XSENSOR's Sports Performance Science Contributor, Antonio Robustelli, MSc, CSCS (Sports Performance Scientist & Technologist with OmniAthlete Performance Concept), offers his take on essential and recommended reading, research, and review for plantar pressure applications using gait analysis for athletes.
Be sure to tune in to get the abstracts, summaries, and key takeaways, or read the complete studies.
Purpose: This paper aims to provide a comprehensive analysis of plantar pressure measurement systems used within sports biomechanics. It examines the underlying sensor technologies, their technical specifications, calibration methodologies, and critically evaluates their applications in analyzing athletic performance and understanding sports-related injury mechanisms.
Design/Methodology/Approach: An extensive literature search was conducted across multiple academic databases to identify peer-reviewed articles pertaining to plantar pressure sensors (capacitive, piezoresistive, piezoelectric, optical, micro-electro-mechanical systems [MEMS]), measurement systems (in-shoe, platform), sports biomechanics applications (running, jumping, cutting, cycling, golf, skiing, team sports), performance analysis, injury risk assessment (stress fractures, plantar fasciitis [PF], Achilles tendinopathy, patellofemoral pain, ankle instability), rehabilitation monitoring and system validation. Key information regarding sensor principles, specifications, calibration, study methodologies, findings, and limitations was systematically extracted and synthesized.
Findings: Various sensor technologies offer distinct advantages and disadvantages for sports biomechanics applications. Capacitive and piezoresistive sensors are prevalent in commercial systems, whereas piezoelectric, optical fiber, and MEMS technologies present emerging alternatives with potential benefits in sensitivity, durability, or integration. Plantar pressure data provides valuable insights into athletic performance by quantifying parameters such as force distribution, Center of Pressure dynamics, and loading symmetry across diverse sporting activities, including running, jumping, cutting, cycling, golf, and skiing. Furthermore, specific plantar pressure patterns, such as elevated regional pressures or altered loading rates, have been associated with increased risk of common sports injuries, including stress fractures, PF, and chronic ankle instability, although establishing definitive causality remains challenging. In-shoe systems offer ecological validity for field-based measurements crucial for sports, whereas platform systems provide higher spatial resolution suitable for laboratory analyses. Validation and calibration remain critical considerations, with significant variability reported between systems and tasks.
Originality/Value: This review synthesizes current knowledge across a broad spectrum of sensor technologies and their specific applications in sports biomechanics, encompassing both performance enhancement and injury analysis. It provides a comparative analysis of different measurement systems, evaluates the state of the art, including validation methodologies, identifies knowledge gaps, and discusses future research directions, offering a valuable resource for researchers, clinicians, coaches, and engineers in the field.
Why the Study is Relevant
The study aims to provide a comprehensive overview of plantar pressure measurement systems in the context of sports biomechanics. The study is a literature review and is relevant because it provides a comprehensive synthesis of plantar pressure measurement technologies within a sports biomechanics context. The authors have systematically compared technical features, including sensor technologies, calibration methods, validation, and sport specific applications, across the domains of performance, injury risk, and rehabilitation. A key limitation of the study is the absence of quantitative meta analysis and sport specific outcome synthesis, meaning causal inferences remain largely theoretical. However, the paper is valuable as a reference framework to inform technology selection in sport science.
Summary
The foot-ankle complex, as the initial point of contact with the ground during human locomotion, plays a pivotal role in attenuating impact forces and stabilizing joint motion, thereby reducing the risk of lower extremity injuries. Understanding the forces exerted on the plantar surface of the foot during movement is fundamental to the field of sports biomechanics. Plantar pressure mapping, the pressure distribution acting on the plantar surface of the foot, provides a quantitative measure of how forces are distributed during static postures and during dynamic activities such as walking, running, jumping, and cutting. The authors of this review tried to provide a comprehensive overview of plantar pressure measurement systems in the context of sports biomechanics.
Key Takeaways
Plantar pressure measurement systems have become indispensable tools in sportsbiomechanics, offering valuable data for performance analysis and injuryprevention.
Plantar pressure data can inform performance and injury risk, but variability in sensortechnology, calibration, and task demands limits direct comparability andweakens causal inference if data are interpreted in isolation.
Sensor hysteresis, drift, and task‑specific loading conditions significantly affectdata quality, highlighting the need for sport‑specific calibration protocolsand cautious use of absolute pressure metrics.
GPlantar pressure analysis is a pivotal tool for assessing foot function, diagnosing deformities, and characterizing gait patterns. Traditional proportion-based segmentation methods are often limited, particularly for atypical foot structures and low-quality data. Although recent advances in machine learning (ML) offer opportunities for automated and robust segmentation across diverse datasets, existing models primarily rely on data from single laboratories, limiting their applicability to multicenter datasets. Furthermore, the prediction of relevant landmarks on the plantar pressure profile has not been explored. This study addresses these gaps by exploring ML-based approaches for anatomical zone segmentation and landmark detection in plantar pressure analysis, including 758 plantar pressure samples from 460 individuals (197 females, 263 males), collected across multiple centers under static and dynamic conditions using two distinct systems. The datasets were further standardized and augmented. The plantar surface was segmented into four regions (hallux, metatarsal area 1, metatarsal areas 2–5, and the heel) using a U-Net model, and deep learning regression models predicted the key points, such as interdigital space coordinates and the center of metatarsal area 1. The results underscore the U-Net’s ability to achieve accuracy comparable to that of experts (Median Dice Scores ≥ 0.88), particularly in regions with well-defined plantar pressure boundaries. Metatarsal area 1 exhibited unique characteristics due to its ambiguous boundaries, and expert reviews played a valuable role in enhancing accuracy in critical cases. Using a regression model (Median Euclidean distance = 7.72) or an ensemble model (Median Euclidean distance = 5.26) did not improve the calculation of the center of metatarsal area 1 directly from the segmentation model (Median Euclidean distance = 4.47). Furthermore, regression-based approaches produced higher errors in key point detection of interdigital space 2–3 (Median Euclidean distance = 10.06) than in the metatarsal area 1 center (Median Euclidean distance = 7.72). These findings emphasize the robustness of the proposed segmentation and key-point prediction models across diverse datasets and hardware configurations. Overall, the proposed methods facilitate the efficient processing of large, multicenter datasets across diverse hardware setups, significantly reducing the reliance on extensive human labeling, lowering costs, and minimizing subjective bias through ML-driven standardization. Leveraging these strengths, this work introduces a novel framework that integrates multicenter plantar pressure data for both segmentation and landmark detection, offering practical value in clinical and research settings by enabling standardized, automated analyses across varying hardware configurations.
Why the Study is Relevant
The study aims to investigate the effectiveness of ML-based approaches for plantar pressure segmentation. The study has a very good sample size (n=460); however, the description of the equipment used is incomplete, including sensor resolution, sampling rate, and the number of pressure sensors.
The paper is relevant because it addresses a key issue in plantar pressure analysis: the subjectivity and limited scalability of manual or proportion based foot segmentation. In fact, the authors demonstrated that automated anatomical segmentation and key point detection can achieve expert level accuracy by using Machine-Learning models.
Summary
Foot deformities are a common problem across age groups and sexes in Western societies and can cause injuries to the lower limbs or even back pain. Plantar pressure analysis plays a crucial role in evaluating, diagnosing, and characterizing gait patterns in patients and provides valuable insights into foot function. Many tasks related to plantar pressure analysis rely heavily on segmenting (also called zoning) pressure profiles into specific areas of interest, such as the medial and lateral zones, to compare pressure distributions (e.g., pronation vs. supination). The authors of this study tried to investigate the effectiveness of ML-based approaches for plantar pressure segmentation as an alternative to manual identification and detection.
Key Takeaways
Deep learning–based plantar pressure segmentation achieves accuracy comparable toexpert manual labeling, reducing operator dependency and enabling large‑scale,multi‑center data analysis.
Despite high technical accuracy, automated outputs still require biomechanicalexpertise to ensure meaningful interpretation, particularly in complex, high‑intensitysport‑specific tasks.
Background: During landing, athletes with Chronic Ankle Instability (CAI) often exhibit abnormal ankle joint movements, with these changes becoming more pronounced as height increases. There is insufficient research on assessing foot pressure distribution during landing at different heights in athletes with CAI, which would help determine their injury risk.
Methods: Twenty male athletes with CAI and twenty healthy controls were recruited in a 2 (group: CAI vs. healthy) × 2 (height: 30 cm vs. 40 cm) mixed experimental design. A 2 × 2 mixed-design ANOVA was used to evaluate foot pressure distribution during landing, measured with a 400 × 400 mm FreeMed baropodometric platform.
Results: Interaction effects were detected in peak force: metatarsal head 3 (MH3) (p = 0.047); load percentage: toes 2–5 (T2–5) (p = 0.050), MH3 (p = 0.038), rearfoot lateral (RF_L) (p = 0.045); peak pressure: MH3 (p = 0.013). Group effects were detected in peak force: T2–5 (p < 0.001), metatarsal head 4 (MH4) (p < 0.001), midfoot lateral (MF_L) (p < 0.001), and RF_L (p < 0.001); load percentage: MH4 (p < 0.001), MF_L (p < 0.001); peak pressure: T2–T5 (p = 0.001), MH4 (p < 0.001), MF_L (p < 0.001), and RF_L (p = 0.033); vCOP (p = 0.018). Pairwise comparisons showed that the peak force, pressure, and load distribution of athletes with CAI in T2–5, MH3, MH4, MF_L, and RF_L were significantly higher than those of the healthy group (p < 0.05). Additionally, the load percentage in RF_L and vCOP of athletes with CAI at a height of 40 cm was significantly greater than that of the healthy group (p < 0.05).
Conclusion: Compared with healthy individuals, athletes with CAI exhibit increased peak forces, pressures, and load percentage at T2–5, MH3, MH4, MF_L, and RF_L during landing. The load percentage in RF_L and vCOP increases with height in athletes with CAI, reflecting impaired postural control and a higher risk of reinjury. This highlights the need for trainers to design specific training programs tailored to the distribution of foot pressure during landing exercises.
Why the Study is Relevant
The study aims to analyze plantar pressure distribution in athletes with Chronic Ankle Instability (CAI) during one-foot landings from different heights. An acceptable sample size (n=40) has been employed, and the measurement protocol has been clearly and appropriately described.
The paper is relevant as it provides evidence linking plantar pressure distribution to injury related movement deficits in a sport specific task. The main limitation is that using a platform based system compromises ecological validity, and findings may not fully generalize to continuous, high speed sport movements. Additionally, causal links to injury risk remain inferential rather than longitudinally demonstrated.
Summary
Ankle sprains are among the most common injuries in competitive sports. It usually occurs during jumping and landing activities, and over 40% of individuals with an ankle sprain develop chronic ankle instability (CAI). Therefore, investigating the landing performance of athletes with CAI holds essential theoretical and practical significance.
The authors of this study sought to analyze plantar pressure distribution in athletes with CAI during one-foot landings from different heights.
Key Takeaways
Athletes with chronic ankle instability exhibit distinct plantar pressure patternsduring single‑leg landings, suggesting compensatory foot loading strategiesthat may influence joint stability and tissue stress.
Plantar load pattern of athletes with CAI shifts from the medial to the lateral area.