identify individuals for AF prevention across diverse populations.

ObjectiveThe current review describes how the health status profile of people with fibromyalgia (FM) compares to that of people in the general population and patients with other health conditions.MethodsA review of 37 studies of FM that measured health status with the 36-item Medical Outcomes Study Short-Form Health Survey (SF-36) or the 12-item Short-Form Health Survey (SF-12).ResultsStudies performed worldwide showed that FM groups were significantly more impaired than people in the general population on all eight health status domains assessed. These domains include physical functioning, role functioning difficulties caused by physical problems, bodily pain, general health, vitality (energy vs. fatigue), social functioning, role functioning difficulties caused by emotional problems and mental health. FM groups had mental health summary scores that fell 1 standard deviation (SD) below the general population mean, and physical health summary scores that fell 2 SD below the general population mean. FM groups also had a poorer overall health status compared to those with other specific pain conditions. FM groups had similar or significantly lower (poorer) physical and mental health status scores compared to those with rheumatoid arthritis, osteoarthritis, osteoporosis, systemic lupus erythematosus, myofacial pain syndrome, primary Sjögren's syndrome and others. FM groups scored significantly lower than the pain condition groups mentioned above on domains of bodily pain and vitality. Health status impairments in pain and vitality are consistent with core features of FM.ConclusionsPeople with FM had an overall health status burden that was greater in magnitude compared to people with other specific pain conditions that are widely accepted as impairing.Review CriteriaStudies in this review were identified through a search of electronic databases (MEDLINE: 1990–2006; EMBASE: 1990–2006). Search terms included: ‘fibromyalgia’, ‘health status’, ‘quality of life’, ‘SF-36’ and ‘SF-12’. Reference lists from published articles were also searched. Studies were selected if they were published in the English language between 1990 and (March) 2006 and assessed health status with a validated version of the SF-36 or the SF-12.Message for the ClinicAlthough FM is a controversial construct, studies performed worldwide showed that the health status profile of people with FM was remarkably consistent. People with FM had significant impairments in both mental and physical health status domains. People with FM had a poorer overall health status than people with specific pain conditions that are widely accepted as impairing.

The assessment of the health status and prediction of the lifespan of cable equipment are critical for ensuring the stability and efficiency of the power grid. This paper develops a temperature-current-capacity-life calculation model for cables, considering the fast and slow charging demands of electric vehicles (EVs). Analyses under scenarios of rapid and slow charging demands are conducted, introducing a cable health index and establishing a health status assessment framework based on this index. The framework accounts for various factors leading to cable faults, offering a comprehensive evaluation of the health status of cables with different fault rates. Building upon this, a prediction method using the Fire Hawk Optimization (FHO) Algorithm and Convolutional Neural Network (CNN) is proposed. This method enhances performance by optimizing the hyperparameters of Bidirectional Gated Recurrent Unit (BiGRU) through FHO, effectively searching and determining the optimal hyperparameter configuration. The impact of different scenarios and varying EV penetration rates on cable temperature is analyzed through case studies, facilitating the assessment and prediction of health status.

Ageing is a complex process influenced by modifiable factors such as diet, which may accelerate or decelerate physiological decline. While chronological age increases uniformly, biological ageing varies between individuals, reflecting differences in health status and the resilience of biological systems. The Klemera-Doubal Method (KDM), a composite biomarker-based index often used as an estimate of biological age, has been associated with morbidity and mortality in large cohorts. This study examined whether dietary manipulation of protein source and macronutrient composition affects KDM estimates in older adults. We analysed data from the Nutrition for Healthy Living study, a 2 × 2 factorial dietary intervention trial involving 104 participants aged 65-75 years. Participants were randomised to one of four diets: omnivorous/high-fat (OHF), omnivorous/high-carbohydrate (OHC), semi-vegetarian/high-fat (VHF) or semi-vegetarian/high-carbohydrate (VHC). KDM-derived δAge (the difference between KDM- and chronological-age) was calculated before and after a 4-week intervention. The OHF group, most like participants' baseline diets, showed no meaningful change in δAge. Compared to OHF, participants in the OHC group showed a significant reduction in δAge. The VHF and VHC groups showed similar reductions in δAge, relative to OHF, though not all reached statistical significance. KDM-derived δAge appears responsive to dietary change within 4 weeks and may offer a useful proxy for evaluating shifts in physiological status. Caution is warranted in interpreting such changes as evidence of biological age reversal as observed shifts may reflect acute physiological responsiveness to dietary inputs rather than altered ageing trajectories. Longer-term treatment would be needed to assess changes in age-related disease risks.

Background: Acute kidney injury (AKI) increases in-hospital morbidity and mortality. Age is a recognized risk factor and is included in prognostic indices, usually as chronological age. However, this may reduce predictive accuracy in older adults, where biological and chronological age may diverge. Methods: Prospective cohort study from 1994 to 2025. Inclusion: ≥20% rise in serum creatinine. 3,274 patients were stratified by age: A (<55), B (55–64), C (65–74), D (75–84), and E (≥85). Compared the Individual Severity Index (ISI, includes age) with the Multiorgan Failure Index (MOFI, does not include age). Clinical profiles, treatment, outcomes, and health status (Karnofsky, ECOG, nutrition 0–4) were assessed. Results: Patient distribution by age group was: A (<55) 24.1%, B (55–64) 22.8%, C (65–74) 27.9%, D (75–84) 20.6%, and E (≥85) 4.6%. Overall mortality was 16.3%; by group: A 19.2%, B 19.0%, C 14.7%, D 13.0%, E 12.1%. Functional causes of AKI (mainly hypovolemia) increased with age: A 71.4%, B 75.4%, C 75.1%, D 79.7%, E 85.9%. In contrast, need for renal replacement therapy declined: A 29.4%, B 26.2%, C 26.4%, D 20.6%, E 11.4%. Chronic kidney disease rose from 26.9% in A to 71.1% in E. Inflammatory diseases were more frequent in younger patients (A 48.2%, E 31.5%). Heart failure prevalence increased from 2.7% in A to 11.4% in E. Oncologic pathology showed the opposite trend, from 40.9% in A to 6.7% in E. Mean Karnofsky declined with age: A 70.17, B 69.44, C 69.15, D 68.40, E 64.03 (p<0.001). Nutritional status (0–4 scale) decreased: A 2.16, B 2.20, C 1.98, D 2.00, E 1.77 (p<0.001). No significant differences were observed in ECOG. ISI (includes age) increased with age: A 0.259, B 0.295, C 0.310, D 0.335, E 0.336. MOFI (excludes age) decreased: A 3.83, B 3.44, C 3.24, D 2.84, E 2.42 (p<0.005). AUC for mortality prediction remained stable for MOFI but declined for ISI, with the lowest discrimination in the oldest group. Conclusion: In older adults, AKI is more often functional, with lower mortality and dialysis need. Prognostic scores based on chronological age (ISI) lose sensitivity/specificity in the elderly. Including biological age markers (frailty, functional status, nutrition) could improve prognostic precision.

Health Status Assessment in a Hypertension Section of an Internal Medicine Clinic

Parents are the principal decision-makers regarding their child's health. Awareness of mothers' view about their children's health, particularly with special health care needs (SHCN) (include hearing impaired children), is essential for health care providers. Therefore, the present study aimed to assess the mothers view about oral health status, oral hygiene practices, and dental services utilization of their children with hearing impairment attending special schools. A cross-sectional study was conducted between May and September 2020 among mothers of students with hearing impairment attending special schools. Also, the telephone structured interview was used to gathering mothers view. 57.4% of the mothers rated their children's oral health status as excellent or good, 27.9% as moderate, and 14.7% as poor. About half of the mothers (49.2%) stated that their children used toothbrushes once daily, and 15% use dental floss. Also, 54% of the children visited the dentist before this survey's conduct. The findings of the present study suggest that children with hearing impairment can also have good oral health status and behaviors. These results may be attributed to the fact that the study sample was taken from two special schools. Also, only the mothers' perception assessment of students' oral health status was done. Further studies are required to increase the strength of evidence.

Novel machine learning framework for multidimensional biological age estimation reveals heterogeneous aging of organ systems.

Exercise Testing and Training Strategies for Healthy and Frail Elderly