This paper presents an automated procedure for acquisition and analysis of BallistoCardioGraphy (BCG) traces. A tri-axial accelerometer and a microcontroller unit are used to record heart-induced recoil forces generated from a lying subject. The problem of BCG J-peak annotation is split into two sub-tasks: candidates extraction, based on a detection signal, and actual annotation, guided by subject-specific search windows. Such procedure is derived from an automatic calibration, which is carried out with no need of concurrent ElectroCardioGram (ECG) or user intervention. The algorithm also implements post-annotation checks for refinement of annotation, which effectively reduces the number of missed J-peaks. The impact of each algorithm phase is analyzed, assessing statistical significance of each step; finally, performance is optimized in a data-driven fashion. Results show that the proposed methodology is able to achieve high sensitivity and precision (the median score is 98.9% and 98.1%, respectively) in J-peak detection. The quality of J-peaks timing annotation is further demonstrated by a very low discrepancy between BCG and ECG HR estimates. Over all population, the standard deviation of such error was found to be approximately 6.56 ms, whereas the Mean Absolute Error just 4.7 ms (i.e. ≈1.18;Ts, where Ts = 4 ms is the sampling period). Such scores, indeed, improve over recent related literature.
Environmental sensors are exploited in smart homes for many purposes. Sensor data inherently carries behavioral information, possibly useful to infer wellness and health-related insights in an indirect fashion. In order to exploit such features, however, powerful analytics are needed to convert raw sensor output into meaningful and accessible knowledge. In this paper, a complete monitoring architecture is presented, including home sensors and cloud-based back-end services. Unsupervised techniques for behavioral data analysis are presented, including: (i) regression and outlier detection models (also used as feature extractors for more complex models); (ii) statistical hypothesis testing frameworks for detecting changes in sensor-detected activities; and (iii) a clustering process, leveraging deep learning techniques, for extracting complex, multivariate patterns from daily sensor data. Such methods are discussed and evaluated on real-life data, collected within several EU-funded projects. Overall, the presented methods may prove very useful to build effective monitoring services, suitable for practical exploitation in caregiving activities, complementing conventional telemedicine techniques.
This paper introduces technical solutions devised to support the Deployment Site - Regione Emilia Romagna (DS-RER) of the ACTIVAGE project. The ACTIVAGE project aims at promoting IoT (Internet of Things)-based solutions for Active and Healthy ageing. DS-RER focuses on improving continuity of care for older adults (65+) suffering from aftereffects of a stroke event. A Wireless Sensor Kit based on Wi-Fi connectivity was suitably engineered and realized to monitor behavioral aspects, possibly relevant to health and wellbeing assessment. This includes bed/rests patterns, toilet usage, room presence and many others. Besides hardware design and validation, cloud-based analytics services are introduced, suitable for automatic extraction of relevant information (trends and anomalies) from raw sensor data streams. The approach is general and applicable to a wider range of use cases; however, for readability’s sake, two simple cases are analyzed, related to bed and toilet usage patterns. In particular, a regression framework is introduced, suitable for detecting trends (long and short-term) and labeling anomalies. A methodology for assessing multi-modal daily behavioral profiles is introduced, based on unsupervised clustering techniques. The proposed framework has been successfully deployed at several real-users’ homes, allowing for its functional validation. Clinical effectiveness will be assessed instead through a Randomized Control Trial study, currently being carried out.
Artificial Intelligence in combination with the Internet of Medical Things enables remote healthcare services through networks of environmental and/or personal sensors. We present a remote healthcare service system which collects real-life data through an environmental sensor package, including binary motion, contact, pressure, and proximity sensors, installed at households of elderly people. Its aim is to keep the caregivers informed of subjects’ health-status progressive trajectory, and alert them of health-related anomalies to enable objective on-demand healthcare service delivery at scale. The system was deployed in 19 households inhabited by an elderly person with post-stroke condition in the Emilia–Romagna region in Italy, with maximal and median observation durations of 98 and 55 weeks. Among these households, 17 were multi-occupancy residences, while the other 2 housed elderly patients living alone. Subjects’ daily behavioral diaries were extracted and registered from raw sensor signals, using rule-based data pre-processing and unsupervised algorithms. Personal behavioral habits were identified and compared to typical patterns reported in behavioral science, as a quality-of-life indicator. We consider the activity patterns extracted across all users as a dictionary, and represent each patient’s behavior as a ‘Bag of Words’, based on which patients can be categorized into sub-groups for precision cohort treatment. Longitudinal trends of the behavioral progressive trajectory and sudden abnormalities of a patient were detected and reported to care providers. Due to the sparse sensor setting and the multi-occupancy living condition, the sleep profile was used as the main indicator in our system. Experimental results demonstrate the ability to report on subjects’ daily activity pattern in terms of sleep, outing, visiting, and health-status trajectories, as well as predicting/detecting 75% hospitalization sessions up to 11 days in advance. 65% of the alerts were confirmed to be semantically meaningful by the users. Furthermore, reduced social interaction (outing and visiting), and lower sleep quality could be observed during the COVID-19 lockdown period across the cohort.
1 April 2019 in IEEE Transactions on Instrumentation and Measurement
This paper presents a fully automated procedure for acquiring and analyzing seismocardiographic (SCG) traces from an Inertial Measurement Unit (IMU) placed over a subject’s sternum. An automated calibration procedure allows for straightforward adaption to different subjects. Calibration is performed once per subject, exploiting ECG (electrocardiogram) markers; relevant patterns and parameters are automatically extracted and used for successive SCG processing, which does not require concurrent ECG information any longer. Annotation of SCG traces is performed in two steps: in the first one, a suitably engineered signal is derived from SCG and used as coarse heartbeat detector; then, annotation can be performed by comparing the prototype extracted at calibration time with segments of SCG data, near to the detected beats. The proposed methodology is validated by direct comparison with ECG, adopted as gold-standard. In particular, three main metrics are taken into account: sensitivity (i.e. percentage of correctly identified heartbeats, compared to ECG), precision (i.e. impact of false positives on truly detected beats) and R2 (i.e. linearity between beat-to-beat measurements as computed by ECG and SCG). Results show satisfactory performance, more than adequate to continuous, long-term monitoring: overall, approximately 90% of heartbeats are correctly detected, on average, with minimal false positives (≈1%). Linearity between ECG and SCG-computed beat-to-beat intervals is extremely high (R2 > 0.95, on average), indicating good agreement between the two measurement methods. These results suggest SCG can be used as a reliable, contactless measure of heart-related parameters.
This paper presents an unsupervised methodology to analyze SeismoCardioGram (SCG) signals. Starting from raw accelerometric data, heartbeat complexes are extracted and annotated, using a two-step procedure. An unsupervised calibration procedure is added to better adapt to different user patterns. Results show that the performance scores achieved by the proposed methodology improve over related literature: on average, 98.5% sensitivity and 98.6% precision are achieved in beat detection, whereas RMS (Root Mean Square) error in heartbeat interval estimation is as low as 4.6 ms. This allows SCG heartbeat complexes to be reliably extracted. Then, the morphological information of such waveforms is further processed by means of a modular Convolutional Variational AutoEncoder network, aiming at extracting compressed, meaningful representation. After unsupervised training, the VAE network is able to recognize different signal morphologies, associating each user to its specific patterns with high accuracy, as indicated by specific performance metrics (including adjusted random and mutual information score, completeness, and homogeneity). Finally, a Linear Model is used to interpret the results of clustering in the learned latent space, highlighting the impact of different VAE architectural parameters (i.e., number of stacked convolutional units and dimension of latent space).