ECSS Paris 2023: OP-AP01
INTRODUCTION: Aging is associated with health issues leading to functional decline and disability. Identifying key factors (biochemical, physical, or social) for successful aging is crucial for resource efficiency [1]. Using unsupervised clustering analysis on routine laboratory test data, we aim to uncover biochemical phenotypes in the spectrum of old age. This approach may enhance understanding of mechanisms influencing healthy aging. We also intend to explore associations between these phenotypes and key health outcomes, including mortality [2]. METHODS: A final sample of n=1491 participants (65 to 99 years old, 57.7% women), from the Toledo Study for Healthy Aging (TSHA), was included. Hierarchical and k-means cluster analyses (Orange software) incorporated 39 variables related to white and red blood cells, and renal, liver lipid, and glucose metabolism. Health outcomes included body composition (DXA), physical functionality (SPPB test), physical activity (PASE questionnaire), disability (Katz questionnaire), frailty (FTS-5 test), comorbidity (medical history), and 12-year mortality (Spanish National Mortality Database). The associations between cluster membership and health outcomes and mortality hazard ratios (HR) were analyzed through general linear models (ANCOVA, SPSS software) and Cox regression (STATA software) respectively, including sex, age, and socioeconomic status as covariates. RESULTS: Three different clusters were identified: Cluster 1 (41.8%, Healthy), all biochemical values within the normal range, taken as reference for statistical analysis; Cluster 2 (44.5%, Metabolic), characterized by high but sub-clinically relevant levels of glucose, triglycerides, HOMA, and liver enzymes; and Cluster 3 (13.7%, Red Blood Cells), defined by lower levels of hematocrit, hemoglobin, and red blood cells. Our findings revealed that Cluster 2 (metabolic) showed a significantly higher BMI in men (28.70±0.21 vs. 27.46±0.35 Kg/m2) and women (31.01±0.35 vs. 29.61±0.26 Kg/m2), and a higher risk of death in women (HR=1.50; 95%CI= (1.08; 2.08)) respect to the healthy cluster. Cluster 3 (Red Blood Cells) participants were older (77.8±0.4 vs. 74.5±0.2 yrs.), and men were less physically active (PASE score: 57.46±6.03 vs 69.40±4.41) and showed worse physical functionality with less gait speed (0.85±0.04 vs 0.94±0.03 m/s) than healthy cluster. They were also less independent in their daily activities with a significantly lower Katz index in both sexes (men: 5.46±0.08 vs. 5.82±0.06; women: 5.56±0.07 vs. 5.77±0.04). Significant findings (p<0.05) were observed for all mentioned values. CONCLUSION: Our findings suggest that a biochemical phenotype characterized by impaired red blood cell function is associated with a decreased health-related quality of life, whereas impaired glucose and lipid metabolism is associated with a higher risk of death. This information could be helpful to develop exercise-based interventions oriented to healthy aging. 1. Urtamo et al. (2019) 2. O ‘Sullivan et al. (2011)
Read CV Raquel González MartosECSS Paris 2023: OP-AP01
INTRODUCTION: Running poses a high risk of developing running-related injuries [1]. The majority of RRIs are the result of an imbalance between the cumulative musculoskeletal load and a person’s load capacity [2, 3]. Therefore, measuring and monitoring the musculoskeletal load during running is essential for the prevention of RRIs. A general estimate of whole-body biomechanical load can be inferred from ground reaction forces (GRFs). Unfortunately, GRF typically can only be measured in a controlled environment, which hinders its wider applicability. Applying machine-learning algorithms to wearables-collected data enables runners to monitor GRF characteristics in various settings [4], extending beyond the confines of the laboratory. Our study presents and evaluates a machine-learning method to predict contact time, active peak, impact peak, and impulse of the vertical GRF (vGRF) during running from 3D sacral acceleration. METHODS: Twenty-seven subjects with varying running experience ran on an instrumented treadmill (Motek Medical BV) at various speeds for 150 seconds at each speed. The instrumented treadmill measured ground reaction forces, and a sensor (Xsens Technologies, Movella) on the lower back captured 3D acceleration. In total, we obtained 50072 steps of which 28078 steps had an impact peak. Subject characteristics, general statistical, and domain-specific features were extracted from the 3D acceleration signal for each step. We used a Lasso (Least Absolute Shrinkage and Selection Operator) model to predict the characteristics of the vGRF. We partitioned the data into a training (23 subjects) and test (4 subjects) set. To select the hyperparameter settings, we conducted a leave-one-subject-out cross-validation on the training set. We compared the performance of our approach to the methods outlined in the work of Alcantara et al. [4] regarding active peak, contact time, and impulse; Verheul et al. [5] for the impact peak using a single-sensor setting. RESULTS: The developed models for predicting active peak, impact peak, impulse, and contact time had a root-mean-squared error of 0.084 body weight (BW), 0.221 BW, 0.005 BW.s, and 0.008 seconds, respectively. Our models outperform the corresponding comparison method from the literature on our data sets by respectively 0.061 BW, 0.054 BW, 0.0032 BW.s, and 0.0006 seconds. CONCLUSION: These results indicate the feasibility of our approach for monitoring selected factors associated with running-related injuries outside the laboratory with a single sensor. REFERENCES: [1] Videbæk, S. et al. Sport. Med. 45, 1017–1026 (2015) [2] Hespanhol Junior, L. C. et al. Sport. Med. 47, 367–377 (2017) [3] Bertelsen, M. L. et al. Scand. J. Med. Sci. Sport. 27, 1170–1180 (2017) [4] Alcantara, R. S. et al. PeerJ 9, 1–18 (2021) [5] Verheul, J. et al. J. Sci. Med. Sport 22, 716–722 (2019)
Read CV Sieglinde BogaertECSS Paris 2023: OP-AP01
INTRODUCTION: Assessing movement quality in real-world settings remains challenging. Indeed, previous research has questioned the reliability and accuracy of directly quantifying motion characteristics (e.g. range of motion) using wearables (1, 2). Whilst machine-learning classification techniques offer promising alternatives, they are often limited by a reliance on small sample sizes, thereby impacting robustness and real-world transferability. The aims of this study were therefore two-fold: i) to generate a machine-learning algorithm to classify foundational motor skill competence, using the bodyweight squat as a representative movement; and ii) to develop a novel data simulation method to artificially boost the sample size and enhance classification accuracy. METHODS: Twenty-three participants (28.1 ± 7.3 years; 17 males) performed three sets of 10 repetitions of squats. Data were captured using three Polar Verity Sense magnetic, angular rate, and gravity (MARG) sensors on the chest and both ankles. Three United Kingdom Strength & Conditioning Association accredited coaches classified each repetition as ‘good’, ‘average’, or ‘poor’, based on pre-determined movement criteria, with the modal score for each repetition used in data labelling. To expand and balance the dataset, original data were augmented with simulated data using Weibull distributions or Gaussian mixture models depending on the feature frequency distributions of the most informative features. A support vector machine (SVM) ensemble with a modal voting system was developed to classify squats with raw, then augmented raw and simulated data, for a comparative analysis. RESULTS: Using only the original data for training, overall SVM ensemble classification accuracy using a hold-out dataset was 40%. However, the model yielded 0% accuracy for the repetitions labelled as ‘good’ due to dataset imbalance. Data-boosting improved sensitivity, increasing ‘good’ accuracy to >95%. However, overall accuracy did not improve due to large ‘average’ class inaccuracies (10%). CONCLUSION: This study introduces a novel data-simulation method for improving movement classification by addressing imbalances often inherent in small datasets. Data-boosting was effective, improving sensitivity and accuracy for ‘good’ and ‘poor’ squat repetitions, even with small training datasets. However, overall accuracy did not improve due to classification issues in the ‘average ’ category. This underlines the challenges of using subjective scoring as the standard for algorithm training. Recognising the limitations of the current dataset, future research should refine data-labelling methods and seek larger, more balanced datasets to mitigate intermediate class ambiguity and further the pursuit of practical application. References 1. T. A. Swain et al., Sports Medicine, 53, 2477–2504 (2023) 2. I. Poitras et al., Sensors. 19, 1555 (2019).
Read CV Thomas Alexander SwainECSS Paris 2023: OP-AP01