Speckle contrast optical spectroscopy improves cuffless blood pressure estimation compared to photoplethysmography (Conference Presentation)

Speckle contrast optical spectroscopy (SCOS) allows for simultaneous monitoring of blood flow (BFi) and volume (PPG) changes within each cardiac pulse. SCOS measurements were collected from 30 subjects and the BFi and PPG pulse waveforms (PWFs) were extracted. We found that machine learning models trained on both BFi and PPG features predicted blood pressure (BP) with lower errors compared to models trained only with PPG features. In addition, 20 subjects were remeasured several weeks later. The models were trained on an individual subject’s first measurement and used to predict BP for the second measurement. With the addition of BFi information, BP estimation was significantly improved.

Authors

Publication Details

Published
2025-03-20
DOI
https://doi.org/10.1117/12.3043781
Citations
1
Primary Topic
Non-Invasive Vital Sign Monitoring
Type
article
Field-Weighted Citation Impact
0.67
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Speckle contrast optical spectroscopy improves cuffless blood pressure estimation compared to photoplethysmography (Conference Presentation)

Nil Z. Gurel, Byungchan Kim, David A. Boas, Darren Roblyer et al.
1 citations
Non-Invasive Vital Sign Monitoring
0.67
article

Speckle contrast optical spectroscopy improves cuffless blood pressure estimation compared to photoplethysmography (Conference Presentation)

Nil Z. Gurel, Byungchan Kim, David A. Boas, Darren Roblyer, Francesco Marsili, Edbert J. Sie, Ana María González Pérez, Ariane Garrett
article en
1 citations

Abstract

Speckle contrast optical spectroscopy (SCOS) allows for simultaneous monitoring of blood flow (BFi) and volume (PPG) changes within each cardiac pulse. SCOS measurements were collected from 30 subjects and the BFi and PPG pulse waveforms (PWFs) were extracted. We found that machine learning models trained on both BFi and PPG features predicted blood pressure (BP) with lower errors compared to models trained only with PPG features. In addition, 20 subjects were remeasured several weeks later. The models were trained on an individual subject’s first measurement and used to predict BP for the second measurement. With the addition of BFi information, BP estimation was significantly improved.

Openalex Percentile: Top 34%
Non-Invasive Vital Sign Monitoring
0.67
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.