A Multidimensional Data-Driven Hybrid Transformer Framework for Non-invasive Continuous Blood Pressure Prediction
2026-08-24 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new way to estimate blood pressure continuously without using a cuff by analyzing sequences of heart-related signals and personal information. They created a model that uses a combination of advanced techniques, including Transformers and machine learning methods, to better understand these signals. Testing on a large medical database showed their system can estimate blood pressure with small errors, meeting important accuracy standards. However, the authors note that further testing with new people and external validation are needed before this can be used in real clinical settings.
cuffless blood pressureECGPPGTransformermachine learningMIMIC-III databasediastolic blood pressuresystolic blood pressuremulti-head attentionclinical validation
Authors
Yuexin Ma, Jingqi Hou, Yuxuan Kang, Zhaoying Liu
Abstract
Objective. To develop and evaluate a cuffless continuous blood pressure (BP) estimator using temporal physiological and demographic features. We propose a hybrid Transformer framework to estimate diastolic and systolic BP from ECG/PPG-derived feature sequences. Approach. Rather than raw waveforms, the framework models 10-step sequences of six physiological descriptors and two demographic covariates. A Multi-Source Temporal Encoder Module combines Transformer, Kolmogorov-Arnold Network, and XGBoost branches to capture complementary temporal, nonlinear, and tabular information. A Dynamic Conditional Fusion-Decoder applies differential multi-head attention, token-weighted aggregation, and gated residual correction. A robust composite objective jointly optimizes DBP and SBP. Main results. Using the MIMIC-III Waveform and Clinical Databases, the source pool comprised 28,486 waveform segments from 203 subjects, and feature generation retained 53,621 observations from 166 subjects. On 2,431 segment-level held-out test windows, mean error +/- standard deviation was 0.41 +/- 3.74 mmHg for diastolic BP and -1.60 +/- 5.95 mmHg for systolic BP, with 95% limits of agreement of [-6.93, 7.74] and [-13.25, 10.06] mmHg, respectively. The proportions within 10 mmHg were 98.48% and 94.36%. The framework achieved the lowest standard deviations and narrowest limits of agreement among the locally retrained baselines. Significance. The feature-sequence fusion framework improved agreement with reference BP and fell within numerical AAMI and BHS Grade A thresholds on this split. This retrospective analysis is not formal device validation; subject-disjoint and external evaluation remain necessary before clinical use.