RESUMEN
Artificial intelligence (AI) and machine learning (ML) methods are currently widely employed in medicine and healthcare. A PubMed search returns more than 100,000 articles on these topics published between 2018 and 2022 alone. Notwithstanding several recent reviews in various subfields of AI and ML in medicine, we have yet to see a comprehensive review around the methods' use in longitudinal analysis and prediction of an individual patient's health status within a personalized disease pathway. This review seeks to fill that gap. After an overview of the AI and ML methods employed in this field and of specific medical applications of models of this type, the review discusses the strengths and limitations of current studies and looks ahead to future strands of research in this field. We aim to enable interested readers to gain a detailed impression of the research currently available and accordingly plan future work around predictive models for deterioration in health status.
Asunto(s)
Inteligencia Artificial , Medicina de Precisión , Humanos , Aprendizaje AutomáticoRESUMEN
BACKGROUND AND PURPOSE: Hereditary spastic paraplegias (HSPs) comprise a group of inherited neurodegenerative disorders characterized by progressive spasticity and weakness. Botulinum toxin has been approved for lower limb spasticity following stroke and cerebral palsy, but its effects in HSPs remain underexplored. We aimed to characterize the effects of botulinum toxin on clinical, gait, and patient-reported outcomes in HSP patients and explore the potential of mobile digital gait analysis to monitor treatment effects and predict treatment response. METHODS: We conducted a prospective, observational, multicenter study involving ambulatory HSP patients treated with botulinum toxin tailored to individual goals. Comparing data at baseline, after 1 month, and after 3 months, treatment response was assessed using clinical parameters, goal attainment scaling, and mobile digital gait analysis. Machine learning algorithms were used for predicting individual goal attainment based on baseline parameters. RESULTS: A total of 56 patients were enrolled. Despite the heterogeneity of treatment goals and targeted muscles, botulinum toxin led to a significant improvement in specific clinical parameters and an improvement in specific gait characteristics, peaking at the 1-month and declining by the 3-month follow-up. Significant correlations were identified between gait parameters and clinical scores. With a mean balanced accuracy of 66%, machine learning algorithms identified important denominators to predict treatment response. CONCLUSIONS: Our study provides evidence supporting the beneficial effects of botulinum toxin in HSP when applied according to individual treatment goals. The use of mobile digital gait analysis and machine learning represents a novel approach for monitoring treatment effects and predicting treatment response.
Asunto(s)
Análisis de la Marcha , Paraplejía Espástica Hereditaria , Humanos , Masculino , Femenino , Paraplejía Espástica Hereditaria/tratamiento farmacológico , Adulto , Persona de Mediana Edad , Análisis de la Marcha/métodos , Estudios Prospectivos , Fármacos Neuromusculares/farmacología , Fármacos Neuromusculares/administración & dosificación , Fármacos Neuromusculares/uso terapéutico , Resultado del Tratamiento , Toxinas Botulínicas Tipo A/uso terapéutico , Toxinas Botulínicas Tipo A/farmacología , Adulto Joven , Anciano , Toxinas Botulínicas/uso terapéuticoRESUMEN
BACKGROUND: The Comprehensive Geriatric Assessment (CGA) records geriatric syndromes in a standardized manner, allowing individualized treatment tailored to the patient's needs and resources. Its use has shown a beneficial effect on the functional outcome and survival of geriatric patients. A recently published German S1 guideline for level 2 CGA provides recommendations for the use of a broad variety of different assessment instruments for each geriatric syndrome. However, the actual use of assessment instruments in routine geriatric clinical practice and its consistency with the guideline and the current state of literature has not been investigated to date. METHODS: An online survey was developed by an expert group of geriatricians and sent to all licenced geriatricians (n = 569) within Germany. The survey included the following geriatric syndromes: motor function and self-help capability, cognition, depression, pain, dysphagia and nutrition, social status and comorbidity, pressure ulcers, language and speech, delirium, and frailty. Respondents were asked to report which geriatric assessment instruments are used to assess the respective syndromes. RESULTS: A total of 122 clinicians participated in the survey (response rate: 21%); after data cleaning, 76 data sets remained for analysis. All participants regularly used assessment instruments in the following categories: motor function, self-help capability, cognition, depression, and pain. The most frequently used instruments in these categories were the Timed Up and Go (TUG), the Barthel Index (BI), the Mini Mental State Examination (MMSE), the Geriatric Depression Scale (GDS), and the Visual Analogue Scale (VAS). Limited or heterogenous assessments are used in the following categories: delirium, frailty and social status. CONCLUSIONS: Our results show that the assessment of motor function, self-help capability, cognition, depression, pain, and dysphagia and nutrition is consistent with the recommendations of the S1 guideline for level 2 CGA. Instruments recommended for more frequent use include the Short Physical Performance Battery (SPPB), the Montreal Cognitive Assessment (MoCA), and the WHO-5 (depression). There is a particular need for standardized assessment of delirium, frailty and social status. The harmonization of assessment instruments throughout geriatric departments shall enable more effective treatment and prevention of age-related diseases and syndromes.
Asunto(s)
Trastornos de Deglución , Delirio , Fragilidad , Humanos , Anciano , Fragilidad/diagnóstico , Fragilidad/epidemiología , Fragilidad/terapia , Evaluación Geriátrica/métodos , Dolor , Encuestas y CuestionariosRESUMEN
Breast cancer is affecting millions of people worldwide. If not appropriately handled, the side effects of different modalities of cancer treatment can negatively impact patients' quality of life and cause treatment interruptions. In recent years, mobile health (mHealth) interventions have shown promising opportunities to support breast cancer care. Numerous studies implemented mobile health interventions aiming to support patients with breast cancer, for example, through physical activity promotion or educational content. Nonetheless, current literature reveals that real-world evidence for the actual benefits remains unclear. In this systematic review, we focus on analyzing the methodology used in recent studies to determine the effects of mHealth applications and wearable devices on the outcome of patients with breast cancer. We followed the PRISMA guideline for the selection, analysis, and reporting of relevant studies found in the databases of Medline, Scopus, Web of Science, and Cochrane Library. A total of 276 unique records were identified, and 20 studies met the inclusion criteria. Study quality was assessed with the Effective Public Health Practice Project (EPHPP) Quality Assessment Tool for Quantitative Studies. While many of the studies used standardized questionnaires as patient-reported outcome measures, there was minimal use of objective measurements, such as activity sensors. Adoption, drop-out rates, and usage behavior of users of the mobile health intervention were often not reported. Future work should clearly define the focus and desired outcome of mHealth interventions and select outcome measures accordingly. Greater transparency facilitates the interpretation of results and conclusions about the real-world evidence of mobile health in breast cancer care.
Asunto(s)
Neoplasias de la Mama , Aplicaciones Móviles , Telemedicina , Humanos , Femenino , Neoplasias de la Mama/terapia , Calidad de Vida , Atención a la Salud , Telemedicina/métodosRESUMEN
Understanding of the human body's internal processes to maintain balance is fundamental to simulate postural control behaviour. The body uses multiple sensory systems' information to obtain a reliable estimate about the current body state. This information is used to control the reactive behaviour to maintain balance. To predict a certain motion behaviour with knowledge of the muscle forces, forward dynamic simulations of biomechanical human models can be utilized. We aim to use predictive postural control simulations to give therapy recommendations to patients suffering from postural disorders in the future. It is important to know which types of modelling approaches already exist to apply such predictive forward dynamic simulations. Current literature provides different models that aim to simulate human postural control. We conducted a systematic literature research to identify the different approaches of postural control models. The different approaches are discussed regarding their applied biomechanical models, sensory representation, sensory integration, and control methods in standing and gait simulations. We searched on Scopus, Web of Science and PubMed using a search string, scanned 1253 records, and found 102 studies to be eligible for inclusion. The included studies use different ways for sensory representation and integration, although underlying neural processes still remain unclear. We found that for postural control optimal control methods like linear quadratic regulators and model predictive control methods are used less, when models' level of details is increasing, and nonlinearities become more important. Considering musculoskeletal models, reflex-based and PD controllers are mainly applied and show promising results, as they aim to create human-like motion behaviour considering physiological processes.
Asunto(s)
Marcha , Equilibrio Postural , Humanos , Movimiento (Física) , Músculos , ReflejoRESUMEN
The advancement of embedded sensor systems allowed the monitoring of complex processes based on connected devices. As more and more data are produced by these sensor systems, and as the data are used in increasingly vital areas of applications, it is of growing importance to also track the data quality of these systems. We propose a framework to fuse sensor data streams and associated data quality attributes into a single meaningful and interpretable value that represents the current underlying data quality. Based on the definition of data quality attributes and metrics to determine real-valued figures representing the quality of the attributes, the fusion algorithms are engineered. Methods based on maximum likelihood estimation (MLE) and fuzzy logic are used to perform data quality fusion by utilizing domain knowledge and sensor measurements. Two data sets are used to verify the proposed fusion framework. First, the methods are applied to a proprietary data set targeting sample rate inaccuracies of a micro-electro-mechanical system (MEMS) accelerometer and second, to the publicly available Intel Lab Data set. The algorithms are verified against their expected behavior based on data exploration and correlation analysis. We prove that both fusion approaches are capable of detecting data quality issues and providing an interpretable data quality indicator.
RESUMEN
In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be applied to marginal sports, where available data are sparse and costly to acquire. Thus, we recorded and annotated inertial measurement unit (IMU) data containing different types of Ultimate Frisbee throws to investigate whether Convolutional Neural Networks (CNNs) and transfer learning can solve this. The relevant actions were automatically detected and were classified using a CNN. The proposed pipeline reaches an accuracy of 66.6%, distinguishing between nine different fine-grained classes. For the classification of the three basic throwing techniques, we achieve an accuracy of 89.9%. Furthermore, the results were compared to a transfer learning-based approach using a beach volleyball dataset as the source. Even if transfer learning could not improve the classification accuracy, the training time was significantly reduced. Finally, the effect of transfer learning on a reduced dataset, i.e., without data augmentations, is analyzed. While having the same number of training subjects, using the pre-trained weights improves the generalization capabilities of the network, i.e., increasing the accuracy and F1 score. This shows that transfer learning can be beneficial, especially when dealing with small datasets, as in marginal sports, and therefore, can improve the tracking of marginal sports.
Asunto(s)
Deportes , Dispositivos Electrónicos Vestibles , Actividades Humanas , Humanos , Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
With tracking systems becoming more widespread in sports research and regular training and competitions, more data are available for sports analytics and performance prediction. We analyzed 2523 ski jumps from 205 athletes on five venues. For every jump, the dataset includes the 3D trajectory, 3D velocity, skis' orientation, and metadata such as wind, starting gate, and ski jumping hill data. Using this dataset, we aimed to predict the expected jump length (xLength) inspired by the expected goals metric in soccer (xG). We evaluate the performance of a fully connected neural network, a convolutional neural network (CNN), a long short-term memory (LSTM), and a ResNet architecture to estimate the xLength. For the prediction of the jump length one second after take-off, we achieve a mean absolute error (MAE) of 5.3 m for the generalization to new athletes and an MAE of 5.9 m for the generalization to new ski jumping hills using ResNet architectures. Additionally, we investigated the influence of the input time after the take-off on the predictions' accuracy. As expected, the MAE becomes smaller with longer inputs. Due to the real-time transmission of the sensor's data, xLength can be updated during the flight phase and used in live TV broadcasting. xLength could also be used as an analysis tool for experts to quantify the quality of the take-off and flight phases.
Asunto(s)
Aprendizaje Profundo , Esquí , Fútbol , Humanos , Atletas , Viento , Fenómenos BiomecánicosRESUMEN
Indoor localization and human activity recognition are two important sources of information to provide context-based assistance. This information is relevant in ambient assisted living (AAL) scenarios, where older adults usually need supervision and assistance in their daily activities. However, indoor localization and human activity recognition have been mostly considered isolated problems. This work presents and evaluates a framework that takes advantage of the relationship between location and activity to simultaneously perform indoor localization, mapping, and human activity recognition. The proposed framework provides a non-intrusive configuration, which fuses data from an inertial measurement unit (IMU) placed in the person's shoe, with proximity and human activity-related data from Bluetooth low energy beacons (BLE) deployed in the indoor environment. A variant of the simultaneous location and mapping (SLAM) framework was used to fuse the location and human activity recognition (HAR) data. HAR was performed using data streaming algorithms. The framework was evaluated in a pilot study, using data from 22 people, 11 young people, and 11 older adults (people aged 65 years or older). As a result, seven activities of daily living were recognized with an F1 score of 88%, and the in-door location error was 0.98 ± 0.36 m for the young and 1.02 ± 0.24 m for the older adults. Furthermore, there were no significant differences between the groups, indicating that our proposed method works adequately in broad age ranges.
Asunto(s)
Inteligencia Ambiental , Actividades Cotidianas , Adolescente , Anciano , Algoritmos , Actividades Humanas , Humanos , Proyectos PilotoRESUMEN
Different control strategies are available for human machine interfaces based on electromyography (EMG) to map voluntary muscle signals to control signals of a remote controlled device. Complex systems such as robots or multi-fingered hands require a natural commanding, which can be realized with proportional and simultaneous control schemes. Machine learning approaches and methods based on regression are often used to realize the desired functionality. Training procedures often include the tracking of visual stimuli on a screen or additional sensors, such as cameras or force sensors, to create labels for decoder calibration. In certain scenarios, where ground truth, such as additional sensor data, can not be measured, e.g., with people suffering from physical disabilities, these methods come with the challenge of generating appropriate labels. We introduce a new approach that uses the EMG-feature stream recorded during a simple training procedure to generate continuous labels. The method avoids synchronization mismatches in the labels and has no need for additional sensor data. Furthermore, we investigated the influence of the transient phase of the muscle contraction when using the new labeling approach. For this purpose, we performed a user study involving 10 subjects performing online 2D goal-reaching and tracking tasks on a screen. In total, five different labeling methods were tested, including three variations of the new approach as well as methods based on binary labels, which served as a baseline. Results of the evaluation showed that the introduced labeling approach in combination with the transient phase leads to a proportional command that is more accurate than using only binary labels. In summary, this work presents a new labeling approach for proportional EMG control without the need of a complex training procedure or additional sensors.
Asunto(s)
Mano , Extremidad Superior , Electromiografía/métodos , Dedos/fisiología , Mano/fisiología , Humanos , Músculo Esquelético/fisiologíaRESUMEN
Efficient handwriting trajectory reconstruction (TR) requires specific writing surfaces for detecting movements of digital pens. Although several motion-based solutions have been developed to remove the necessity of writing surfaces, most of them are based on classical sensor fusion methods limited, by sensor error accumulation over time, to tracing only single strokes. In this work, we present an approach to map the movements of an IMU-enhanced digital pen to relative displacement data. Training data is collected by means of a tablet. We propose several pre-processing and data-preparation methods to synchronize data between the pen and the tablet, which are of different sampling rates, and train a convolutional neural network (CNN) to reconstruct multiple strokes without the need of writing segmentation or post-processing correction of the predicted trajectory. The proposed system learns the relative displacement of the pen tip over time from the recorded raw sensor data, achieving a normalized error rate of 0.176 relative to unit-scaled tablet ground truth (GT) trajectory. To test the effectiveness of the approach, we train a neural network for character recognition from the reconstructed trajectories, which achieved a character error rate of 19.51%. Finally, a joint model is implemented that makes use of both the IMU data and the generated trajectories, which outperforms the sensor-only-based recognition approach by 0.75%.
Asunto(s)
Escritura Manual , Accidente Cerebrovascular , Humanos , Movimiento , Redes Neurales de la Computación , ComprimidosRESUMEN
Driver monitoring systems play an important role in lower to mid-level autonomous vehicles. Our work focuses on the detection of cognitive load as a component of driver-state estimation to improve traffic safety. By inducing single and dual-task workloads of increasing intensity on 51 subjects, while continuously measuring signals from multiple modalities, based on physiological measurements such as ECG, EDA, EMG, PPG, respiration rate, skin temperature and eye tracker data, as well as behavioral measurements such as action units extracted from facial videos, performance metrics like reaction time and subjective feedback using questionnaires, we create ADABase (Autonomous Driving Cognitive Load Assessment Database) As a reference method to induce cognitive load onto subjects, we use the well-established n-back test, in addition to our novel simulator-based k-drive test, motivated by real-world semi-autonomously vehicles. We extract expert features of all measurements and find significant changes in multiple modalities. Ultimately we train and evaluate machine learning algorithms using single and multimodal inputs to distinguish cognitive load levels. We carefully evaluate model behavior and study feature importance. In summary, we introduce a novel cognitive load test, create a cognitive load database, validate changes using statistical tests, introduce novel classification and regression tasks for machine learning and train and evaluate machine learning models.
Asunto(s)
Conducción de Automóvil , Carga de Trabajo , Humanos , Conducción de Automóvil/psicología , Aprendizaje Automático , Tiempo de Reacción , CogniciónRESUMEN
Developing machine learning algorithms for time-series data often requires manual annotation of the data. To do so, graphical user interfaces (GUIs) are an important component. Existing Python packages for annotation and analysis of time-series data have been developed without addressing adaptability, usability, and user experience. Therefore, we developed a generic open-source Python package focusing on adaptability, usability, and user experience. The developed package, Machine Learning and Data Analytics (MaD) GUI, enables developers to rapidly create a GUI for their specific use case. Furthermore, MaD GUI enables domain experts without programming knowledge to annotate time-series data and apply algorithms to it. We conducted a small-scale study with participants from three international universities to test the adaptability of MaD GUI by developers and to test the user interface by clinicians as representatives of domain experts. MaD GUI saves up to 75% of time in contrast to using a state-of-the-art package. In line with this, subjective ratings regarding usability and user experience show that MaD GUI is preferred over a state-of-the-art package by developers and clinicians. MaD GUI reduces the effort of developers in creating GUIs for time-series analysis and offers similar usability and user experience for clinicians as a state-of-the-art package.
Asunto(s)
Programas Informáticos , Interfaz Usuario-Computador , Algoritmos , Humanos , Aprendizaje AutomáticoRESUMEN
BACKGROUND: To objectively assess a patient's gait, a robust identification of stride borders is one of the first steps in inertial sensor-based mobile gait analysis pipelines. While many different methods for stride segmentation have been presented in the literature, an out-of-lab evaluation of respective algorithms on free-living gait is still missing. METHOD: To address this issue, we present a comprehensive free-living evaluation dataset, including 146.574 semi-automatic labeled strides of 28 Parkinson's Disease patients. This dataset was used to evaluate the segmentation performance of a new Hidden Markov Model (HMM) based stride segmentation approach compared to an available dynamic time warping (DTW) based method. RESULTS: The proposed HMM achieved a mean F1-score of 92.1% and outperformed the DTW approach significantly. Further analysis revealed a dependency of segmentation performance to the number of strides within respective walking bouts. Shorter bouts ([Formula: see text] strides) resulted in worse performance, which could be related to more heterogeneous gait and an increased diversity of different stride types in short free-living walking bouts. In contrast, the HMM reached F1-scores of more than 96.2% for longer bouts ([Formula: see text] strides). Furthermore, we showed that an HMM, which was trained on at-lab data only, could be transferred to a free-living context with a negligible decrease in performance. CONCLUSION: The generalizability of the proposed HMM is a promising feature, as fully labeled free-living training data might not be available for many applications. To the best of our knowledge, this is the first evaluation of stride segmentation performance on a large scale free-living dataset. Our proposed HMM-based approach was able to address the increased complexity of free-living gait data, and thus will help to enable a robust assessment of stride parameters in future free-living gait analysis applications.
Asunto(s)
Enfermedad de Parkinson , Algoritmos , Marcha , Análisis de la Marcha , Humanos , CaminataRESUMEN
For sports scientists and coaches, its crucial to have reliable tracking systems to improve athletes. Therefore, this study aimed to examine the validity of a wearable real-time tracking system (WRRTS) for the quantification of ski jumping. The tracking system consists of wearable trackers attached to the ski bindings of the athletes and fixed antennas next to the jumping hill. To determine the accuracy and precision of the WRRTS, four athletes of the German A or B National Team performed 35 measured ski jumps. The WRRTS was used to measure the 3D positions and ski angles during the jump. The measurements are compared with camera measurements for the in-flight parameters and the official video distance for the jumping distance to assess their accuracy. We statistically evaluated the different methods using Bland-Altman plots. We thereby find a mean absolute error of 0.46 m for the jumping distance, 0.12 m for the in-flight positions, and 0.8°, and 3.4° for the camera projected pitch and V-style opening angle, respectively. We show the validity of the presented WRRTS to measure the investigated parameters. Thus, the system can be used as a tracking system during training and competitions for coaches and sports scientists. The real-time feature of the tracking system enables usage during live TV broadcasting.
Asunto(s)
Esquí , Dispositivos Electrónicos Vestibles , Atletas , Fenómenos Biomecánicos , HumanosRESUMEN
The applicability of sensor-based human activity recognition in sports has been repeatedly shown for laboratory settings. However, the transferability to real-world scenarios cannot be granted due to limitations on data and evaluation methods. On the example of football shot and pass detection against a null class we explore the influence of those factors for real-world event classification in field sports. For this purpose we compare the performance of an established Support Vector Machine (SVM) for laboratory settings from literature to the performance in three evaluation scenarios gradually evolving from laboratory settings to real-world scenarios. In addition, three different types of neural networks, namely a convolutional neural net (CNN), a long short term memory net (LSTM) and a convolutional LSTM (convLSTM) are compared. Results indicate that the SVM is not able to reliably solve the investigated three-class problem. In contrast, all deep learning models reach high classification scores showing the general feasibility of event detection in real-world sports scenarios using deep learning. The maximum performance with a weighted f1-score of 0.93 was reported by the CNN. The study provides valuable insights for sports assessment under practically relevant conditions. In particular, it shows that (1) the discriminative power of established features needs to be reevaluated when real-world conditions are assessed, (2) the selection of an appropriate dataset and evaluation method are both required to evaluate real-world applicability and (3) deep learning-based methods yield promising results for real-world HAR in sports despite high variations in the execution of activities.
Asunto(s)
Aprendizaje Profundo , Fútbol Americano , Humanos , Laboratorios , Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
Smart sensors are an integral part of the Fourth Industrial Revolution and are widely used to add safety measures to human-robot interaction applications. With the advancement of machine learning methods in resource-constrained environments, smart sensor systems have become increasingly powerful. As more data-driven approaches are deployed on the sensors, it is of growing importance to monitor data quality at all times of system operation. We introduce a smart capacitive sensor system with an embedded data quality monitoring algorithm to enhance the safety of human-robot interaction scenarios. The smart capacitive skin sensor is capable of detecting the distance and angle of objects nearby by utilizing consumer-grade sensor electronics. To further acknowledge the safety aspect of the sensor, a dedicated layer to monitor data quality in real-time is added to the embedded software of the sensor. Two learning algorithms are used to implement the sensor functionality: (1) a fully connected neural network to infer the position and angle of objects nearby and (2) a one-class SVM to account for the data quality assessment based on out-of-distribution detection. We show that the sensor performs well under normal operating conditions within a range of 200 mm and also detects abnormal operating conditions in terms of poor data quality successfully. A mean absolute distance error of 11.6mm was achieved without data quality indication. The overall performance of the sensor system could be further improved to 7.5mm by monitoring the data quality, adding an additional layer of safety for human-robot interaction.
Asunto(s)
Robótica , Algoritmos , Exactitud de los Datos , Electrónica , Humanos , Monitoreo FisiológicoRESUMEN
Maximizing performance success in sports is about continuous learning and adaptation processes. Aside from physiological, technical and emotional performance factors, previous research focused on perceptual skills, revealing their importance for decision-making. This includes deriving relevant environmental information as a result of eye, head and body movement interaction. However, to evaluate visual exploratory activity (VEA), generally utilized laboratory settings have restrictions that disregard the representativeness of assessment environments and/or decouple coherent cognitive and motor tasks. In vivo studies, however, are costly and hard to reproduce. Furthermore, the application of elaborate methods like eye tracking are cumbersome to implement and necessitate expert knowledge to interpret results correctly. In this paper, we introduce a virtual reality-based reproducible assessment method allowing the evaluation of VEA. To give insights into perceptual-cognitive processes, an easily interpretable head movement-based metric, quantifying VEA of athletes, is investigated. Our results align with comparable in vivo experiments and consequently extend them by showing the validity of the implemented approach as well as the use of virtual reality to determine characteristics among different skill levels. The findings imply that the developed method could provide accurate assessments while improving the control, validity and interpretability, which in turn informs future research and developments.
Asunto(s)
Deportes , Realidad Virtual , Atletas , Humanos , Aprendizaje , MovimientoRESUMEN
Climbing stairs is a fundamental part of daily life, adding additional demands on the postural control system compared to level walking. Although real-world gait analysis studies likely contain stair ambulation sequences, algorithms dedicated to the analysis of such activities are still missing. Therefore, we propose a new gait analysis pipeline for foot-worn inertial sensors, which can segment, parametrize, and classify strides from continuous gait sequences that include level walking, stair ascending, and stair descending. For segmentation, an existing approach based on the hidden Markov model and a feature-based gait event detection were extended, reaching an average segmentation F1 score of 98.5% and gait event timing errors below ±10ms for all conditions. Stride types were classified with an accuracy of 98.2% using spatial features derived from a Kalman filter-based trajectory reconstruction. The evaluation was performed on a dataset of 20 healthy participants walking on three different staircases at different speeds. The entire pipeline was additionally validated end-to-end on an independent dataset of 13 Parkinson's disease patients. The presented work aims to extend real-world gait analysis by including stair ambulation parameters in order to gain new insights into mobility impairments that can be linked to clinically relevant conditions such as a patient's fall risk and disease state or progression.
Asunto(s)
Análisis de la Marcha , Caminata , Algoritmos , Pie , Marcha , HumanosRESUMEN
Digital technologies provide the opportunity to analyze gait patterns in patients with Parkinson's Disease using wearable sensors in clinical settings and a home environment. Confirming the technical validity of inertial sensors with a 3D motion capture system is a necessary step for the clinical application of sensor-based gait analysis. Therefore, the objective of this study was to compare gait parameters measured by a mobile sensor-based gait analysis system and a motion capture system as the gold standard. Gait parameters of 37 patients were compared between both systems after performing a standardized 5 × 10 m walking test by reliability analysis using intra-class correlation and Bland-Altman plots. Additionally, gait parameters of an age-matched healthy control group (n = 14) were compared to the Parkinson cohort. Gait parameters representing bradykinesia and short steps showed excellent reliability (ICC > 0.96). Shuffling gait parameters reached ICC > 0.82. In a stridewise synchronization, no differences were observed for gait speed, stride length, stride time, relative stance and swing time (p > 0.05). In contrast, heel strike, toe off and toe clearance significantly differed between both systems (p < 0.01). Both gait analysis systems distinguish Parkinson patients from controls. Our results indicate that wearable sensors generate valid gait parameters compared to the motion capture system and can consequently be used for clinically relevant gait recordings in flexible environments.