The usage of smart glasses in goods logistics and order picking has mainly been studied through cross-sectional experimental studies. Our longitudinal field study investigated the effects of smart glasses on the eyesight of 43 employees at two German companies. We combined ophthalmological examinations and questionnaire surveys at two points in time, six months apart. The vision of the employees was examined before and after each work shift. Mixed effects logistic regression was conducted to determine the associations between smart glasses use and effects on visual acuity. In the baseline examination, differences in eyesight before and after shifts were small and not statistically significant. However, some individuals experienced deteriorations, especially in visual acuity at near distances (n = 7 for the right eye, n = 6 for the left). Participants over 40 years of age had 16.1 times higher odds of deterioration compared to those under 40 years (95% CI: 2.7–95.9, p = 0.002). The most commonly reported eye strains were eye fatigue (n = 32), rubbing (n = 25), and burning (n = 24). If smart glasses are to be implemented in logistics companies, it is recommended to offer employees eye tests with an industrial physician in advance.

Use of head-mounted displays (HMDs) and hand-held displays (HHDs) may affect the effectiveness of stability control mechanisms and impair resistance to falls. This study aimed to examine whether the ability to control stability during locomotion is diminished while using HMDs and HHDs. Fourteen healthy adults (21–46 years) were assessed under single-task (no display) and dual-task (spatial 2-n-back presented on the HMD or the HHD) conditions while performing various locomotor tasks. An optical motion capture system and two force plates were used to assess locomotor stability using an inverted pendulum model. For perturbed standing, 57% of the participants were not able to maintain stability by counter-rotation actions when using either display, compared to the single-task condition. Furthermore, around 80% of participants (dual-task) compared to 50% (single-task) showed a negative margin of stability (i.e., an unstable body configuration) during recovery for perturbed walking due to a diminished ability to increase their base of support effectively. However, no evidence was found for HMDs or HHDs affecting stability during unperturbed locomotion. In conclusion, additional cognitive resources required for dual-tasking, using either display, are suggested to result in delayed response execution for perturbed standing and walking, consequently diminishing participants’ ability to use stability control mechanisms effectively and increasing the risk of falls.

Slip, trip, and fall (STF) accidents cause high rates of absence from work in many companies. During the 2022 reporting period, the German Social Accident Insurance recorded 165,420 STF accidents, of which 12 were fatal and 2485 led to disability pensions. Particularly in the traffic, transport and logistics sector, STF accidents are the most frequently reported occupational accidents. Therefore, an accurate detection of near-falls is critical to improve worker safety. Efficient detection algorithms are essential for this, but their performance heavily depends on large, well-curated datasets. However, there are drawbacks to current datasets, including small sample sizes, an emphasis on older demographics, and a reliance on simulated rather than real data. In this paper we report the collection of a standardised kinematic STF dataset from real-world STF events affecting parcel delivery workers and steelworkers. We further discuss the use of the data to evaluate dynamic stability control during locomotion for machine learning and build a standardised database. We present the data collection, discuss the classification of the data, present the totality of the data statistically, and compare it with existing databases. A significant research gap is the limited number of participants and focus on older populations in previous studies, as well as the reliance on simulated rather than real-world data. Our study addresses these gaps by providing a larger dataset of real-world STF events from a working population with physically demanding jobs. The population studied included 110 participants, consisting of 55 parcel delivery drivers and 55 steelworkers, both male and female, aged between 19 and 63 years. This diverse participant base allows for a more comprehensive understanding of STF incidents in different working environments.

Biomechanical data play a crucial role in health research by providing relevant information about musculoskeletal mechanical loading and neuromuscular dysfunction during movement, which are essential for optimizing treatment strategies and improving patient outcomes. The relevance of such data for decision making processes in clinical settings depends on its quality and volume, as larger datasets enable more robust conclusions across diverse populations and conditions. In machine learning, extensive and representative datasets are vital for training algorithms to develop accurate predictive models. This systematic literature review explores the current landscape of biomechanical datasets and databases, examining existing resources, identifying gaps in data availability and quality, and discussing the potential for a new, structured database to address these shortcomings. We conducted a comprehensive search across PubMed, IEEE Xplore, Scopus, ScienceDirect, Springer, and arXiv using keywords related to biomechanics, gait, and human activity recognition (HAR). The review identified studies covering various motion types, data formats, and metadata availability. Our findings highlight significant challenges, including inconsistent metadata, lack of standardization during data acquisition and data processing, limited motion variety, and accessibility issues. Addressing these challenges through standardized data formats, comprehensive metadata, and enhanced accessibility could greatly advance decision making processes via machine learning approaches for clinical and therapeutic settings. This review emphasizes the need for improved biomechanical data resources to support the development of accurate machine learning models and innovative clinical interventions.

Objectives: The objective of this study was to assess the current usage, challenges, and specific needs regarding biomechanical data, with a focus on gait analysis, across a diverse field such as sports performance, clinical rehabilitation, and occupational health. Methods: We conducted a survey among more than 300 institutions in the DACH region (Germany, Austria, Switzerland). Of 49 individuals who began the survey, 24 submitted complete responses. Results: Findings indicate that participants recognize the value of biomechanical data, yet adoption of publicly available datasets is hindered by inconsistent formats, limited metadata, and strict privacy regulations. Respondents emphasized standardized documentation and clearer guidelines to facilitate sharing and collaboration. Many institutions are overwhelmed by legal compliance, with data proception laws posing significant hurdles to effective usage. Conclusions: The results highlight the need to (1) establish standardized file formats, (2) improve metadata quality, (3) develop transparent, consistent data-sharing protocols, and (4) clarify legal frameworks for compliance.

Understanding the decision-making behavior of machine learning models is essential in domains where individual predictions matter, such as medical diagnosis or sports analytics. While explainable artificial intelligence (XAI) methods such as SHAP provide instance-level feature attributions, they mainly summarize typical decision behavior and offer limited support for systematically exploring atypical yet correctly classified cases. In this work, we introduce the Classification Outlier Variability Score (COVAS), a framework designed to support hypothesis generation through the analysis of explanation variability. COVAS operates in the explanation space and builds directly on SHAP value representations. It quantifies how strongly an individual instance’s SHAP-based explanation deviates from class-specific attribution patterns by aggregating standardized SHAP deviations into a single score. Consequently, the applicability of COVAS inherits the model- and data-agnostic properties of SHAP, provided that explanations can be computed for the underlying model and data. We evaluate COVAS on publicly available datasets from the medical and sports domains. The results show that COVAS reveals explanation-space outliers not captured by feature-space outlier detection or prediction uncertainty measures. Robustness analyses demonstrate stability across parameter choices, class imbalance, model initialization, and model classes. Overall, COVAS complements existing XAI techniques by enabling targeted instance-level inspection and facilitating XAI-guided hypothesis formulation.