In alpine skiing, four commonly used turning styles are snowplow, snowplow-steering, drifting and carving. They differ significantly in speed, directional control and difficulty to execute. While they are visually distinguishable, data-driven classification is underexplored. The aim of this work is to classify alpine skiing styles based on a global navigation satellite system (GNSS) and inertial measurement units (IMU). Data of 2000 turns of 20 advanced or expert skiers were collected with two IMU sensors on the upper cuff of each ski boot and a mobile phone with GNSS. After feature extraction and feature selection, turn style classification was applied separately for parallel (drifted or carved) and non-parallel (snowplow or snowplow-steering) turns. The most important features for style classification were identified via recursive feature elimination. Three different classification methods were then tested and compared: Decision trees, random forests and gradient boosted decision trees. Classification accuracies were lowest for the decision tree and similar for the random forests and gradient boosted classification trees, which both achieved accuracies of more than 93% in the parallel classification task and 88% in the non-parallel case. While the accuracy might be improved by considering slope and weather conditions, these first results suggest that IMU data can classify alpine skiing styles reasonably well.

The search for monitoring tools that provide early indication of injury and illness could contribute to better player protection. The aim of the present study was to i) determine the feasibility of and adherence to our monitoring approach, and ii) identify variables associated with up-coming illness and injury. We incorporated a comprehensive set of monitoring tools consisting of external load and physical fitness data, questionnaires, blood, neuromuscular-, hamstring, hip abductor and hip adductor performance tests performed over a three-month period in elite under-18 academy soccer players. Twenty-five players (age: 16.6 ± 0.9 years, height: 178 ± 7 cm, weight: 74 ± 7 kg, VO2max: 59 ± 4 ml/min/kg) took part in the study. In addition to evaluating adherence to the monitoring approach, data were analyzed using a linear support vector machine (SVM) to predict illness and injuries. The approach was feasible, with no injuries or dropouts due to the monitoring process. Questionnaire adherence was high at the beginning and decreased steadily towards the end of the study. An SVM resulted in the best classification results for three classification tasks, i.e., illness prediction, illness determination and injury prediction. For injury prediction, one of four injuries present in the test data set was detected, with 96.3% of all data points (i.e., injuries and non-injuries) correctly detected. For both illness prediction and determination, there was only one illness in the test data set that was detected by the linear SVM. However, the model showed low precision for injury and illness prediction with a considerable number of false-positives. The results demonstrate the feasibility of a holistic monitoring approach with the possibility of predicting illness and injury. Additional data points are needed to improve the prediction models. In practical application, this may lead to overcautious recommendations on when players should be protected from injury and illness.

Inertial measurement units (IMU) are widely used in sports applications to digitise human motion by measuring acceleration and rotational velocity in three-dimensional space. A common machine learning problem is the classification of human motion primitives from IMU data. In order to investigate the classification methods used in the existing literature and to analyse whether and how the time-dependent data structure is considered in the classification process of motion data analysis in sports, a scoping review was conducted. Based on a keyword search, articles from 2010 to 2021 were extracted, and 93 articles were relevant for data extraction. Over- and undersampling of data and data augmentation techniques were rarely used. The classification methods applied can be divided into three main branches: classic machine learning and deep learning models, threshold-based approaches, and dynamic time warping. The most often applied algorithms were support vector machines (SVM), followed by neural networks and k-nearest neighbours. In comparative works, when more than one classifier was applied, random forests, neural networks, boosting models and SVM were found to be the methods that achieved the highest accuracy. If the time-dependent data structure was taken into account, it was incorporated either within the models, for example, by using long-short-term memory models or within the feature calculation step by using rolling windows with an overlap, which was the most common method of considering the time dependency of the IMU data.

The foot strike pattern performed during running is an important variable for runners, performance practitioners, and industry specialists. Versatile, wearable sensors may provide foot strike information while encouraging the collection of diverse information during ecological running. The purpose of the current study was to predict foot strike angle and classify foot strike pattern from Loadsol^TM wearable pressure insoles using three machine learning techniques (multiple linear regression―MR, conditional inference tree―TREE, and random forest―FRST). Model performance was assessed using three-dimensional kinematics as a ground-truth measure. The prediction-model accuracy was similar for the regression, inference tree, and random forest models (RMSE: MR = 5.16°, TREE = 4.85°, FRST = 3.65°; MAPE: MR = 0.32°, TREE = 0.45°, FRST = 0.33°), though the regression and random forest models boasted lower maximum precision (13.75° and 14.3°, respectively) than the inference tree (19.02°). The classification performance was above 90% for all models (MR = 90.4%, TREE = 93.9%, and FRST = 94.1%). There was an increased tendency to misclassify mid foot strike patterns in all models, which may be improved with the inclusion of more mid foot steps during model training. Ultimately, wearable pressure insoles in combination with simple machine learning techniques can be used to predict and classify a runner’s foot strike with sufficient accuracy.

Load management, i.e., prescribing, monitoring, and adjusting training load, is primarily aimed at preventing injury and maximizing performance. The search for objective monitoring tools to assess the external and internal load of athletes is of great interest for sports science research. In this 4-week pilot study, we assessed the feasibility and acceptance of an extensive monitoring approach using biomarkers, neuromuscular performance, and questionnaires in an elite youth soccer setting. Eight male players (mean ± SD: age: 17.0 ± 0.6 years, weight: 69.6 ± 8.2 kg, height: 177 ± 7 cm, VO_2max: 62.2 ± 3.8 ml/min/kg) were monitored with a local positioning system (e.g., distance covered, sprints), biomarkers (cell-free DNA, creatine kinase), questionnaires, neuromuscular performance testing (counter-movement jump) and further strength testing (Nordic hamstring exercise, hip abduction and adduction). Feasibility was high with no substantial impact on the training routine and no adverse events such as injuries during monitoring. Adherence to the performance tests was high, but adherence to the daily questionnaires was low, and decreased across the study period. Occasional significant correlations were observed between questionnaire scores and training load data, as well as between questionnaire scores and neuromuscular performance. However, due to the small sample size, these findings should be treated with caution. These preliminary results highlight the feasibility of the approach in elite soccer, but also indicate that modifications are needed in further large-scale studies, particularly in relation to the length of the questionnaire.

Artificial intelligence (AI) and machine learning (ML) are increasingly being applied in sports science to predict performance, assess injury risk, and support tactical decision-making. However, the opacity of many machine learning (ML) models has led to a growing interest in explainable AI (XAI) methods, which aim to make the decisions of "black box" algorithms more transparent and interpretable. The result of this is an increase in trust, facilitation of model validation, and enablement of more informed decision-making for practitioners and analysts. While XAI is well established in domains like healthcare or finance, its application in sports science remains fragmented and underexplored. This scoping review follows the PRISMA-Sc approach and systematically examines how XAI and interpretable ML techniques have been applied in the context of sports science. Between 2014 and June 2024, a total of 19 studies were identified through a multi-database search and analyzed in terms of sport type, ML model, XAI method, dependent variable, limitations, challenges and future research. The results reveal a clear dominance of SHapley Additive Explanations across multiple disciplines, while other tools such as Gradient-weighted Class Activation Mapping, Individual Conditional Expectation Plots, or domain-specific approaches are rarely used. Visual and rule-based explanation methods were largely absent. The findings highlight a lack of methodological diversity and limited validation of explanations with domain experts or practitioners. To increase real-world impact, future work should explore comparative evaluations of XAI techniques, domain-specific explanation frameworks, and user-centered approaches that align with the needs of coaches, athletes, and analysts.