Ultra-low-power Physical Activity Classifier for Wearables: From Generic MCUs to ASICs.

In the era of Internet of Things (IoT), an increasing amount of sensors is being integrated into intelligent wearable devices. These sensors have the potential to produce a large quantity of physiological data streams to be analyzed in order to produce meaningful and actionable information. An important part of this processing is usually located in the device itself and takes the form of embedded algorithms which are executed into the onboard microcontroller (MCU). As data processing algorithms have become more complex due to, in part, the disruption of machine learning, they are taking an increasing part of MCU time becoming one of the main driving factors in the energy budget of the overall embedded system. We propose to integrate such algorithms into dedicated low-power circuits making the power consumption of the processing part negligible to the overall system. We provide the results of several implementations of a pre-trained physical activity classifier used in smartwatches and wristbands. The algorithm combines signal processing for feature extraction and machine learning in the form of decision trees for physical activity classification. We show how an in-silicon implementation decreases up to 0.1 µW the power consumption compared to 73 µW on a general-purpose ARM's Cortex-M0 MCU.

Challenging the Limitations of Atrial Fibrillation Detection in the Presence of Other Cardiac Arrythmias.

Atrial fibrillation (AF) affects millions of people worldwide and needs to be diagnosed in its early stage to provide proper treatment. However, the numerous wearable devices available today are not yet able to discriminate AF episodes from other cardiac arrhythmias and merely detect normal vs abnormal rhythms.In this study we investigated the performance of a traditional classifier - designed to distinguish AF and sinus rhythm (SR) using inter-beat intervals (IBI) - when confronted with other - non-AF - arrhythmias. This classifier was challenged with data of 37 patients wearing an optical heart rate monitor device during catheter ablation procedures. We first analyzed the classification performance of pure AF vs SR and then gradually introduced non-AF arrhythmias in the time windows used for classification.We obtained a high classification performance (accuracy, sensitivity and specificity of 0.979, 1.000 and 0.966) for purely AF and SR. In contrast, when increasing the maximal possible number of non-AF arrhythmias to 50%, the performance decreased to an accuracy, sensitivity and specificity of 0.886, 0.998 and 0.853. While sinus tachycardia led to false positives the classification was not impaired by the presence of extrasystoles, bigeminy, bradycardia, frequent ectopic beats or atrial flutter.Our study quantifies to what extent a traditional IBI-based classifier is not sufficient to distinguish AF from other arrhythmias. Future work should concentrate on acquiring datasets with a high diversity of arrhythmias and employing new classification features.

Discrimination of entangled photon pair from classical photons by de Broglie wavelength.

Quantum optics largely relies on the fundamental concept that the diffraction and interference patterns of a multi-partite state are determined by its de Broglie wavelength. In this paper we show that this is still true for a mixed state with one sub-system being in a classical coherent state and one being in entangled state. We demonstrate the quantum-classical light discrimination using de Broglie wavelength for the states with all classical parameters being the same.

Automated Pulse Oximeter Waveform Analysis to Track Changes in Blood Pressure During Anesthesia Induction: A Proof-of-Concept Study.

BACKGROUND: Intraoperative hypotension is associated with postoperative complications and death. Oscillometric brachial cuffs are used to measure arterial pressure (AP) in most surgical patients but may miss acute changes in AP. We hypothesized that pulse oximeter waveform analysis may help to detect changes in systolic AP (SAP) and mean AP (MAP) during anesthesia induction. METHODS: In 40 patients scheduled for an elective surgery necessitating general anesthesia and invasive AP monitoring, we assessed the performance of a pulse oximeter waveform analysis algorithm (optical blood pressure monitoring [oBPM]) to estimate SAP, MAP, and their changes during the induction of general anesthesia. Acute AP changes (>20%) in SAP and MAP assessed by the reference invasive method and by oBPM were compared using 4-quadrant and polar plots. The tracking ability of the algorithm was evaluated on changes occurring over increasingly larger time spans, from 30 seconds up to 5 minutes. The second objective of the study was to assess the ability of the oBPM algorithm to cope with the Association for the Advancement of Medical Instrumentation (AAMI) standards. The accuracy and precision of oBPM in estimating absolute SAP and MAP values compared to the invasive method was evaluated at various instants after algorithm calibration, from 30 seconds to 5 minutes. RESULTS: Rapid changes (occurring over time spans of ≤60 seconds) in SAP and MAP assessed by oBPM were strongly correlated and showed excellent concordance with changes in invasive AP (worst-case Pearson correlation of 0.94 [0.88, 0.97] [95% confidence interval], concordance rate of 100% [100%, 100%], and angular concordance rate at ±30° of 100% [100%, 100%]). The trending ability tended to decrease progressively as the time span over which the changes occurred increased, reaching 0.89 (0.85, 0.91) (Pearson correlation), 97% (95%, 100%) (concordance rate), and 90% (85%, 94%) (angular concordance rate) in the worst case. Regarding accuracy and precision, oBPM-derived SAP values were shown to comply with AAMI criteria up to 2 minutes after calibration, whereas oBPM-derived MAP values were shown to comply with criteria at all times. CONCLUSIONS: Pulse oximeter waveform analysis was useful to track rapid changes in SAP and MAP during anesthesia induction. A good agreement with reference invasive measurements was observed for MAP up to at least 5 minutes after initial calibration. In the future, this method could be used to track changes in AP between intermittent oscillometric measurements and to automatically trigger brachial cuff inflation when a significant change in AP is detected.

Can one detect atrial fibrillation using a wrist-type photoplethysmographic device?

This study aims at evaluating the potential of a wrist-type photoplethysmographic (PPG) device to discriminate between atrial fibrillation (AF) and other types of rhythm. Data from 17 patients undergoing catheter ablation of various arrhythmias were processed. ECGs were used as ground truth and annotated for the following types of rhythm: sinus rhythm (SR), AF, and ventricular arrhythmias (VA). A total of 381/1370/415 10-s epochs were obtained for the three categories, respectively. After pre-processing and removal of segments corresponding to motion artifacts, two different types of feature were derived from the PPG signals: the interbeat interval-based features and the wave-based features, consisting of complexity/organization measures that were computed either from the PPG waveform itself or from its power spectral density. Decision trees were used to assess the discriminative capacity of the proposed features. Three classification schemes were investigated: AF against SR, AF against VA, and AF against (SR&VA). The best results were achieved by combining all features. Accuracies of 98.1/95.9/95.0 %, specificities of 92.4/88.7/92.8 %, and sensitivities of 99.7/98.1/96.2 % were obtained for the three aforementioned classification schemes, respectively. Graphical Abstract Atrial fibrillation detection using PPG signals.

Respiratory and cardiac monitoring at night using a wrist wearable optical system.

Sleep monitoring provides valuable insights into the general health of an individual and helps in the diagnostic of sleep-derived illnesses. Polysomnography, is considered the gold standard for such task. However, it is very unwieldy and therefore not suitable for long-term analysis. Here, we present a non-intrusive wearable system that, by using photoplethysmography, it can estimate beat-to-beat intervals, pulse rate, and breathing rate reliably during the night. The performance of the proposed approach was evaluated empirically in the Department of Psychology at the University of Fribourg. Each participant was wearing two smart-bracelets from Ava as well as a complete polysomnographic setup as reference. The resulting mean absolute errors are 17.4ms (MAPE 1.8%) for the beat-to-beat intervals, 0.13beats-per-minute (MAPE 0.20%) for the pulse rate, and 0.9breaths-per-minute (MAPE 6.7%) for the breath rate.

Towards 24/7 continuous heart rate monitoring.

Heart rate (HR) and HR variability (HRV) carry rich information about physical activity, mental and physical load, physiological status, and health of an individual. When combined with activity monitoring and personalized physiological modelling, HR/HRV monitoring may be used for monitoring of complex behaviors and impact of behaviors and external factors on the current physiological status of an individual. Optical HR monitoring (OHR) from wrist provides a comfortable and unobtrusive method for HR/HRV monitoring and is better adhered by users than traditional ECG electrodes or chest straps. However, OHR power consumption is significantly higher than that for ECG based methods due to the measurement principle based on optical illumination of the tissue. We developed an algorithmic approach to reduce power consumption of the OHR in 24/7 HR trending. We use continuous activity monitoring and a fast converging frequency domain algorithm to derive a reliable HR estimate in 7.1s (during outdoor sports, in average) to 10.0s (during daily life). The method allows >80% reduction in power consumption in 24/7 OHR monitoring when average HR monitoring is targeted, without significant reduction in tracking accuracy.

Evaluation of accuracy and reliability of PulseOn optical heart rate monitoring device.

PulseOn is a wrist-worn optical heart rate (HR) monitor based on photoplethysmography. It utilizes multi-wavelength technology and optimized sensor geometry to monitor blood flow at different depths of skin tissue, and it dynamically adapts to an optimal measurement depth in different conditions. Movement artefacts are reduced by adaptive movement-cancellation algorithms and optimized mechanics, which stabilize the sensor-to-skin contact. In this paper, we evaluated the accuracy and reliability of PulseOn technology against ECG-derived HR in laboratory conditions during a wide range of physical activities and also during outdoor sports. In addition, we compared the performance to another on-the-shelf wrist-worn consumer product Mio LINK(®). The results showed PulseOn reliability (% of time with error <;10bpm) of 94.5% with accuracy (100% - mean absolute percentage error) 96.6% as compared to ECG (vs 86.6% and 94.4% for Mio LINK(®), correspondingly) during laboratory protocol. Similar or better reliability and accuracy was seen during normal outdoor sports activities. The results show that PulseOn provides reliability and accuracy similar to traditional chest strap ECG HR monitors during cardiovascular exercise.

Evaluation of the beat-to-beat detection accuracy of PulseOn wearable optical heart rate monitor.

Heart rate variability (HRV) provides significant information about the health status of an individual. Optical heart rate monitoring is a comfortable alternative to ECG based heart rate monitoring. However, most available optical heart rate monitoring devices do not supply beat-to-beat detection accuracy required by proper HRV analysis. We evaluate the beat-to-beat detection accuracy of a recent wrist-worn optical heart rate monitoring device, PulseOn (PO). Ten subjects (8 male and 2 female; 35.9±10.3 years old) participated in the study. HRV was recorded with PO and Firstbeat Bodyguard 2 (BG2) device, which was used as an ECG based reference. HRV was recorded during sleep. As compared to BG2, PO detected on average 99.57% of the heartbeats (0.43% of beats missed) and had 0.72% extra beat detection rate, with 5.94 ms mean absolute error (MAE) in beat-to-beat intervals (RRI) as compared to the ECG based RRI BG2. Mean RMSSD difference between PO and BG2 derived HRV was 3.1 ms. Therefore, PO provides an accurate method for long term HRV monitoring during sleep.

Parametric estimation of pulse arrival time: a robust approach to pulse wave velocity.

Pulse wave velocity (PWV) is a surrogate of arterial stiffness and represents a non-invasive marker of cardiovascular risk. The non-invasive measurement of PWV requires tracking the arrival time of pressure pulses recorded in vivo, commonly referred to as pulse arrival time (PAT). In the state of the art, PAT is estimated by identifying a characteristic point of the pressure pulse waveform. This paper demonstrates that for ambulatory scenarios, where signal-to-noise ratios are below 10 dB, the performance in terms of repeatability of PAT measurements through characteristic points identification degrades drastically. Hence, we introduce a novel family of PAT estimators based on the parametric modeling of the anacrotic phase of a pressure pulse. In particular, we propose a parametric PAT estimator (TANH) that depicts high correlation with the Complior(R) characteristic point D1 (CC = 0.99), increases noise robustness and reduces by a five-fold factor the number of heartbeats required to obtain reliable PAT measurements.