The use of isolated supplements to enhance performance is widespread among athletes. The aim of this study was to increase knowledge about the combined effects of caffeine and New Zealand blackcurrant (NZBC) dietary supplements. In this study, two subjects each underwent four phases of four sessions in a double-blind and randomized alternating treatment single-case design. After a 3-week pre-test phase, the supplement combinations of placebo/placebo, caffeine/placebo (5 mg/kg), NZBC/placebo (600 mg), and caffeine/NZBC (5 mg/kg + 600 mg) were taken and weekly performance tests were conducted to examine their effects on relative power (W/kg) during a 20-minute time trial on a bicycle. Data were analyzed descriptively and using the Tau-U calculator from Single Case Research. The ergogenic effect of caffeine was confirmed in both subjects, with increases of 3.3% and 6.5%, while the positive effect of NZBC on performance was only seen in one subject (13.4%). The combination of caffeine and NZBC again increased performance in both subjects (2.2% and 19.2%), but the data only showed an additive effect of the supplements in one subject. Further studies are required to confirm or refute this evidence of the synergistic effects of these supplements.

Postural deficits such as hyperlordosis (hollow back) or hyperkyphosis (hunchback) are relevant health issues. Diagnoses depend on the experience of the examiner and are therefore often subjective and prone to errors. Machine learning (ML) methods in combination with explainable ar-tificial intelligence (XAI) tools have proven useful for providing an objective, data-based orien-tation. However, only a few works have considered posture parameters, leaving the potential of more human-friendly XAI interpretations still untouched. Therefore, the present work proposes an objective, data-driven ML system for medical decision support that enables especially human-friendly interpretations using counterfactual explanations (CFs). Posture data for 1151 subjects were recorded by means of stereophotogrammetry. An expert-based classification of the subjects regarding the presence of hyperlordosis or hyperkyphosis was initially performed. Using a Gaussian progress classifier, the models were trained and interpreted using CFs. Label errors were flagged and re-evaluated using confident learning. Very good classification performances for both hyperlordosis and hyperkyphosis were found, whereby the re-evaluation and correction of the test labels led to a significant improvement (MPRAUC = 0.97). A statistical evaluation showed that the CFs seemed to be plausible in general. In the context of personalized medicine, the present study’s approach could be of importance for reducing diagnostic errors and thereby improving the individual adaptation of therapeutic measures. Likewise, it could be a basis for the development of apps for preventive posture assessment.

Individuals may exhibit altered foot mechanics, in this case foot pronation, only when fatigue sets in. Therefore, a more evidence-based understanding of these fatigue-induced changes may be helpful for future gait analysis and return to play tests, since fatigue could provide new insights that might explain a person’s complaints. Methods: 25 healthy test persons (24.3±2.7 years, BMI: 22.7±2.8) participated in this controlled non-randomized study of unilateral fatigue of the right foot stabilizing muscles with regard to the pronation of the foot, measured by navicular drop (ND) in a static (statND) und dynamic (dynND) state. The left foot served as a control. Surface electromyography was used to verify fatigue. Results: While statND didn’t change, the dynND increased significantly by 1.44±2.1 mm (= 22.3 %) after fatigue of the foot stabilizing muscles. No correlation was found between statND and dynND. Conclusion: Muscular fatigue can affect foot pronation. The dynND appears to be more representative of the loads in everyday life, whereby most studies work with the statND.