Dataset Information

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks.

ABSTRACT: Vertical ground reaction force (GRFz) measurements are the best tool for assessing horses' weight-bearing lameness. However, collection of these data is often impractical for clinical use. This study evaluates GRFz predicted using data from body-mounted IMUs and long short-term memory recurrent neural networks (LSTM-RNN). Twenty-four clinically sound horses, equipped with IMUs on the upper-body (UB) and each limb, walked and trotted on a GRFz measuring treadmill (TiF). Both systems were time-synchronised. Data from randomly selected 16, 4, and 4 horses formed training, validation, and test datasets, respectively. LSTM-RNN with different input sets (All, Limbs, UB, Sacrum, or Withers) were trained to predict GRFz curves or peak-GRFz. Our models could predict GRFz shapes at both gaits with RMSE below 0.40 N.kg^-1. The best peak-GRFz values were obtained when extracted from the predicted curves by the all dataset. For both GRFz curves and peak-GRFz values, predictions made with the All or UB datasets were systematically better than with the Limbs dataset, showing the importance of including upper-body kinematic information for kinetic parameters predictions. More data should be gathered to confirm the usability of LSTM-RNN for GRFz predictions, as they highly depend on factors like speed, gait, and the presence of weight-bearing lameness.

SUBMITTER: Parmentier JIM

PROVIDER: S-EPMC9839734 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks.

Parmentier J I M JIM Bosch S S van der Zwaag B J BJ Weishaupt M A MA Gmel A I AI Havinga P J M PJM van Weeren P R PR Braganca F M Serra FMS

Scientific reports 20230113 1

Vertical ground reaction force (GRFz) measurements are the best tool for assessing horses' weight-bearing lameness. However, collection of these data is often impractical for clinical use. This study evaluates GRFz predicted using data from body-mounted IMUs and long short-term memory recurrent neural networks (LSTM-RNN). Twenty-four clinically sound horses, equipped with IMUs on the upper-body (UB) and each limb, walked and trotted on a GRFz measuring treadmill (TiF). Both systems were time-syn ...[more]

PMID: 36639409

Similar Datasets

Project description:BackgroundArtificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research.ObjectiveThis systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities. The focus will be on the types of models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research.MethodsThis study examines this synergy of AI models and IMU data by using a systematic methodology, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, to explore 3 core questions: (1) Which medical fields are most actively researching AI and IMU data? (2) Which models are being used in the analysis of IMU data within these medical fields? (3) What are the characteristics of the datasets used for in this fields?ResultsThe median dataset size is of 50 participants, which poses significant limitations for AI models given their dependency on large datasets for effective training and generalization. Furthermore, our analysis reveals the current dominance of machine learning models in 76% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for deep learning models in this area. Impressively, 93% of the studies used supervised learning, revealing an underuse of unsupervised learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. In addition, there was a preference for conducting studies in clinical settings (77%), rather than in real-life scenarios, a choice that, along with the underapplication of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts.ConclusionsIn conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field toward the adoption of more complex deep learning models, and the expansion of the application of AI models on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research.

Project description:BackgroundWalking patterns can provide important indications of a person's health status and be beneficial in the early diagnosis of individuals with a potential walking disorder. For appropriate gait analysis, it is critical that natural functional walking characteristics are captured, rather than those experienced in artificial or observed settings. To better understand the extent to which setting influences gait patterns, and particularly whether observation plays a varying role on subjects of different ages, the current study investigates to what extent people walk differently in lab versus real-world environments and whether age dependencies exist.MethodsThe walking patterns of 20 young and 20 elderly healthy subjects were recorded with five wearable inertial measurement units (ZurichMOVE sensors) attached to both ankles, both wrists and the chest. An automated detection process based on dynamic time warping was developed to efficiently identify the relevant sequences. From the ZurichMOVE recordings, 15 spatio-temporal gait parameters were extracted, analyzed and compared between motion patterns captured in a controlled lab environment (10 m walking test) and the non-controlled ecologically valid real-world environment (72 h recording) in both groups.ResultsSeveral parameters (Cluster A) showed significant differences between the two environments for both groups, including an increased outward foot rotation, step width, number of steps per 180° turn, stance to swing ratio, and cycle time deviation in the real-world. A number of parameters (Cluster B) showed only significant differences between the two environments for elderly subjects, including a decreased gait velocity (p = 0.0072), decreased cadence (p = 0.0051) and increased cycle time (p = 0.0051) in real-world settings. Importantly, the real-world environment increased the differences in several parameters between the young and elderly groups.ConclusionElderly test subjects walked differently in controlled lab settings compared to their real-world environments, which indicates the need to better understand natural walking patterns under ecologically valid conditions before clinically relevant conclusions can be drawn on a subject's functional status. Moreover, the greater inter-group differences in real-world environments seem promising regarding the sensitive identification of subjects with indications of a walking disorder.

Dataset Information

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks.

Publications

Prediction of continuous and discrete kinetic parameters in horses from inertial measurement units data using recurrent artificial neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets