The digitalisation of geriatric care refers to the use of emerging technologies to manage and provide person-centered care to the elderly by collecting patients’ data electronically and using them to streamline the care process, which improves the overall quality, accuracy, and efficiency of healthcare. In many countries, healthcare providers still rely on the manual measurement of bioparameters, inconsistent monitoring, and paper-based care plans to manage and deliver care to elderly patients. This can lead to a number of problems, including incomplete and inaccurate record-keeping, errors, and delays in identifying and resolving health problems. The purpose of this study is to develop a geriatric care management system that combines signals from various wearable sensors, noncontact measurement devices, and image recognition techniques to monitor and detect changes in the health status of a person. The system relies on deep learning algorithms and the Internet of Things (IoT) to identify the patient and their six most pertinent poses. In addition, the algorithm has been developed to monitor changes in the patient’s position over a longer period of time, which could be important for detecting health problems in a timely manner and taking appropriate measures. Finally, based on expert knowledge and a priori rules integrated in a decision tree-based model, the automated final decision on the status of nursing care plan is generated to support nursing staff.
Heart rate recovery (HRR) after physical exercise is a convenient method to assess cardiovascular autonomic function. Since stair climbing is a common daily activity, usually followed by a slow walking or rest, this type of activity can be considered as an alternative HRR test. The present study explores the feasibility to estimate HRR parameters after stair climbing using a wrist-worn device with embedded photoplethysmography and barometric pressure sensors. A custom-made wrist-worn device, capable of acquiring heart rate and altitude, was used to estimate the time-constant of exponential decay , the short-term time constant , and the decay of heart rate in 1 min . Fifty-four healthy volunteers were instructed to climb the stairs at three different climbing rates. When compared to the reference electrocardiogram, the absolute and percentage errors were found to be ≤ 21.0 s (≤ 52.7%) for , ≤ 0.14 (≤ 19.2%) for , and ≤ 7.16 bpm (≤ 20.7%) for in 75% of recovery phases available for analysis. The proposed approach to monitoring HRR parameters in an unobtrusive way may complement information provided by personal health monitoring devices (e.g., weight loss, physical activity), as well as have clinical relevance when evaluating the efficiency of cardiac rehabilitation program outside the clinical setting.
Objective : The growing interest to integrate consumer smart wristbands in eHealth applications spawns the need for novel approaches of data parametrization which account for the technology-specific constraints. The present study aims to investigate the feasibility of a consumer smart wristband to be used for computing pulse rate parameters during free-living activities. Approach : The feasibility of computing pulse rate variability (PRV) as well as pulse rate and physical activity-related parameters using the smart wristband was investigated, having an electrocardiogram as a reference. The parameters were studied on the pulse rate and step data from 54 participants, diagnosed with various cardiovascular diseases. The data were acquired during free-living activities with no user lifestyle intervention. Main results : The comparison results show that the smart wristband is well-suited for computing the mean interbeat interval and the standard deviation of the averaged interbeat intervals. However, it is less reliable when estimating frequency domain and nonlinear parameters. Heart recovery time, estimated by fitting an exponential model to the events, satisfying the conditions of the 3 min step test, showed satisfactory agreement (relative error <20%) with the reference ECG in one-third of all cases. On the other hand, the heart’s adaptation to physical workload, expressed as the slope of the linear regression curve, was underestimated in most cases. Significance : The present study demonstrates that pulse rate parametrization using a consumer smart wristband is in principle feasible. The results show that the smart wristband is well suited for computing basic PRV parameters which have been reported to be associated with poorer health outcomes. In addition, the study introduces a methodology for the estimation of post-exercise heart recovery time and the heart’s adaptation to physical workload during free-living activities.
8 February 2025 in Biomedical Signal Processing and Control
Purpose: Deep vein thrombosis (DVT) poses significant health risks, including potentially fatal pulmonary embolism. Current clinical practice relies heavily on ultrasonography, requiring a skilled specialist. Alternative methods, such as light reflection rheography (LRR) and venous occlusion plethysmography (VOP), are non-invasive and simple; however, studies report limited consistency and standardization. The development of biosignal-based diagnostic tools is constrained by the inherent risks of DVT, including embolization, and challenges in patient recruitment. The ability to simulate DVT-like conditions would aid in developing and testing alternative screening methods. This study aims to present a simulation method of venous hemodynamic alterations resembling deep vein thrombosis using controlled external thigh compression with ultrasonic visualization. Methods: Data collection with thirty healthy volunteers was conducted in a laboratory using a commercially available system VasoScreen 5000–4000 to record LRR and VOP signals. Vein stenosis at varying levels was induced through controlled external thigh compression under ultrasonic guidance. Results: The experimental simulation showed statistically significant but small changes in LRR parameters across different stenosis levels. In comparison, VOP results showed greater differences across stenosis levels, with 70% and 100% performing the best. In these cases, 47% and 70% of the measurements, respectively, were below the normal reference limit, with a notably increased outflow time constant, compared to the baseline measurements, where it remained low despite varying venous capacity. Conclusion: Presented hemodynamic alterations demonstrated to be a feasible option for simulating DVT-like conditions via controlled external pressure on the thigh.