Diffuse correlation spectroscopy and machine learning algorithms provide continuous blood pressure feedback and allow real-time monitoring of intraoperative and at-risk patients.
Abnormal blood pressure is one of the key indicators of many common illnesses and conditions, and is important data for healthcare providers. For patients suffering from hypertension or cardiovascular disease, or undergoing surgery, continuous blood pressure monitoring can quickly detect dangerous fluctuations and avoid serious complications. However, existing continuous blood pressure monitoring can be invasive and painful, leading to unique complications.
Li et al. An alternative non-invasive method for continuous blood pressure monitoring using diffusion correlation spectroscopy (DCS) combined with machine learning has been developed.
DCS is a technique that relies on near-infrared light to directly image blood flow. Blood flow is not the same as blood pressure, but they are related, and the authors trained machine learning models to correlate the two. They demonstrated the effectiveness of this method by accurately measuring the blood pressure in 12 human subjects.
“In our tests, the results showed that continuous blood pressure monitoring achieved Grade A in both systolic and diastolic blood pressure, following the standards of the British Hypertension Society,” said author Zhe Li.
The author plans to continue developing machine learning models to expand the sample size and further improve its accuracy. It also integrates the integration of other physiological data into the analysis to improve results.
“In the future, this method could be applied to portable devices, allowing patients to monitor their blood pressure in real time in their daily lives,” Li said.
sauce: Zhe Li, Jiangtao Bai, Xianyu Cao, Haiqing Song, Peng Tian, Ran Wei, Jinchao Feng, Pengyu liu, Kebin Jia, Zhe Li, Jiangtao Bai, Xianyu Cao, Xianyu Cao, Xingyu Cao, Yangyu Cao, Yangyu Cao, Yangyu Cao, and Kebin Jia, “Continuous noninvasive blood pressure estimation using diffuse correlation spectroscopy.” APL Bioengineering (2025). You can access the article https://doi.org/10.1063/5.0266243 .
