This study quantitatively evaluated whether and how machine learning (ML) models built by data from controlled conditions can fit real-world conditions. This study focused on feature-based models using wearable technology from real-world data collected from young adults, so as to provide insights into the models’ robustness and the specific challenges posed by diverse environmental noise. Feature-based models, particularly XGBoost and Decision Trees, demonstrated considerable resilience, maintaining higher accuracy and reliability across different noise levels. This investigation included an in-depth analysis of transfer learning, highlighting its potential and limitations in adapting models developed from standard datasets, like WESAD, to complex real-world scenarios. Moreover, this study analyzed the distributed feature importance across various physiological signals, such as electrodermal activity (EDA) and electrocardiography (ECG), considering their vulnerability to environmental factors. It was found that integrating multiple physiological data types could significantly enhance model robustness. The results underscored the need for a nuanced understanding of signal contributions to model efficacy, suggesting that feature-based models showed much promise in practical applications.

Tai Chi (TC) practice has been shown to improve both cognitive and physical function in older adults. However, the neural mechanisms underlying the benefits of TC remain unclear. Our primary aims are to explore whether distinct age-related and TC-practice-related relationships can be identified with respect to either temporal or spatial (within/between-network connectivity) differences. This cross-sectional study examined recurrent neural network dynamics, employing an adaptive, data-driven thresholding approach to source-localized resting-state EEG data in order to identify meaningful connections across time-varying graphs, using both temporal and spatial features derived from a hidden Markov model (HMM). Mann–Whitney U tests assessed between-group differences in temporal and spatial features by age and TC practice using either healthy younger adult controls (YACs, n = 15), healthy older adult controls (OACs, n = 15), or Tai Chi older adult practitioners (TCOAs, n = 15). Our results showed that aging is associated with decreased within-network and between-network functional connectivity (FC) across most brain networks. Conversely, TC practice appears to mitigate these age-related declines, showing increased FC within and between networks in older adults who practice TC compared to non-practicing older adults. These findings suggest that TC practice may abate age-related declines in neural network efficiency and stability, highlighting its potential as a non-pharmacological intervention for promoting healthy brain aging. This study furthers the triple-network model, showing that a balancing and reorientation of attention might be engaged not only through higher-order and top-down mechanisms (i.e., FPN/DAN) but also via the coupling of bottom-up, sensory–motor (i.e., SMN/VIN) networks.

Objective: This study aims at comparing the energy expenditure (EE) and heart rate (HR) data from Ring Fit Adventure (RFA) with those from indirect calorimetry (COSMED) and a heart rate monitor (Polar FT7). A secondary goal is to evaluate self-reported enjoyment and perceived effort levels. Materials and Methods: Thirty participants (age = 21.8 ± 2.2; body mass index = 31.8 ± 4.4) were recruited for two laboratory visits. The first visit involved baseline measurements. In the second visit, participants performed a 55-minute ad libitum exercise session with the RFA in adventure mode with moderate difficulty. During this session, EE, HR, perceived effort, and enjoyment of physical activity were recorded. Results: Although no statistically significant overestimation of EE was found between the RFA and the metabolic cart, two-way analysis of variance results show a main effect of condition (RFA vs. Polar FT7) on HR (122.8 ± 20.1 bpm and 129.0 ± 18.6 bpm; P = 0.007; ᶯ_p² = 0.235). Based on comprehensive statistical evaluations, including the mean absolute percent error, intraclass correlations, typical error of measurement, and limits of agreement, the data suggest that the RFA provides reliable estimates for EE and HR. Overall, participants enjoyed the game considerably (71.3 ± 5.9/80 arbitrary units), and their reported perceived exertion was low. Conclusion: This study underscores that the RFA values are relatively accurate and precise, and thus it can be safely suggested for individuals with overweight and obesity to adopt an active lifestyle.

Objective: This study is aimed at assessing the impact of a 1‐month exergaming intervention ( Fitness Boxing 2: rhythm and exercise ), performed for 150 min per week, on blood glucose levels, strength, and body composition in sedentary office workers with overweight or obesity. Methods: Then, 21 sedentary participants (age: 38.0 ± 7.5 years, BMI: 30.8 ± 4.9 kg/m ² ) were randomly assigned to either an experimental group ( n = 11; 4 men and 7 women) or a control group ( n = 10; 2 men and 8 women). The experimental group completed 20 sessions, each consisting of 30 min of exergaming, 5 days per week. The control group was instructed to maintain their usual daily activities. Before and after the intervention, blood glucose, strength, and body composition were measured. Results: The average daily energy expenditure was 330.7 ± 86.9 kcal, with a maximum perceived effort of 12.7 ± 1.8 arbitrary units. An interaction effect between group and time was found in the experimental group in blood glucose ( % Δ = −7.8; p = 0.027; d = 0.590), grip strength of the nondominant hand ( % Δ = 14.1; p = 0.006; d = 0.383), and back–leg–chest strength ( % Δ = 41.5; p = 0.001; d = 0.662). No differences were found in any of the outcome variables of interest for the control group over time (pre vs. post; p > 0.05). Additionally, no differences in groups (experimental vs. control) and time (pre vs. post) were yielded for weight and body composition. Conclusion: The results of this work demonstrate that engagement with exergames can improve blood glucose and strength in sedentary office workers with overweight or obesity.

Tai Chi is a Chinese martial art that provides an adaptive and accessible exercise for older adults with varying functional capacity. While Tai Chi is widely recommended for its physical benefits, wider adoption in at-home practice presents challenges for practitioners, as limited feedback may hamper learning. This study examined the feasibility of using a wearable sensor, combined with machine learning (ML) approaches, to automatically and objectively classify Tai Chi expertise. We hypothesized that the combination of wrist acceleration profiles with ML approaches would be able to accurately classify practitioners’ Tai Chi expertise levels. Twelve older active Tai Chi practitioners were recruited for this study. The self-reported lifetime practice hours were used to identify subjects in low, medium, or highly experienced groups. Using 15 acceleration-derived features from a wearable sensor during a self-guided Tai Chi movement and 8 ML architectures, we found multiclass classification performance to range from 0.73 to 0.97 in accuracy and F1-score. Based on feature importance analysis, the top three features were found to each result in a 16–19% performance drop in accuracy. These findings suggest that wrist-wearable-based ML models may accurately classify practice-related changes in movement patterns, which may be helpful in quantifying progress in at-home exercises.

Background: To determine if 3‐year changes in serum insulin resistance (IR) were related to changes in brain volume and glucose uptake, cognition, and CSF biomarkers in cognitively unimpaired and impaired older adults.Method: Alzheimer’s Disease Neuroimaging Initiative data was downloaded for 275 aged adults (55‐89 years). Participants had longitudinal T1‐ and T2‐weighted volume scans, fluorodeoxyglucose (FDG) scans, CSF β‐amyloid (Aβ) and tau species, and cognitive performance over baseline and months 6, 12, 18, 24, and 36. Growth curve modeling in R regressed IR against these outcomes, by itself and with clinical diagnosis as a moderator. Cognitively unimpaired (CU) adults were used as a reference group to determine potential effects in pathological aging.Result: In AD and/or Mild Cognitive Impairment progressors to AD (MCI‐P), higher IR over time was related to progressive atrophy in medial temporal frontoinsular areas. Similarly, decline was seen in global cognition and both memory and executive function. HOMA1‐IR associations were partially mediated by p‐tau‐181. Among clinical diagnosis groups, higher IR was significantly related to amyloid, p‐tau‐181, and total tau 181 among AD patients but not MCI or unimpaired groups.Conclusion: These findings suggest that in older adults who develop AD or had AD at baseline, higher IR over time is related to brain atrophy and consequent cognitive decline, perhaps as a function of amyloid or tau deposition.