Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Series
This work addresses the need for reliable real-time artefact cleaning in medical monitoring, such as for arterial blood pressure and photoplethysmography, to improve clinical decision-making, though it appears incremental as it builds on existing pulsatile waveform methods.
The authors tackled the problem of artefact contamination in medical pulsatile time series, which compromises clinical decision-making, by introducing GenClean, a generalised label-free framework that demonstrated robust performance under patient-level distribution shifts and was validated on a dataset of 180,000 ABP samples and cross-disease cohorts.
Artefacts compromise clinical decision-making in the use of medical time series. Pulsatile waveforms offer probabilities for accurate artefact detection, yet most approaches rely on supervised manners and overlook patient-level distribution shifts. To address these issues, we introduce a generalised label-free framework, GenClean, for real-time artefact cleaning and leverage an in-house dataset of 180,000 ten-second arterial blood pressure (ABP) samples for training. We first investigate patient-level generalisation, demonstrating robust performances under both intra- and inter-patient distribution shifts. We further validate its effectiveness through challenging cross-disease cohort experiments on the MIMIC-III database. Additionally, we extend our method to photoplethysmography (PPG), highlighting its applicability to diverse medical pulsatile signals. Finally, its integration into ICM+, a clinical research monitoring software, confirms the real-time feasibility of our framework, emphasising its practical utility in continuous physiological monitoring. This work provides a foundational step toward precision medicine in improving the reliability of high-resolution medical time series analysis