Continuous Cuffless Blood Pressure Estimation Using a Multimodal Conv1D-LSTM Architecture and the SOUNDI® Wearable Device
Dario Bovio, Alice Turrini, Alice Prandoni, Alberto Porro, Pietro Cerveri, Caterina Salito · 2026
Read Continuous Cuffless Blood Pressure Estimation Using a Multimodal Conv1D-LSTM Architecture and the SOUNDI® Wearable Device by Dario Bovio, Alice Turrini, Alice Prandoni, Alberto Porro, Pietro Cerveri, Caterina Salito (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13510968.txt.
Description
Bovio and colleagues build a wearable that estimates blood pressure continuously without a cuff. Their 2026 paper pairs the SOUNDI device, a multimodal sensor platform, with a neural network mixing convolutional and memory layers to read physiological signals and predict systolic and diastolic pressure. Data came from twenty healthy volunteers measured against a validated ambulatory reference device.
Two evaluations were run. Testing on entirely unseen people, the honest test of generalisation, the best subject's average error was about five millimetres of mercury for systolic and under four for diastolic pressure. Under a personalised split, where the model sees part of each person's data, errors fell to about three millimetres for both values, with correlations near 0.95 for systolic pressure. The authors present the results as feasibility evidence for cuffless monitoring, while noting the gap between personalised and person-independent performance.
Catalog record
| CREATOR | Dario Bovio, Alice Turrini, Alice Prandoni, Alberto Porro, Pietro Cerveri, Caterina Salito |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |