Validation of two hybrid approaches for clustering age-related groups based on gait kinematics data
Rafael Caldas, Rebeca Sarai, Fernando Buarque de Lima Neto, Bernd Markert
Age-associated changes in walking parameters are relevant to recognize functional capacity and physical performance. However, the sensible nuances of slightly different gait patterns are hardly noticeable by inexperienced observers. Due to the complexity of this evaluation, we aimed at verifying the efficiency of applied hybrid-adaptive algorithms to cluster groups with similar gait patterns. Based on self-organizing maps (SOM), k-means clustering (KM), and fuzzy c-means (FCM), we compared the hybrid algorithms to a conventional FCM approach to cluster accordingly age-related groups. Additionally, we performed a relevance analysis to identify the principal gait characteristics. Our experiments, based on inertial-sensors data, comprised a sample of 180 healthy subjects, divided into age-related groups. The outcomes suggest that our methods outperformed the FCM algorithm, demonstrating a high accuracy (88%) and consistent sensitivity also to distinguish groups that presented a significant difference (p < .05) only in one of the six observed gait features. The applied algorithms showed a compatible performance, but the SOM + KM required less computation cost and, therefore, was more efficient. Furthermore, the results indicate the overall importance of cadence, as a measurement of physical performance, especially when clustering subjects by their age. Such output provides valuable information to healthcare professionals, concerning the subject’s physical performance related to his age, supporting and guiding the physical evaluation.
Adaptive predictive systems applied to gait analysis: A systematic review
Rafael Caldas, Tariq Fadel, Fernando Buarque, Bernd Markert
Background: Due to the high susceptivity of the walking pattern to be affected by several disorders, accurate analysis methods are necessary. Given the complexity and relevance of such assessment, the utilization of methods to facilitate it plays a significant role, provided that they do not compromise the outcomes. Research questions: This paper aimed at identifying the standards for the application of adaptive predictive systems to gait analysis, given the extensive research on this field. Furthermore, we also intended to check whether such methods can effectively support clinicians in determining the number of physiotherapy sessions necessary to recover gait-related dysfunctions. Methods: Through a screening process of scientific databases, we considered studies encompassed from 1968 to April 2019. Within these 50 years, we found 24 papers that met our inclusion criteria. They were analyzed according to their data acquisition and processing methods via ad hoc questionnaires. Additionally, we examined quantitatively the adaptive approaches. Results: Concerning data acquisition, the included papers presented a mean score of 6.1 SD 1.0, most of them applying optoelectronic systems, and the ground reaction force (GRF) was the most used parameter. The AI quality assessment showed an above-average rate of 7.8 SD 1.0, and artificial neural networks (ANN) being the paradigm most frequently utilized. Our systematic review identified only one study that addressed therapeutics including a predictive method. Significance: While much progress has been identified to predict assessment aspects, there is little effort to assist healthcare professionals in establishing the rehabilitation duration and prognostics. Therefore, future studies should focus on accomplishing the production of applications of predictive methods to therapeutics and prog- nosis, not lingering extremely on the analysis of gait features.
Clustering of Self-Organizing Maps as a means to support gait kinematics analysis and symmetry evaluation
Rafael Caldas, Diego Rátiva, Fernando Buarque de Lima Neto
Gait analysis is relevant for the functional diagnostic of several musculoskeletal disorders. Walking pat- terns can be analyzed using techniques such as video processing and inertial measurement units (IMU). In this work, a Self-Organizing Maps (SOM) algorithm is applied to reduce the complexity of kinematic features obtained by IMU sensors of a sample of 40 individuals. Our system provides a simpler data rep- resentation (2-D graphic) than conventional methods, which often applies statistical analysis. We have tested the proposed method to analyze typical and simulated limping gait pattern under well-controlled conditions. Based on kinematic parameters and symmetry-related features, SOM algorithm was able to or- ganize the sample in groups of subjects with three different gait patterns, normal and limping with each lower limb. Moreover, our system may be used to evaluate the recovery of a patient, offering intuitive information of his walking pattern in an assessment report. However, further research with atypical-gait subjects is necessary before applying such method as a clinical tool.
A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms
Rafael Caldas, M. Mundt, W. Potthast, Fernando Buarque, B. Markert
The conventional methods to assess human gait are either expensive or complex to be applied regularly in clinical practice. To reduce the cost and simplify the evaluation, inertial sensors and adaptive algorithms have been utilized, respectively. This paper aims to summarize studies that applied adaptive also called artificial intelligence (AI) algorithms to gait analysis based on inertial sensor data, verifying if they can support the clinical evaluation. Articles were identified through searches of the main databases, which were encompassed from 1968 to October 2016. We have identified 22 studies that met the inclusion criteria. The included papers were analyzed due to their data acquisition and processing methods with specific questionnaires. Concerning the data acquisition, the mean score is 6.1 ± 1.62, what implies that 13 of 22 papers failed to report relevant outcomes. The quality assessment of AI algorithms presents an above-average rating (8.2 ± 1.84). Therefore, AI algorithms seem to be able to support gait analysis based on inertial sensor data. Further research, however, is necessary to enhance and standardize the application in patients, since most of the studies used distinct methods to evaluate healthy subjects.