End-to-end sensor fusion and classification of atrial fibrillation using deep neural networks and smartphone mechanocardiography.

Objective. The purpose of this research is to develop a new deep learning framework for detecting atrial fibrillation (AFib), one of the most common heart arrhythmias, by analyzing the heart's mechanical functioning as reflected in seismocardiography (SCG) and gyrocardiography (GCG) signals. Jointly, SCG and GCG constitute the concept of mechanocardiography (MCG), a method used to measure precordial vibrations with the built-in inertial sensors of smartphones.Approach. We present a modified deep residual neural network model for the classification of sinus rhythm, AFib, and Noise categories from tri-axial SCG and GCG data derived from smartphones. In the model presented, pre-processing including automated early sensor fusion and spatial feature extraction are carried out using attention-based convolutional and residual blocks. Additionally, we use bidirectional long short-term memory layers on top of fully-connected layers to extract both spatial and spatiotemporal features of the multidimensional SCG and GCG signals. The dataset consisted of 728 short measurements recorded from 300 patients. Further, the measurements were divided into disjoint training, validation, and test sets, respectively, of 481 measurements, 140 measurements, and 107 measurements. Prior to ingestion by the model, measurements were split into 10 s segments with 75 percent overlap, pre-processed, and augmented.Main results. On the unseen test set, the model delivered average micro- and macro-F1-score of 0.88 (0.87-0.89; 95% CI) and 0.83 (0.83-0.84; 95% CI) for the segment-wise classification as well as 0.95 (0.94-0.96; 95% CI) and 0.95 (0.94-0.96; 95% CI) for the measurement-wise classification, respectively.Significance. Our method not only can effectively fuse SCG and GCG signals but also can identify heart rhythms and abnormalities in the MCG signals with remarkable accuracy.

Identification of Motor Symptoms Related to Parkinson Disease Using Motion-Tracking Sensors at Home (KÄVELI): Protocol for an Observational Case-Control Study.

BACKGROUND: Clinical characterization of motion in patients with Parkinson disease (PD) is challenging: symptom progression, suitability of medication, and level of independence in the home environment can vary across time and patients. Appointments at the neurological outpatient clinic provide a limited understanding of the overall situation. In order to follow up these variations, longer-term measurements performed outside of the clinic setting could help optimize and personalize therapies. Several wearable sensors have been used to estimate the severity of symptoms in PD; however, longitudinal recordings, even for a short duration of a few days, are rare. Home recordings have the potential benefit of providing a more thorough and objective follow-up of the disease while providing more information about the possible need to change medications or consider invasive treatments. OBJECTIVE: The primary objective of this study is to collect a dataset for developing methods to detect PD-related symptoms that are visible in walking patterns at home. The movement data are collected continuously and remotely at home during the normal lives of patients with PD as well as controls. The secondary objective is to use the dataset to study whether the registered medication intakes can be identified from the collected movement data by looking for and analyzing short-term changes in walking patterns. METHODS: This paper described the protocol for an observational case-control study that measures activity using three different devices: (1) a smartphone with a built-in accelerometer, gyroscope, and phone orientation sensor, (2) a Movesense smart sensor to measure movement data from the wrist, and (3) a Forciot smart insole to measure the forces applied on the feet. The measurements are first collected during the appointment at the clinic conducted by a trained clinical physiotherapist. Subsequently, the subjects wear the smartphone at home for 3 consecutive days. Wrist and insole sensors are not used in the home recordings. RESULTS: Data collection began in March 2018. Subject recruitment and data collection will continue in spring 2019. The intended sample size was 150 subjects. In 2018, we collected a sample of 103 subjects, 66 of whom were diagnosed with PD. CONCLUSIONS: This study aims to produce an extensive movement-sensor dataset recorded from patients with PD in various phases of the disease as well as from a group of control subjects for effective and impactful comparison studies. The study also aims to develop data analysis methods to monitor PD symptoms and the effects of medication intake during normal life and outside of the clinic setting. Further applications of these methods may include using them as tools for health care professionals to monitor PD remotely and applying them to other movement disorders. TRIAL REGISTRATION: ClinicalTrials.gov NCT03366558; https://clinicaltrials.gov/ct2/show/NCT03366558. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/12808.

Identification of Parkinson's Disease Utilizing a Single Self-recorded 20-step Walking Test Acquired by Smartphone's Inertial Measurement Unit.

Parkinson's disease (PD) is a degenerative and long-term disorder of the central nervous system, which often causes motor symptoms, e.g., tremor, rigidity, and slowness. Currently, the diagnosis of PD is based on patient history and clinical examination. Technology-derived decision support systems utilizing, for example, sensor-rich smartphones can facilitate more accurate PD diagnosis. These technologies could provide less obtrusive and more comfortable remote symptom monitoring. The recent studies showed that motor symptoms of PD can reliably be detected from data gathered via smartphones. The current study utilized an open-access dataset named "mPower" to assess the feasibility of discriminating PD from non-PD by analyzing a single self-administered 20-step walking test. From this dataset, 1237 subjects (616 had PD) who were age and gender matched were selected and classified into PD and non-PD categories. Linear acceleration (ACC) and gyroscope (GYRO) were recorded by built-in sensors of smartphones. Walking bouts were extracted by thresholding signal magnitude area of the ACC signals. Features were computed from both ACC and GYRO signals and fed into a random forest classifier of size 128 trees. The classifier was evaluated deploying 100-fold cross-validation and provided an accumulated accuracy rate of 0.7 after 10k validations. The results show that PD and non-PD patients can be separated based on a single short-lasting self-administered walking test gathered by smartphones' built-in inertial measurement units.

An Activity Recognition Framework Deploying the Random Forest Classifier and A Single Optical Heart Rate Monitoring and Triaxial AccelerometerWrist-Band.

Wrist-worn sensors have better compliance for activity monitoring compared to hip, waist, ankle or chest positions. However, wrist-worn activity monitoring is challenging due to the wide degree of freedom for the hand movements, as well as similarity of hand movements in different activities such as varying intensities of cycling. To strengthen the ability of wrist-worn sensors in detecting human activities more accurately, motion signals can be complemented by physiological signals such as optical heart rate (HR) based on photoplethysmography. In this paper, an activity monitoring framework using an optical HR sensor and a triaxial wrist-worn accelerometer is presented. We investigated a range of daily life activities including sitting, standing, household activities and stationary cycling with two intensities. A random forest (RF) classifier was exploited to detect these activities based on the wrist motions and optical HR. The highest overall accuracy of 89.6 ± 3.9% was achieved with a forest of a size of 64 trees and 13-s signal segments with 90% overlap. Removing the HR-derived features decreased the classification accuracy of high-intensity cycling by almost 7%, but did not affect the classification accuracies of other activities. A feature reduction utilizing the feature importance scores of RF was also carried out and resulted in a shrunken feature set of only 21 features. The overall accuracy of the classification utilizing the shrunken feature set was 89.4 ± 4.2%, which is almost equivalent to the above-mentioned peak overall accuracy.

Seasonal weight variation patterns in seven countries located in northern and southern hemispheres.

The digital revolution of information and technology in late 20th century has led to emergence of devices that help people monitor their weight in a long-term manner. Investigation of population-level variations of body mass using smart connected weight scales enabled the health coaches acquire deeper insights about the models of people's behavior as a function of time. Typically, body mass varies when the seasons change. That is, during the warmer seasons people's body mass tend to decrease while in colder seasons it usually moves up. In this paper we study the seasonal variations of body mass in seven countries by utilization of linear regression. Deviation of monthly weight values from the starting point of astronomical years (beginning of spring) were modeled by fitting orthogonal polynomials in each country. The distinction of weight variations in southern and northern hemispheres were then investigated. The studied population involves 6429 anonymous weight scale users from:(1) Australia, (2) Brazil, (3) France, (4) Germany, (5) Great Britain, (6) Japan, and (7) United States of America. The results suggest that there are statistically significant differences between the models of weight variation in southern and northern hemispheres. In both northern and southern hemispheres the lowest weight values were observed in the summer. However, the highest weight values were noticed in the winter and in the spring for northern and southern hemispheres, respectively.