December 5, 2024Scientific ReportsOpen Access

Robust modelling of arterial blood pressure reconstruction from photoplethysmography

View Full Paper

Ask AI

Bookmark

Why the study?

Blood pressure indicates cardiovascular disease and arterial blood pressure waveforms reflect cardiovascular status, prompting the development of deep-learning methods to convert photoplethysmogram signals into continuous waveforms.

Does a U2-Net-based deep learning model with a Bi-block and combined loss function improve the accuracy of arterial blood pressure reconstruction from photoplethysmography compared to existing methods?

Structured PICO

Population

150 records from the UCI dataset (derived from MIMIC II) and 20 cases from the VitalDB dataset containing synchronized photoplethysmogram (PPG) and arterial blood pressure (ABP) signals.

Intervention

A deep-learning method based on U2-Net with a Bi-block and a combined loss function to convert photoplethysmogram (PPG) signals into arterial blood pressure (ABP) waveforms.

Comparator

Existing methods including standard U2-Net with MSE loss, W-Net, Wave-U-Net, and other PPG-to-ABP conversion models.

Outcome

Mean absolute error ± standard deviation (MAE ± STD) for systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP), and total error index (TEI).surrogate

A novel deep-learning model using U2-Net and a combined loss function accurately reconstructs arterial blood pressure waveforms from photoplethysmography signals, demonstrating robustness across different datasets and sampling frequencies.

Limitations

The MAX loss function introduced in the combined loss function focuses more on minimizing the maximum error, which sacrifices the accuracy of the waveform’s mean value to some extent.

Implication

Enables potential cuffless BP monitoring; hypothesis-generating and requires prospective validation before clinical adoption.

Abstract

Blood pressure is a crucial indicator of cardiovascular disease, and arterial blood pressure (ABP) waveforms contain information that reflects the cardiovascular status. We propose a novel deep-learning method that converts photoplethysmogram (PPG) signals into ABP waveforms. We used [Formula: see text]-Net as a feature extractor and designed a Bi-block to capture individualised time information in encoder feature extraction. We further enhanced the prediction accuracy of the ABP waveforms by applying a combined loss function to each layer of deep supervision. We also propose a total error index (TEI) to measure overall performance. Furthermore, we extended our method from the UCI dataset to the VitalDB dataset, achieving mean absolute error ± standard deviation (MAE ± STD) values of 2.48 ± 1.95, 1.42 ± 1.42, and 1.48 ± 1.36 mmHg for systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP) in UCI dataset, and 2.16 ± 1.53, 1.12 ± 0.59, and 1.35 ± 0.84 mmHg in VitalDB dataset, respectively. The mean ± STD values of the TEI index are 0.29 ± 0.10 in UCI dataset and 0.29 ± 0.15 in VitalDB dataset. These results demonstrate the superiority of the proposed method over existing methods and its robustness to different sampling frequencies and devices.