Key result
An LSTM multi-stage model using physiological features achieved a MAE of 2.03 ± 3.12 mmHg for SBP and 1.18 ± 1.70 mmHg for DBP, reducing errors by up to 86.21% versus standard features.
Why the study?
Optimal feature selection for continuous blood pressure estimation using interpretable models for medical professionals remains challenging.
Does an LSTM multi-stage transfer learning model using physiologically motivating features improve continuous blood pressure estimation accuracy from PPG signals compared to traditional models?
Does an LSTM multi-stage transfer learning model using physiologically motivating features improve continuous blood pressure estimation accuracy from PPG signals compared to traditional models?
A novel LSTM multi-stage transfer learning model using physiologically derived PPG features significantly improves continuous blood pressure estimation accuracy.
Requires prospective validation before clinical use; extends LSTM modeling for PPG-based BP estimation.
Considerable research has been devoted to developing machine-learning models for continuous Blood Pressure (BP) estimation. A challenging problem that arises in this domain is the selection of optimal features with interpretable models for medical professionals. The aim of this study was to investigate evidence-based physiologically motivating features based on a solid physiological background of BP determinants. A powerful and compact set of features encompassing six physiologically oriented features was extracted in addition to another set of features consisting of six commonly used features for comparison purposes. In this study, we proposed a BP predictive model using Long Short-Term Memory (LSTM) networks with multi-stage transfer learning approach. The proposed model topology consists of three cascaded stages. First, a BP classification stage. Second, a Mean Arterial Pressure (MAP) regression stage to further approximate a quantity proportional to Vascular Resistance (VR) using the extracted Cardiac Output (CO) from the PPG signal. Third, the main BP estimation stage. The final stage (final BP prediction) is able to exploit embedded correlations between BP and the proposed features along with derived outputs carrying hemodynamic characteristics through the sub-sequence stages. We also constructed traditional single-stage Artificial Neural Network (ANN) and LSTM-based models to appraise the performance gain of our proposed model. The models were tested and evaluated on 40 subjects from the MIMIC II database. The LSTM-based multi-stage model attained a MAE ± SD of 2.03 ± 3.12 for SBP and 1.18 ± 1.70 mmHg for DBP. The proposed set of features resulted in drastic error reduction, of up to 86.21%, compared to models trained on the commonly used features. The superior performance of the proposed multi-stage model provides confirmatory evidence that the selected transferable features among the stages coupled with the high-performing multi-stage topology enhance blood pressure estimation accuracy using PPG signals. This indicates the compelling nature and sufficiency of the proposed efficient features set.
No takes yet. Share an insight, caveat, or question.
Ali et al. (2022) studied Blood pressure estimation (n=40). LSTM multi-stage transfer learning model with physiological features vs. Models trained on commonly used features was evaluated on Mean Absolute Error (MAE) for Systolic and Diastolic Blood Pressure. An LSTM multi-stage model using physiological features achieved a MAE of 2.03 ± 3.12 mmHg for SBP and 1.18 ± 1.70 mmHg for DBP, reducing errors by up to 86.21% versus standard features.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: