Publications by authors named "D M Atienza"
Acoustical knee health assessment has long promised an alternative to clinically available medical imaging tools, but this modality has yet to be adopted in medical practice. The field is currently led by machine learning models processing acoustical features, which have presented promising diagnostic performances. However, these methods overlook the intricate multi-source nature of audio signals and the underlying mechanisms at play.
View Article and Find Full Text PDFKID-PPG: Knowledge Informed Deep Learning for Extracting Heart Rate from a Smartwatch.
IEEE Trans Biomed Eng
October 2024
Article Synopsis
- Accurate extraction of heart rate from photoplethysmography (PPG) signals is difficult due to issues like motion artifacts and signal loss, leading to challenges in measurement.
- The authors present KID-PPG, a new deep learning model that combines expert knowledge with advanced techniques to improve heart rate tracking by addressing motion artifact removal, signal degradation assessment, and realistic analysis.
- KID-PPG was tested on the PPGDalia dataset, achieving superior accuracy with an average error of 2.85 beats per minute, demonstrating that using prior knowledge can significantly enhance deep learning performance in biomedical applications.
Article Synopsis
- There is an increasing demand for effective automated seizure detection algorithms using EEG data due to the rise of long-term monitoring needs.
- This paper introduces a unified framework to standardize validation methods for these algorithms, addressing the inconsistencies in datasets, methodologies, and performance measures.
- The authors also present the EEG 10-20 seizure detection benchmark, along with an open-source software library, to help evaluate existing algorithms and enhance research in seizure detection for better outcomes for individuals with epilepsy.*
Irregular sampling of time series in electronic health records (EHRs) is one of the main challenges for developing machine learning models. Additionally, the pattern of missing values in certain clinical variables is not at random but depends on the decisions of clinicians and the state of the patient. Point process is a mathematical framework for analyzing event sequence data consistent with irregular sampling patterns.
View Article and Find Full Text PDFVinylene carbonate (VC) is a widely used electrolyte additive in lithium-ion batteries for enhanced solid electrolyte interphase formation on the anode side. However, the cathode electrolyte interphase (CEI) formation with VC has received a lot less attention. This study presents a comprehensive investigation employing advanced in situ/operando-based Raman and X-ray absorption spectroscopy (XAS) to explore the effect of electrolyte composition on the CEI formation and suppression of surface reconstruction of LiNiMnCoO (NMC) cathodes.
View Article and Find Full Text PDF