Application of a Machine Learning Technology in the Definition of Metabolically Healthy and Unhealthy Status: A Retrospective Study of 2567 Subjects Suffering from Obesity with or without Metabolic Syndrome

The key factors playing a role in the pathogenesis of metabolic alterations observed in many patients with obesity have not been fully characterized. Their identification is crucial, and it would represent a fundamental step towards better management of this urgent public health issue. This aim could be accomplished by exploiting the potential of machine learning (ML) technology. In a single-centre study (n = 2567), we used an ML analysis to cluster patients with metabolically healthy (MHO) or metabolically unhealthy (MUO) obesity, based on several clinical and biochemical variables. The first model provided by ML was able to predict the presence/absence of MHO with an accuracy of 66.67% and 72.15%, respectively, and included the following parameters: HOMA-IR, upper body fat/lower body fat, glycosylated haemoglobin, red blood cells, age, alanine aminotransferase, uric acid, white blood cells, insulin-like growth factor 1 (IGF-1) and gamma-glutamyl transferase. For each of these parameters, ML provided threshold values identifying either MUO or MHO. A second model including IGF-1 zSDS, a surrogate marker of IGF-1 normalized by age and sex, was even more accurate with a 71.84% and 72.3% precision, respectively. Our results demonstrated high IGF-1 levels in MHO patients, thus highlighting a possible role of IGF-1 as a novel metabolic health parameter to effectively predict the development of MUO using ML technology.

Single Camera-Based Remote Physical Therapy: Verification on a Large Video Dataset

In recent years, several systems have been developed to capture human motion in real-time using common RGB cameras. This approach has great potential to become widespread among the general public as it allows the remote evaluation of exercise at no additional cost. The concept of using these systems in rehabilitation in the home environment has been discussed, but no work has addressed the practical problem of detecting basic body parts under different sensing conditions on a large scale. In this study, we evaluate the ability of the OpenPose pose estimation algorithm to perform keypoint detection of anatomical landmarks under different conditions. We infer the quality of detection based on the keypoint confidence values reported by the OpenPose. We used more than two thousand unique exercises for the evaluation. We focus on the influence of the camera view and the influence of the position of the trainees, which are essential in terms of the use for home exercise. Our results show that the position of the trainee has the greatest effect, in the following increasing order of suitability across all camera views: lying position, position on the knees, sitting position, and standing position. On the other hand, the effect of the camera view was only marginal, showing that the side view is having slightly worse results. The results might also indicate that the quality of detection of lower body joints is lower across all conditions than the quality of detection of upper body joints. In this practical overview, we present the possibilities and limitations of current camera-based systems in telerehabilitation.

The Relationship between VO2 and Muscle Deoxygenation Kinetics and Upper Body Repeated Sprint Performance in Trained Judokas and Healthy Individuals

The present study sought to investigate if faster upper body oxygen uptake (VO2) and hemoglobin/myoglobin deoxygenation ([HHb]) kinetics during heavy intensity exercise were associated with a greater upper body repeated-sprint ability (RSA) performance in a group of judokas and in a group of individuals of heterogenous fitness level. Eight judokas (JT) and seven untrained healthy participants (UT) completed an incremental step test, two heavy intensity square-wave transitions and an upper body RSA test consisting of four 15 s sprints, with 45 s rest, from which the experimental data were obtained. In the JT group, VO2 kinetics, [HHb] kinetics and the parameters determined in the incremental test were not associated with RSA. However, when the two groups were combined, the amplitude of the primary phase VO2 and [HHb] was positively associated with the accumulated work in the four sprints (ΣWork). Additionally, maximal aerobic power (MAP), peak VO2 and the first ventilatory threshold (VT1) showed a positive correlation with ΣWork and an inverse correlation with the decrease in peak power output (Dec-PPO) between the first and fourth sprints. Faster VO2 and [HHb] kinetics do not seem to be associated with an increased upper body RSA in JT. However, other variables of aerobic fitness seem to be associated with an increased upper body RSA performance in a group of individuals with heterogeneous fitness level.

Recognition and prediction of driver’s whole body posture model

The driver’s whole-body posture at the time of a collision is a key factor in determining the magnitude of injury to the driver. However, current researchs on driver posture models only consider the upper body posture of the driver, and the lower body area which is not perceived by sensors is not studied. This paper investigates the driver’s posture and establishes a 3D posture model of the driver’s whole body through the application of machine vision algorithms and regression model statistics. This study proposes an improved Kinect-OpenPose algorithm for identifying the 3D spatial coordinates of nine keypoints of the driver’s upper body. The posture prediction regression model of four keypoints of the lower body is established by conducting volunteer posture acquisition experiments on the developed simulated driving seat and analyzing the volunteer posture data through using the principal components of the upper body keypoints and the seat parameters. The experiments proved that the error of the regression model in this paper is minor than that of current studies, and the accuracy of the keypoint location and the keypoint connection length of the established driver whole body posture model is high, which provides implications for future studies.

Low-Cost Force Sensors Embedded in Physical Human–Machine Interfaces: Concept, Exemplary Realization on Upper-Body Exoskeleton, and Validation

In modern times, the collaboration between humans and machines increasingly rises, combining their respective benefits. The direct physical support causes interaction forces in human–machine interfaces, whereas their form determines both the effectiveness and comfort of the collaboration. However, their correct detection requires various sensor characteristics and remains challenging. Thus, this paper presents a developed low-cost sensor pad working with a silicone capsule and a piezoresistive pressure sensor. Its measurement accuracy is validated in both an isolated testing environment and a laboratory study with four test subjects (gender-balanced), and an application integrated in interfaces of an active upper-body exoskeleton. In the material-testing machine, it becomes apparent that the sensor pad generally features the capability of reliably determining normal forces on its surface until a certain threshold. This is also proven in the real application, where the measurement data of three sensor pads spatially embedded in the exoskeletal interface are compared to the data of an installed multi-axis load cell and a high-resolution flexible pressure map. Here, the consideration of three sensor pads potentially enables detection of exoskeletal support on the upper arm as well as “poor” fit conditions such as uneven pressure distributions that recommend immediate system adjustments for ergonomic improvements.

Retrospective Analysis of Training Intensity Distribution Based on Race Pace Versus Physiological Benchmarks in Highly Trained Sprint Kayakers

Background Research results on the training intensity distribution (TID) in endurance athletes are equivocal. This non-uniformity appears to be partially founded in the different quantification methods that are implemented. So far, TID research has solely focused on sports involving the lower-body muscles as prime movers (e.g. running). Sprint kayaking imposes high demands on the upper-body endurance capacity of the athlete. As there are structural and physiological differences between upper- and lower-body musculature, TID in kayaking should be different to lower-body dominant sports. Therefore, we aimed to compare the training intensity distribution during an 8-wk macrocycle in a group of highly trained sprint kayakers employing three different methods of training intensity quantification. Methods Heart rate (HR) and velocity during on-water training of nine highly trained German sprint kayakers were recorded during the final 8 weeks of a competition period leading to the national championships. The fractional analysis of TID was based on three zones (Z) derived from either HR (TIDBla-HR) or velocity (TIDBla-V) based on blood lactate (Bla) concentrations (Z1 ≤ 2.5 mmol L−1 Bla, Z2 = 2.5–4.0 mmol L−1 Bla, Z3 ≥ 4.0 mmol L−1 Bla) of an incremental test or the 1000-m race pace (TIDRace): Z1 ≤ 85% of race pace, Z2 = 86–95% and Z3 ≥ 95%. Results TIDBla-V (Z1: 68%, Z2: 14%, Z3: 18%) differed from TIDBla-HR (Z1: 91%, Z2: 6%, Z3: 3%) in each zone (all p < 0.01). TIDRace (Z1: 73%, Z2: 20%, Z3: 7%) differed to Z3 in TIDBla-V (p < 0.01) and all three TIDBla-HR zones (all p < 0.01). Individual analysis revealed ranges of Z1, Z2, Z3 fractions for TIDBla-HR of 85–98%, 2–11% and 0.1–6%. For TIDBla-V, the individual ranges were 41–82% (Z1), 6–30% (Z2) and 8–30% (Z3) and for TIDRace 64–81% (Z1), 14–29% (Z2) and 4–10% (Z3). Conclusion The results show that the method of training intensity quantification substantially affects the fraction of TID in well-trained sprint kayakers. TIDRace determination shows low interindividual variation compared to the physiologically based TIDBla-HR and TIDBla-V. Depending on the aim of the analysis TIDRace, TIDBla-HR and TIDBla-V have advantages as well as drawbacks and may be implemented in conjunction to maximize adaptation.

Correlations between body postures and musculoskeletal pain in guitar players

Background The guitar-playing community is the largest group at risk of developing playing related musculoskeletal disorders. A thorough investigation of the relationships between the various risk factors and players’ report on musculoskeletal pain using objective and accurate means of assessment has yet to be reported. Purpose (a) to explore the correlations between demographic characteristics, anthropometric measurements, playing habits, and personal habits of guitar player and their complaints of musculoskeletal pain, (b) explore the correlations between the upper body kinematics of guitar players during playing the guitar and their complaints of musculoskeletal pain, and (c) compare the upper body kinematics of guitar players during playing the guitar while sitting versus standing. Methods Twenty-five guitar players (27.5±4.6 years old) filled out questionnaires regarding their guitar-playing habits, and the Standardized Nordic Questionnaires for the analysis of musculoskeletal symptoms. Kinematics of their torso and upper limbs were tracked while they played a tune twice, once while sitting and once while standing. Results We found moderate correlations between the number of painful joints in the last year and factors, such as physical comfort while playing, years of playing, and position during playing. During standing, lower back pain severity correlated with the rotation range of the torso, while during sitting, it moderately correlated with the average radial-ulnar deviation of the right wrist. During sitting, we found higher anterior and right tilt of the torso, combined with greater abduction of the right shoulder, higher flexion in the left shoulder and higher radial deviation in the left wrist. Conclusion Our results point to several risk factors, related both to playing habits but also to playing posture, which should be considered by the guitar players in order to prevent playing-related musculoskeletal disorders.

Aerobic Exercise Combination Intervention to Improve Physical Performance Among the Elderly: A Systematic Review

The benefits of aerobic exercise for the elderly are well-known. They extend beyond cardiovascular changes and can reduce the inactivity-induced loss of strength, mobility, balance, and endurance that are vital for the safe performance of daily activities in older adults. However, the benefits of combined aerobic exercise with other exercises such as strength/resistance, multi-component and aerobic exercise remain unknown. The purpose of this study is to examine the effects of combined aerobic exercise on physical performance among the elderly, as opposed to single aerobic exercise. We searched four databases of SCOPUS, PubMed, EBSCOhost, and CINAHL Plus to find 18 articles that met criteria. Data was extracted using PICOs extraction tool and summarized using a narrative synthesis approach. Studies have shown that aerobics combined resistance/strength training (CEX), multi-component training (ME), and dance combined training has positive and significant effects on the physical performance (upper body strength and lower body strength, dynamic balance, fall risk, mobility, gait, agility, flexibility) of the elderly. CEX had additional benefits compared to aerobic training (AER) and resistance/strength training (RES) in gait speed, lower limb strength, and trunk fat. Furthermore, CEX was more effective than AER in improving sitting and stretching, elbow flexion, knee flexion, shoulder flexion and stretching, strength and body fat, function reach test, 30-s chair standing test and 6-min walking test, self-evaluation of body function. Therefore, the combination of multiple components contributes to the overall improvement in physical fitness of the elderly, thus preventing them from losing balance and reducing susceptibility to injury.Clinical Trial Registration: [https://www.crd.york.ac.uk/prospero/#recordDetails], identifier [CRD42021213147].

Inferring Humor Styles Through Men’s Formidability

Men’s formidability is inferred multimodally through various facial and bodily features. Such inferences frequently provide downstream perceptions of various traits and motivational states that inform subsequent affiliative decisions. Within these inferences could be an implicit understanding of men’s preferred humor styles. Across four studies, this research considered perceptions of men’s proclivity to employ each of the four humor styles through different formidability cues: upper body strength (Study 1), body muscularity (Study 2), facial width-to-height ratio (Study 3), and neck musculature (Study 4). Results indicated a relatively consistent perception of formidable features being diagnostic of men’s interest in aggressive humor. Additional findings indicate certain formidability cues connote a disinterest in self-defeating and self-enhancing humor. Facial and bodily cues finally connoted affiliative humor in different capacities. We frame findings from an evolutionary perspective based on perceptions of the various benefits and costs of different formidability features.