External Workloads Vary by Position and Game Result in US-based Professional Soccer Players.

Professional soccer is a physically demanding sport that requires players to be highly trained. Advances using GPS allow the tracking of external workloads for individual players in practice and competition, however, there is a lack of evidence on how these measures impact match results. Therefore, we analyzed external workloads by player position and determined if they vary depending on the result of competitive matches. External workloads were analyzed in professional soccer players (n = 25) across 28 competitive games. One-way ANOVA determined if workloads varied by position (striker - ST, wide midfielder - WM, central midfielder - CM, wide defender - WD, central defender - CD) or across games won (n = 8), lost (n = 13) or tied (n = 7). Repeated-measures ANOVA assessed differences in workloads specific to each position in each of the result categories. Statistical significance was set at p < 0.05. Across all games, more high-speed and very-high speed running was done by ST and WD compared to CD (p < 0.001) and CM (p < 0.001 - 0.02). Whole-team data showed no differences in any external workload variable with respect to match result (p > 0.05), however, in games won ST did more very high-speed running than in losing games (p = 0.03) and defending players did more high and very high-speed running in games tied vs. those won or lost (p < 0.05). Whole-team external workloads do not vary depending on the match result; however, high speed running may be a differentiating factor at the positional level. Coaches should consider position-specific analysis when examining player workloads.

Automated Detection of Aortic Stenosis Using Machine Learning.

BACKGROUND: Aortic stenosis (AS) is a degenerative valve condition that is underdiagnosed and undertreated. Detection of AS using limited two-dimensional echocardiography could enable screening and improve appropriate referral and treatment of this condition. The aim of this study was to develop methods for automated detection of AS from limited imaging data sets. METHODS: Convolutional neural networks were trained, validated, and tested using limited two-dimensional transthoracic echocardiographic data sets. Networks were developed to accomplish two sequential tasks: (1) view identification and (2) study-level grade of AS. Balanced accuracy and area under the receiver operator curve (AUROC) were the performance metrics used. RESULTS: Annotated images from 577 patients were included. Neural networks were trained on data from 338 patients (average n = 10,253 labeled images), validated on 119 patients (average n = 3,505 labeled images), and performance was assessed on a test set of 120 patients (average n = 3,511 labeled images). Fully automated screening for AS was achieved with an AUROC of 0.96. Networks can distinguish no significant (no, mild, mild to moderate) AS from significant (moderate or severe) AS with an AUROC of 0.86 and between early (mild or mild to moderate AS) and significant (moderate or severe) AS with an AUROC of 0.75. External validation of these networks in a cohort of 8,502 outpatient transthoracic echocardiograms showed that screening for AS can be achieved using parasternal long-axis imaging only with an AUROC of 0.91. CONCLUSION: Fully automated detection of AS using limited two-dimensional data sets is achievable using modern neural networks. These methods lay the groundwork for a novel method for screening for AS.

A prescribed walking regimen plus arginine supplementation improves function and quality of life for patients with pulmonary arterial hypertension: a pilot study.

Current evidence suggests that exercise training is beneficial in pulmonary arterial hypertension (PAH). Unfortunately, the standard supervised, hospital-based programs limit patient accessibility to this important intervention. Our proof-of-concept study aimed to provide insight into the usefulness of a prescribed walking regimen along with arginine supplementation to improve outcomes for patients with PAH. Twelve PAH patients (all women) in New York Heart Association (NYHA) functional class (FC) II (n = 7) or III (n = 5) and in stable condition for ≥ 3 months were enrolled. Patients performed home- and fitness-center- based walking at 65-75% heart rate (HR) reserve for 45 min, six sessions/week for 12 weeks. Concomitant L-arginine supplementation (6000 mg/day) was provided to maximize beneficial endothelial training adaptations. Cardiopulmonary exercise testing, 6-min walk testing (6MWT), echocardiography, laboratory studies, and quality of life (QoL) survey (SF-36) were performed at baseline and 12 weeks. Eleven patients completed the study (72 session adherence rate = 96 ± 3%). Objective improvement was demonstrated by the 6MWT distance (increased by 40 ± 13 m, P = 0.01), VO2max (increased by 2 ± 0.7 mL/kg/min, P = 0.02), time-to-VO2max (increased by 2.5 ± 0.6 min, P = 0.001), VO2 at anaerobic threshold (increased by 1.3 ± 0.5 mL/kg/min, P = 0.04), HR recovery (reduced by 68 ± 23% in slope, P = 0.01), and SF-36 subscales of Physical Functioning and Energy/Fatigue (increased by 70 ± 34% and 74 ± 34%, respectively, P < 0.05). No adverse events occurred, and right ventricular function and brain natriuretic peptide levels remained stable, suggesting safety of the intervention. This proof-of-concept study indicates that a simple walking regimen with arginine supplementation is a safe and efficacious intervention for clinically stable PAH patients, with gains in objective function and QoL measures. Further investigation in a randomized controlled trial is warranted.