Here an inertial sensor-based monitoring system for measuring and analyzing upper limb movements is presented. The final goal is the integration of this motion-tracking device within a portable rehabilitation system for brain injury patients. A set of four inertial sensors mounted on a special garment worn by the patient provides the quaternions representing the patient upper limb’s orientation in space. A kinematic model is built to estimate 3D upper limb motion for accurate therapeutic evaluation. The human upper limb is represented as a kinematic chain of rigid bodies with three joints and six degrees of freedom. Validation of the system has been performed by co-registration of movements with a commercial optoelectronic tracking system. Successful results are shown that exhibit a high correlation among signals provided by both devices and obtained at the Institut Guttmann Neurorehabilitation Hospital.

In recent years, human activity recognition (HAR) has gained importance in several domains such as surveillance, recognizing indoor and outdoor activities, and providing active and assisted living environments in smart homes and healthcare services. In all these scenarios, audio-, video- and image-based processing algorithms have been applied as well as systems using wearable sensors. This scoping review focuses on audio- and video-based activity recognition systems for healthcare applications. We provide a comprehensive overview of these systems and technologies and discuss their complexity, performance, robustness, stage of development, scalability as well as achievable privacy and security levels. Additionally, we present and discuss datasets that are designed for the evaluation of these activity recognition systems. Although a number of robust approaches have already been proposed, they still pose challenges when it comes to integrating them in larger systems or into clinical practice. We identify challenges for application of audio- and video-based HAR systems in real-word healthcare scenarios, draw recommendations and conclusions based on comparisons of existing approaches, and analyze future trends.

Falls are a leading cause of unintentional trauma-related deaths worldwide, and a significant contributor to elderly dependence. To address this, the goal of this project was to predict recurrent falls in the older population using machine learning techniques, with the aim of reducing the number of falls and their consequences.To achieve this, a dataset obtained from Getafe University Hospital’s Geriatric Falls Unit was used (obtained from the Hospital’s Electronic Health Records). This extensive dataset was one the key strengths of our work. Feature extraction was performed through natural language processing, which recognized pre-defined patterns and helped build the profiles of the 304 older adults who composed the dataset. The proposed data system was comprised of four main blocks: the senior’s profile and environment, clinical information and tests carried out in the hospital, medications, and different diseases they presented. Using the extracted attributes and data from those 304 older adults, this project compared the performance of various machine learning techniques in their ability to classify older adults between future fallers and non fallers. Training different models and ensembles and comparing the results, we obtained that Bagging with Random Forest as base model is the best classifier, predicting accurately 75.8% of the data with 70.0% sensitivity and 80.5% specificity. Ultimately, this research project aimed at setting the first stone to a larger study that could help monitoring older adults and obtaining dynamic and automatic predictions of falls.

The present paper describes a system for older people to self-administer the 30-s chair stand test (CST) at home without supervision. The system comprises a low-cost sensor to count sit-to-stand (SiSt) transitions, and an Android application to guide older people through the procedure. Two observational studies were conducted to test (i) the sensor in a supervised environment (n = 7; m = 83.29 years old, sd = 4.19; 5 female), and (ii) the complete system in an unsupervised one (n = 7; age 64–74 years old; 3 female). The participants in the supervised test were asked to perform a 30-s CST with the sensor, while a member of the research team manually counted valid transitions. Automatic and manual counts were perfectly correlated (Pearson’s r = 1, p = 0.00). Even though the sample was small, none of the signals around the critical score were affected by harmful noise; p (harmless noise) = 1, 95% CI = (0.98, 1). The participants in the unsupervised test used the system in their homes for a month. None of them dropped out, and they reported it to be easy to use, comfortable, and easy to understand. Thus, the system is suitable to be used by older adults in their homes without professional supervision.