A Machine Learning Approach for Walking Classification in Elderly People with Gait Disorders

Abstract

Walking ability of elderly individuals, who suffer from walking difficulties, is limited, which restricts their mobility independence. The physical health and well-being of the elderly population are affected by their level of physical activity. Therefore, monitoring daily activities can help improve the quality of life. This becomes especially a huge challenge for those, who suffer from dementia and Alzheimer’s disease. Thus, it is of great importance for personnel in care homes/rehabilitation centers to monitor their daily activities and progress. Unlike normal subjects, it is required to place the sensor on the back of this group of patients, which makes it even more challenging to detect walking from other activities. With the latest advancements in the field of health sensing and sensor technology, a huge amount of accelerometer data can be easily collected. In this study, a Machine Learning (ML) based algorithm was developed to analyze the accelerometer data collected from patients with walking difficulties, who live in one of the municipalities in Denmark. The ML algorithm is capable of accurately classifying the walking activity of these individuals with different walking abnormalities. Various statistical, temporal, and spectral features were extracted from the time series data collected using an accelerometer sensor placed on the back of the participants. The back sensor placement is desirable in patients with dementia and Alzheimer’s disease since they may remove visible sensors to them due to the nature of their diseases. Then, an evolutionary optimization algorithm called Particle Swarm Optimization (PSO) was used to select a subset of features to be used in the classification step. Four different ML classifiers such as k-Nearest Neighbors (kNN), Random Forest (RF), Stacking Classifier (Stack), and Extreme Gradient Boosting (XGB) were trained and compared on an accelerometry dataset consisting of 20 participants. These models were evaluated using the leave-one-group-out cross-validation (LOGO-CV) technique. The Stack model achieved the best performance with average sensitivity, positive predictive values (precision), F1-score, and accuracy of 86.85%, 93.25%, 88.81%, and 93.32%, respectively, to classify walking episodes. In general, the empirical results confirmed that the proposed models are capable of classifying the walking episodes despite the challenging sensor placement on the back of the patients, who suffer from walking disabilities.

Daily Activities of Elder Adults Using Optimized Deep Learning Model in China

“…Patients in one Danish municipality who have trouble walking were monitored with accelerometers, and an (ML) based system was developed by Peimankar et al [23]. The ML algorithm can reliably categorise the walking behaviour of people with a variety of walking disorders.…”

Automatic Gait Classification Model Empowered by Machine Learning for People with and without Osteoporosis Using Smart Walker

“…Utilizing assistive devices such as crutches, canes, and walkers provides a practical approach to acquiring training datasets for machine learning algorithms in osteoporosis management [28]. These devices, designed to support and restore normal locomotion in individuals affected by injuries or pathologies, are easily equipped with sensors to capture gait and posture data [29,30]. A smart walker, for instance, functions as a minimalist tool in gait classification system development, simultaneously supporting users while acquiring kinetic data [30].…”

“…These devices, designed to support and restore normal locomotion in individuals affected by injuries or pathologies, are easily equipped with sensors to capture gait and posture data [29,30]. A smart walker, for instance, functions as a minimalist tool in gait classification system development, simultaneously supporting users while acquiring kinetic data [30]. Moreover, while video-based gait analysis raises privacy issues, smart walkers collect data solely from the user's interaction with the device, thus alleviating privacy concerns.…”

“…Smart walkers present numerous advantages, including ease of use, a controlled environment for data collection, and standardized data output. A smart walker functions as a minimalist tool in gait classification system development, simultaneously supporting users while acquiring kinetic data [30]. This technology not only monitors osteoporosis progression and evaluates treatment effectiveness but also reduces fall risks and enhances overall mobility in individuals with osteoporosis [28].…”

AUD-DSS: a decision support system for early detection of patients with alcohol use disorder

“…ML has emerged as a promising approach for clinical decision support tools across various health care domains. ML techniques have been successfully employed in diverse areas, including the detection of dementia and Alzheimer’s disease [ 20 , 21 ], early detection of diabetes [ 22 ], detection of atrial fibrillation [ 23 ], as well as the early detection of AUD, among others.…”