Abstract:Inertial sensors are commonly embedded in several devices, including smartphones, and other specific devices. This type of sensors may be used for different purposes, including the recognition of different diseases. Several studies are focused on the use of accelerometer signals for the automatic recognition of different diseases, and it may empower the different treatments with the use of less invasive and painful techniques for patients. This paper aims to provide a systematic review of the studies available… Show more
“…Hence, they can be implemented as wearable devices (e.g., smartwatches, fitness bands, and smart clothing [9,10]). Because human health problems are most often expressed as measurable behaviors [11], IMUs are more suitable for daily activity data collection than other sensors. Hence, many IMUbased HAR studies have been accomplished [3][4][5]9].…”
In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.
“…Hence, they can be implemented as wearable devices (e.g., smartwatches, fitness bands, and smart clothing [9,10]). Because human health problems are most often expressed as measurable behaviors [11], IMUs are more suitable for daily activity data collection than other sensors. Hence, many IMUbased HAR studies have been accomplished [3][4][5]9].…”
In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.
“…Entropy and statistical parameters such as mean value, standard deviation and variance are other sensible metrics [ 28 , 31 ]. Several features, extracted from both the time and frequency domain and different machine learning (ML) algorithms have been employed to classify FOG and pre-FOG events [ 36 ].…”
Background: Freezing of Gait (FOG) is one of the most disabling motor complications of Parkinson’s disease, and consists of an episodic inability to move forward, despite the intention to walk. FOG increases the risk of falls and reduces the quality of life of patients and their caregivers. The phenomenon is difficult to appreciate during outpatients visits; hence, its automatic recognition is of great clinical importance. Many types of sensors and different locations on the body have been proposed. However, the advantages of a multi-sensor configuration with respect to a single-sensor one are not clear, whereas this latter would be advisable for use in a non-supervised environment. Methods: In this study, we used a multi-modal dataset and machine learning algorithms to perform different classifications between FOG and non-FOG periods. Moreover, we explored the relevance of features in the time and frequency domains extracted from inertial sensors, electroencephalogram and skin conductance. We developed both a subject-independent and a subject-dependent algorithm, considering different sensor subsets. Results: The subject-independent and subject-dependent algorithms yielded accuracies of 85% and 88% in the leave-one-subject-out and leave-one-task-out test, respectively. Results suggest that the inertial sensors positioned on the lower limb are generally the most significant in recognizing FOG. Moreover, the performance impairment experienced when using a single tibial accelerometer instead of the optimal multi-modal configuration is limited to 2–3%. Conclusions: The achieved results disclose the possibility of getting a good FOG recognition using a minimally invasive set-up made of a single inertial sensor. This is very significant in the perspective of implementing a long-term monitoring of patients in their homes, during activities of daily living.
“…However, it has been demonstrated that remote mobility measurement systems requiring the usage of a wearable sensor can have dropout rates of up to 32% after 6 months and 50% after a year [ 10 ]. Smartphones, ubiquitous, portable, user-friendly and affordable devices with one or several embedded inertial sensors, offer a promising new avenue for the analysis of the mobility performance of PD patients outside clinical environments, complementing the capacity measures obtained in-consultation and yielding rater-independent, quantitative outcomes with higher ecological validity [ 11 , 12 ]. The validity of smartphone applications for this purpose has been shown in healthy subjects and in PD patients, albeit mostly in supervised environments, requiring the device to be worn in a predetermined location and orientation, and not accounting for the heterogeneity of smartphone usage among the population [ 13 , 14 , 15 ].…”
Ecological evaluation of gait using mobile technologies provides crucial information regarding the evolution of symptoms in Parkinson’s disease (PD). However, the reliability and validity of such information may be influenced by the smartphone’s location on the body. This study analyzed how the smartphone location affects the assessment of PD patients’ gait in a free-living environment. Twenty PD patients (mean ± SD age, 64.3 ± 10.6 years; 9 women (45%) performed 3 trials of a 250 m outdoor walk using smartphones in 5 different body locations (pants pocket, belt, hand, shirt pocket, and a shoulder bag). A method to derive gait-related metrics from smartphone sensors is presented, and its reliability is evaluated between different trials as well as its concurrent validity against optoelectronic and smartphone criteria. Excellent relative reliability was found with all intraclass correlation coefficient values above or equal to 0.85. High absolute reliability was observed in 21 out of 30 comparisons. Bland-Altman analysis revealed a high level of agreement (LoA between 4.4 and 17.5%), supporting the use of the presented method. This study advances the use of mobile technology to accurately and reliably quantify gait-related metrics from PD patients in free-living walking regardless of the smartphone’s location on the body.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.