Enabling Continuous Wearable Reflectance Pulse Oximetry at the Sternum

Chan, Michael; Ganti, Venu; Heller, J. Alex; Abdallah, Calvin A.; Etemadi, Mozziyar; Inan, Omer T.

doi:10.3390/bios11120521

Cited by 16 publications

(7 citation statements)

References 34 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the modules were interfaced with a data acquisition system (MP160, Biopac Systems, Goleta, CA, USA) with dedicated software (AcqKnowledge, Biopac Systems, Goleta, CA, USA). Note that all the physiological signals employed in this work are highly compatible with wearable sensing, as demonstrated in our prior work on patch [ 26 ] and wristwatch [ 27 ] devices.…”

Section: Methodsmentioning

confidence: 91%

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

Chalumuri

Kimball

Mousavi

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.

show abstract

Section: Methodsmentioning

confidence: 91%

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

Chalumuri

Kimball

Mousavi

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“… 20 There are a number of rigid and bulky devices that monitor vasoconstriction. 12 , 13 , 21 , 22 , 23 , 24 , 25 , 26 Overall, new studies in soft material interfaces are necessary to unlock chest-based PPG’s medical potential for vasoconstriction detection.…”

Section: Introductionmentioning

confidence: 99%

Soft wireless sternal patch to detect systemic vasoconstriction using photoplethysmography

Zavanelli¹,

Lee²,

Guess³

et al. 2023

iScience

View full text Add to dashboard Cite

“…More complex signal processing circuits limit their application in wearable and portable scenarios [ 35 , 36 ]. There is an urgent need to design a small-size pulse wave sensor flexible array [ 37 , 38 , 39 ] and a signal processing circuit [ 40 ].…”

Section: Introductionmentioning

confidence: 99%

Wearable Multi-Channel Pulse Signal Acquisition System Based on Flexible MEMS Sensor Arrays with TSV Structure

Kang,

Huang,

Zhang

et al. 2023

Biomimetics

View full text Add to dashboard Cite

Micro-electro-mechanical system (MEMS) pressure sensors play a significant role in pulse wave acquisition. However, existing MEMS pulse pressure sensors bound with a flexible substrate by gold wire are vulnerable to crush fractures, leading to sensor failure. Additionally, establishing an effective mapping between the array sensor signal and pulse width remains a challenge. To solve the above problems, we propose a 24-channel pulse signal acquisition system based on a novel MEMS pressure sensor with a through-silicon-via (TSV) structure, which connects directly to a flexible substrate without gold wire bonding. Firstly, based on the MEMS sensor, we designed a 24-channel pressure sensor flexible array to collect the pulse waves and static pressure. Secondly, we developed a customized pulse preprocessing chip to process the signals. Finally, we built an algorithm to reconstruct the three-dimensional pulse wave from the array signal and calculate the pulse width. The experiments verify the high sensitivity and effectiveness of the sensor array. In particular, the measurement results of pulse width are highly positively correlated with those obtained via infrared images. The small-size sensor and custom-designed acquisition chip meet the needs of wearability and portability, meaning that it has significant research value and commercial prospects.

show abstract

Enabling Continuous Wearable Reflectance Pulse Oximetry at the Sternum

Cited by 16 publications

References 34 publications

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

Soft wireless sternal patch to detect systemic vasoconstriction using photoplethysmography

Wearable Multi-Channel Pulse Signal Acquisition System Based on Flexible MEMS Sensor Arrays with TSV Structure

Contact Info

Product

Resources

About