Objective: This paper discusses the evolution of pervasive healthcare from its inception for activity recognition using wearable sensors to the future of sensing implant deployment and data processing. Methods: We provide an overview of some of the past milestones and recent developments, categorized into different generations of pervasive sensing applications for health monitoring. This is followed by a review on recent technological advances that have allowed unobtrusive continuous sensing combined with diverse technologies to reshape the clinical workflow for both acute and chronic disease management. We discuss the opportunities of pervasive health monitoring through data linkages with other health informatics systems including the mining of health records, clinical trial databases, multiomics data integration, and social media. Conclusion: Technical advances have supported the evolution of the pervasive health paradigm toward preventative, predictive, personalized, and participatory medicine. Significance: The sensing technologies discussed in this paper and their future evolution will play a key role in realizing the goal of sustainable healthcare systems.

From Wearable Sensors to Smart Implants-–Toward Pervasive and Personalized Healthcare

Recent studies in computer vision have shown that, while practically invisible to a human observer, skin color changes due to blood flow can be captured on face videos and, surprisingly, be used to estimate the heart rate (HR). While considerable progress has been made in the last few years, still many issues remain open. In particular, state of-the-art approaches are not robust enough to operate in natural conditions (e.g. in case of spontaneous movements, facial expressions, or illumination changes). Opposite to previous approaches that estimate the HR by processing all the skin pixels inside a fixed region of interest, we introduce a strategy to dynamically select face regions useful for robust HR estimation. Our approach, inspired by recent advances on matrix completion theory, allows us to predict the HR while simultaneously discover the best regions of the face to be used for estimation. Thorough experimental evaluation conducted on public benchmarks suggests that the proposed approach significantly outperforms state-of the-art HR estimation methods in naturalistic conditions.

/pdf/self-adaptive-matrix-completion-for-heart-rate-estimation-34gc3nht50.pdf

Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions

This paper presents a MUlti-SEnsor biomedical IC (MUSEIC). It features a high-performance, low-power analog front-end (AFE) and fully integrated DSP. The AFE has three biopotential readouts, one bio-impedance readout, and support for general-purpose analog sensors The biopotential readout channels can handle large differential electrode offsets ( ${\pm} $ 400 mV), achieve high input impedance ( ${>}$ 500 M $\Omega$ ), low noise ( ${ 620 nVrms in 150 Hz), and large CMRR ( ${>}$ 110 dB) without relying on trimming while consuming only 31 $\mu$ W/channel. In addition, fully integrated real-time motion artifact reduction, based on simultaneous electrode-tissue impedance measurement, with feedback to the analog domain is supported. The bio-impedance readout with pseudo-sine current generator achieves a resolution of 9.8 m $\Omega$ / $\surd$ Hz while consuming just 58 $\mu$ W/channel. The DSP has a general purpose ARM Cortex M0 processor and an HW accelerator optimized for energy-efficient execution of various biomedical signal processing algorithms achieving 10 $\times$ or more energy savings in vector multiply-accumulate executions.

A 345 µW Multi-Sensor Biomedical SoC With Bio-Impedance, 3-Channel ECG, Motion Artifact Reduction, and Integrated DSP

This paper describes a mixed-signal ECG System-on-Chip (SoC) that is capable of implementing configurable functionality with low-power consumption for portable ECG monitoring applications. A low-voltage and high performance analog front-end extracts 3-channel ECG signals and single channel electrode-tissue-impedance (ETI) measurement with high signal quality. This can be used to evaluate the quality of the ECG measurement and to filter motion artifacts. A custom digital signal processor consisting of 4-way SIMD processor provides the configurability and advanced functionality like motion artifact removal and R peak detection. A built-in 12-bit analog-to-digital converter (ADC) is capable of adaptive sampling achieving a compression ratio of up to 7, and loop buffer integration reduces the power consumption for on-chip memory access. The SoC is implemented in 0.18 $\mu$ m CMOS process and consumes 32 $\mu$ W from a 1.2 V while heart beat detection application is running, and integrated in a wireless ECG monitoring system with Bluetooth protocol. Thanks to the ECG SoC, the overall system power consumption can be reduced significantly.

A Configurable and Low-Power Mixed Signal SoC for Portable ECG Monitoring Applications

Breathing rate (BR) is a key physiological parameter used in a range of clinical settings. Despite its diagnostic and prognostic value, it is still widely measured by counting breaths manually. A plethora of algorithms have been proposed to estimate BR from the electrocardiogram (ECG) and pulse oximetry (photoplethysmogram, PPG) signals. These BR algorithms provide opportunity for automated, electronic, and unobtrusive measurement of BR in both healthcare and fitness monitoring. This paper presents a review of the literature on BR estimation from the ECG and PPG. First, the structure of BR algorithms and the mathematical techniques used at each stage are described. Second, the experimental methodologies that have been used to assess the performance of BR algorithms are reviewed, and a methodological framework for the assessment of BR algorithms is presented. Third, we outline the most pressing directions for future research, including the steps required to use BR algorithms in wearable sensors, remote video monitoring, and clinical practice.

Breathing Rate Estimation From the Electrocardiogram and Photoplethysmogram: A Review

A motion artifact removal method with a two-stage cascade LMS adaptive filter is proposed for an ambulatory ECG monitoring system. The first LMS stage consisting of analog feedback prevents the signal saturation to reduce the input dynamic range. An adaptive step-size LMS algorithm is introduced and employed for the second LMS stage. The adaptive step-size algorithm can achieve fast convergence to track large sudden motion artifact quickly, while preventing the distortion of the ECG component. The filtering performance is evaluated by the heart beat detection, measured by sensitivity (Se) and positive predictive value (+p), and the performance is increased by 9.8% and 6.48%, respectively, compared to the unfiltered signal at the worst case with -25dB SNR. The proposed motion artifact method is implemented on an ambulatory ECG monitoring module, and the real-time measurement shows a significant performance improvement.

Motion artifact removal using cascade adaptive filtering for ambulatory ECG monitoring system

This paper presents a voltage-scalable digital signal processing system designed for the use in a wireless sensor node (WSN) for ambulatory monitoring of biomedical signals. To fulfill the requirements of ambulatory monitoring, power consumption, which directly translates to the WSN battery lifetime and size, must be kept as low as possible. The proposed processing platform is an event-driven system with resources to run applications with different degrees of complexity in an energy-aware way. The architecture uses effective system partitioning to enable duty cycling, single instruction multiple data (SIMD) instructions, power gating, voltage scaling, multiple clock domains, multiple voltage domains, and extensive clock gating. It provides an alternative processing platform where the power and performance can be scaled to adapt to the application need. A case study on a continuous wavelet transform (CWT)-based heart-beat detection shows that the platform not only preserves the sensitivity and positive predictivity of the algorithm but also achieves the lowest energy/sample for ElectroCardioGram (ECG) heart-beat detection publicly reported today.

An Ultra Low Energy Biomedical Signal Processing System Operating at Near-Threshold

Recent advances in low-power micro-electronics are revolutionizing ECG monitoring. Wearable patches now allow comfortable monitoring over several days. Achieving reliable and high integrity recording however remains a challenge, especially under daily-life activities. In this paper we present a system approach to motion artifact reduction in ambulatory recordings. A custom ultra-low-power ECG analog front-end read-out for simultaneous measurement of ECG and electrode-tissue impedance, from the same electrode, is reported. Integrating this front-end, we describe a wireless patch for the monitoring of 3-lead ECG, electrode electrical artifact and 3D-acceleration. Beyond ECG monitoring, this wireless patch provides the additional necessary data to filter out motion artifact. Two algorithm methods are tested. The first method applies ICA for de-noising multi-lead ECG recordings. The second method is an adaptive filter that uses skin/electrode impedance as the measurement of noise. Algorithms, circuits and system provide a platform for reliable ECG monitoring on-the-move.

Motion artifact reduction in ambulatory ECG monitoring: an integrated system approach

The performance of several adaptive filter (AdF) algorithm implementations was investigated in the context of cleaning noisy ambulatory ECGs. Together with a noisy ECG signal, both body movement measured with accelerometers and skin-electrode impedance (SEI) were considered as reference signals to the AdF. ECG with artificial motion artifacts were generated by combining clean ECGs with noise signals. Several implementations and combinations of AdFs, and two reference signals (accelerometers and SEI) were investigated. Performance was measured by evaluating the output (sensitivity (Se) and positive predictivity (+P)) of a beat detection (BD) algorithm. Using AdF algorithm improved the performance of a BD algorithm as compared to non-filtering. SEI used as reference signal outperformed accelerometers. A variant of LMS, LMS sign-error, gave the best performance from all implementations considered. However, distortion observed in the filtered signal is high and therefore, these results cannot be extended to other features within the ECG.

http://cinc.mit.edu/archives/2012/pdf/0045.pdf

Torfinn Berset

Papers

Motion artifact removal using cascade adaptive filtering for ambulatory ECG monitoring system

An Ultra Low Energy Biomedical Signal Processing System Operating at Near-Threshold

Motion artifact reduction in ambulatory ECG monitoring: an integrated system approach

Adaptive filtering in ECG denoising: A comparative study

Clinical validation of a low-power and wearable ECG patch for long term full-disclosure monitoring.