Fall risk prediction using temporal gait features and machine learning approaches.

Introduction: Falls have been acknowledged as a major public health issue around the world. Early detection of fall risk is pivotal for preventive measures. Traditional clinical assessments, although reliable, are resource-intensive and may not always be feasible. Methods: This study explores the efficacy of artificial intelligence (AI) in predicting fall risk, leveraging gait analysis through computer vision and machine learning techniques. Data was collected using the Timed Up and Go (TUG) test and JHFRAT assessment from MMU collaborators and augmented with a public dataset from Mendeley involving older adults. The study introduces a robust approach for extracting and analyzing gait features, such as stride time, step time, cadence, and stance time, to distinguish between fallers and non-fallers. Results: Two experimental setups were investigated: one considering separate gait features for each foot and another analyzing averaged features for both feet. Ultimately, the proposed solutions produce promising outcomes, greatly enhancing the model's ability to achieve high levels of accuracy. In particular, the LightGBM demonstrates a superior accuracy of 96% in the prediction task. Discussion: The findings demonstrate that simple machine learning models can successfully identify individuals at higher fall risk based on gait characteristics, with promising results that could potentially streamline fall risk assessment processes. However, several limitations were discovered throughout the experiment, including an insufficient dataset and data variation, limiting the model's generalizability. These issues are raised for future work consideration. Overall, this research contributes to the growing body of knowledge on fall risk prediction and underscores the potential of AI in enhancing public health strategies through the early identification of at-risk individuals.

Temporal and spatial characteristics of plantar pressure center trajectory for identifying early Parkinson's disease gait.

Gait analysis can be utilized as an effective method for identifying Parkinson's disease (PD) [1]. However, research methods based on the time-domain gait feature analysis are influenced by population characteristics such as individual height, age, and weight, which unfavorably affect PD diagnostic decision-making.

[A two-dimensional video based quantification method and clinical application research of motion disorders].

The increasing prevalence of the aging population, and inadequate and uneven distribution of medical resources, have led to a growing demand for telemedicine services. Gait disturbance is a primary symptom of neurological disorders such as Parkinson's disease (PD). This study proposed a novel approach for the quantitative assessment and analysis of gait disturbance from two-dimensional (2D) videos captured using smartphones. The approach used a convolutional pose machine to extract human body joints and a gait phase segmentation algorithm based on node motion characteristics to identify the gait phase. Moreover, it extracted features of the upper and lower limbs. A height ratio-based spatial feature extraction method was proposed that effectively captures spatial information. The proposed method underwent validation via error analysis, correction compensation, and accuracy verification using the motion capture system. Specifically, the proposed method achieved an extracted step length error of less than 3 cm. The proposed method underwent clinical validation, recruiting 64 patients with Parkinson's disease and 46 healthy controls of the same age group. Various gait indicators were statistically analyzed using three classic classification methods, with the random forest method achieving a classification accuracy of 91%. This method provides an objective, convenient, and intelligent solution for telemedicine focused on movement disorders in neurological diseases.

A two-dimensional video based quantification method and clinical application research of motion disorders / 生物医学工程学杂志

The increasing prevalence of the aging population, and inadequate and uneven distribution of medical resources, have led to a growing demand for telemedicine services. Gait disturbance is a primary symptom of neurological disorders such as Parkinson's disease (PD). This study proposed a novel approach for the quantitative assessment and analysis of gait disturbance from two-dimensional (2D) videos captured using smartphones. The approach used a convolutional pose machine to extract human body joints and a gait phase segmentation algorithm based on node motion characteristics to identify the gait phase. Moreover, it extracted features of the upper and lower limbs. A height ratio-based spatial feature extraction method was proposed that effectively captures spatial information. The proposed method underwent validation via error analysis, correction compensation, and accuracy verification using the motion capture system. Specifically, the proposed method achieved an extracted step length error of less than 3 cm. The proposed method underwent clinical validation, recruiting 64 patients with Parkinson's disease and 46 healthy controls of the same age group. Various gait indicators were statistically analyzed using three classic classification methods, with the random forest method achieving a classification accuracy of 91%. This method provides an objective, convenient, and intelligent solution for telemedicine focused on movement disorders in neurological diseases.

Spatiotemporal and kinematic characteristics augmentation using Dual-GAN for ankle instability detection.

Obtaining massive amounts of training data is often crucial for computer-assisted diagnosis using deep learning. Unfortunately, patient data is often small due to varied constraints. We develop a new approach to extract significant features from a small clinical gait analysis dataset to improve computer-assisted diagnosis of Chronic Ankle Instability (CAI) patients. In this paper, we present an approach for augmenting spatiotemporal and kinematic characteristics using the Dual Generative Adversarial Networks (Dual-GAN) to train a series of modified Long Short-Term Memory (LSTM) detection models making the training process more data-efficient. Namely, we use LSTM-, LSTM-Fully Convolutional Networks (FCN)-, and Convolutional LSTM-based detection models to identify the patients with CAI. The Dual-GAN enables the synthesized data to approximate the real data distribution visualized by the t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm. Then we trained the proposed detection models using real data collected from a controlled laboratory study and mixed data from real and synthesized gait features. The detection models were tested in real data to validate the positive role in data augmentation as well as to demonstrate the capability and effectiveness of the modified LSTM algorithm for CAI detection using spatiotemporal and kinematic characteristics in walking. Dual-GAN generated efficient spatiotemporal and kinematic characteristics to augment the training set promoting the performance of CAI detection and the modified LSTM algorithm yielded an enhanced classification outcome to identify those CAI patients from a group of control subjects based on gait analysis data than any previous reports.

Association between gait features assessed by artificial intelligent system and cognitive function decline in patients with silent cerebrovascular disease: study protocol of a multicenter prospective cohort study (ACCURATE-2).

BACKGROUND: Gait disturbances may appear prior to cognitive dysfunction in the early stage of silent cerebrovascular disease (SCD). Subtle changes in gait characteristics may provide an early warning of later cognitive decline. Our team has proposed a vision-based artificial intelligent gait analyzer for the rapid detection of spatiotemporal parameters and walking pattern based on videos of the Timed Up and Go (TUG) test. The primary objective of this study is to investigate the relationship between gait features assessed by our artificial intelligent gait analyzer and cognitive function changes in patients with SCD. METHODS: This will be a multicenter prospective cohort study involving a total of 14 hospitals from Shanghai and Guizhou. One thousand and six hundred patients with SCD aged 60-85 years will be consecutively recruited. Eligible patients will undergo the intelligent gait assessment and neuropsychological evaluation at baseline and at 1-year follow-up. The intelligent gait analyzer will divide participant into normal gait group and abnormal gait group according to their walking performance in the TUG videos at baseline. All participants will be naturally observed during 1-year follow-up period. Primary outcome are the changes in Mini-Mental State Examination (MMSE) score. Secondary outcomes include the changes in intelligent gait spatiotemporal parameters (step length, gait speed, step frequency, step width, standing up time, and turning back time), the changes in scores on other neuropsychological tests (Montreal Cognitive Assessment, the Stroop Color Word Test, and Digit Span Test), falls events, and cerebrovascular events. We hypothesize that both groups will show a decline in MMSE score, but the decrease of MMSE score in the abnormal gait group will be more significant. CONCLUSION: This study will be the first to explore the relationship between gait features assessed by an artificial intelligent gait analyzer and cognitive decline in patients with SCD. It will demonstrate whether subtle gait abnormalities detected by the artificial intelligent gait analyzer can act as a cognitive-related marker for patients with SCD. TRIAL REGISTRATION: This trial was registered at ClinicalTrials.gov ( NCT04456348 ; 2 July 2020).

Evaluating the Accuracy of Virtual Reality Trackers for Computing Spatiotemporal Gait Parameters.

Ageing, disease, and injuries result in movement defects that affect daily life. Gait analysis is a vital tool for understanding and evaluating these movement dysfunctions. In recent years, the use of virtual reality (VR) to observe motion and offer augmented clinical care has increased. Although VR-based methodologies have shown benefits in improving gait functions, their validity against more traditional methods (e.g., cameras or instrumented walkways) is yet to be established. In this work, we propose a procedure aimed at testing the accuracy and viability of a VIVE Virtual Reality system for gait analysis. Seven young healthy subjects were asked to walk along an instrumented walkway while wearing VR trackers. Heel strike (HS) and toe off (TO) events were assessed using the VIVE system and the instrumented walkway, along with stride length (SL), stride time (ST), stride width (SW), stride velocity (SV), and stance/swing percentage (STC, SWC%). Results from the VR were compared with the instrumented walkway in terms of detection offset for time events and root mean square error (RMSE) for gait features. An absolute offset between VR- and walkway-based data of (15.3 ± 12.8) ms for HS, (17.6 ± 14.8) ms for TOs and an RMSE of 2.6 cm for SW, 2.0 cm for SL, 17.4 ms for ST, 2.2 m/s for SV, and 2.1% for stance and swing percentage were obtained. Our findings show VR-based systems can accurately monitor gait while also offering new perspectives for VR augmented analysis.

Estimation and validation of temporal gait features using a markerless 2D video system.

BACKGROUND AND OBJECTIVE: Estimation of temporal gait features, such as stance time, swing time and gait cycle time, can be used for clinical evaluations of various patient groups having gait pathologies, such as Parkinson's diseases, neuropathy, hemiplegia and diplegia. Most clinical laboratories employ an optoelectronic motion capture system to acquire such features. However, the operation of these systems requires specially trained operators, a controlled environment and attaching reflective markers to the patient's body. To allow the estimation of the same features in a daily life setting, this paper presents a novel vision based system whose operation does not require the presence of skilled technicians or markers and uses a single 2D camera. METHOD: The proposed system takes as input a 2D video, computes the silhouettes of the walking person, and then estimates key biomedical gait indicators, such as the initial foot contact with the ground and the toe off instants, from which several other temporal gait features can be derived. RESULTS: The proposed system is tested on two datasets: (i) a public gait dataset made available by CASIA, which contains 20 users, with 4 sequences per user; and (ii) a dataset acquired simultaneously by a marker-based optoelectronic motion capture system and a simple 2D video camera, containing 10 users, with 5 sequences per user. For the CASIA gait dataset A the relevant temporal biomedical gait indicators were manually annotated, and the proposed automated video analysis system achieved an accuracy of 99% on their identification. It was able to obtain accurate estimations even on segmented silhouettes where, the state-of-the-art markerless 2D video based systems fail. For the second database, the temporal features obtained by the proposed system achieved an average intra-class correlation coefficient of 0.86, when compared to the ``gold standard" optoelectronic motion capture system. CONCLUSIONS: The proposed markerless 2D video based system can be used to evaluate patients' gait without requiring the usage of complex laboratory settings and without the need for physical attachment of sensors/markers to the patients. The good accuracy of the results obtained suggests that the proposed system can be used as an alternative to the optoelectronic motion capture system in non-laboratory environments, which can be enable more regular clinical evaluations.

Automatic Classification of Gait Impairments Using a Markerless 2D Video-Based System.

Systemic disorders affecting an individual can cause gait impairments. Successful acquisition and evaluation of features representing such impairments make it possible to estimate the severity of those disorders, which is important information for monitoring patients' health evolution. However, current state-of-the-art systems perform the acquisition and evaluation of these features in specially equipped laboratories, typically limiting the periodicity of evaluations. With the objective of making health monitoring easier and more accessible, this paper presents a system that performs automatic detection and classification of gait impairments, based on the acquisition and evaluation of biomechanical gait features using a single 2D video camera. The system relies on two different types of features to perform classification: (i) feet-related features, such as step length, step length symmetry, fraction of foot flat during stance phase, normalized step count, speed; and (ii) body-related features, such as the amount of movement while walking, center of gravity shifts and torso orientation. The proposed system uses a support vector machine to decide whether the observed gait is normal or if it belongs to one of three different impaired gait groups. Results show that the proposed system outperforms existing markerless 2D video-based systems, with a classification accuracy of 98.8%.

Effects of balance ability and handgrip height on kinematics of the gait, torso, and pelvis in elderly women using a four-wheeled walker.

AIM: Numerous elderly individuals use the four-wheeled walker (FWW) as a gait-assistive device. The walker's handgrip height is important for correct use. However, few clinical studies have investigated the biomechanical effects of the FWW's handgrip height on balance. Therefore, the present study assessed kinematic features of the gait, torso and pelvis during use of the FWW at two levels of handgrip height (48% vs 55% of the subject's height) while assessing balance in older adults. METHODS: A total of 20 older adults were allocated into two groups according to the Berg Balance Scale (BBS): good balance (GB; BBS≥46) versus poor balance (PB; BBS<45). Participants walked with the FWW at 48% or 55% handgrip height for 10 m. RESULTS: Our study showed that the double-support period and stance phase significantly increased at 55% handgrip height, but the swing phase significantly decreased in the GB group. In the PB group, velocity and stride length significantly increased at 55% handgrip height. Tilt angle of the torso in the GB group was significantly lower at 55% than at 48% handgrip height, but no differences were observed in the PB group. In the pelvis, initial contact and toe-off angles of tilt were lower in the GB group at 55% handgrip height, but no differences were observed in the PB group. CONCLUSIONS: These results showed that kinematic features of the gait, torso, and pelvis in older adults using the FWW might be dependent on the handgrip height of the FWW and the patient's balance. Additionally, greater than 48% of the body height might be appropriate for older adults with poor balance.