Signal quality assessment of peripheral venous pressure.

Develop a signal quality index (SQI) for the widely available peripheral venous pressure waveform (PVP). We focus on the quality of the cardiac component in PVP. We model PVP by the adaptive non-harmonic model. When the cardiac component in PVP is stronger, the PVP is defined to have a higher quality. This signal quality is quantified by applying the synchrosqueezing transform to decompose the cardiac component out of PVP, and the SQI is defined as a value between 0 and 1. A database collected during the lower body negative pressure experiment is utilized to validate the developed SQI. All signals are labeled into categories of low and high qualities by experts. A support vector machine (SVM) learning model is trained for practical purpose. The developed signal quality index coincide with human experts' labels with the area under the curve 0.95. In a leave-one-subject-out cross validation (LOSOCV), the SQI achieves accuracy 0.89 and F1 0.88, which is consistently higher than other commonly used signal qualities, including entropy, power and mean venous pressure. The trained SVM model trained with SQI, entropy, power and mean venous pressure could achieve an accuracy 0.92 and F1 0.91 under LOSOCV. An exterior validation of SQI achieves accuracy 0.87 and F1 0.92; an exterior validation of the SVM model achieves accuracy 0.95 and F1 0.96. The developed SQI has a convincing potential to help identify high quality PVP segments for further hemodynamic study. This is the first work aiming to quantify the signal quality of the widely applied PVP waveform.

Optimization of Using Multiple Machine Learning Approaches in Atrial Fibrillation Detection Based on a Large-Scale Data Set of 12-Lead Electrocardiograms: Cross-Sectional Study.

BACKGROUND: Atrial fibrillation (AF) represents a hazardous cardiac arrhythmia that significantly elevates the risk of stroke and heart failure. Despite its severity, its diagnosis largely relies on the proficiency of health care professionals. At present, the real-time identification of paroxysmal AF is hindered by the lack of automated techniques. Consequently, a highly effective machine learning algorithm specifically designed for AF detection could offer substantial clinical benefits. We hypothesized that machine learning algorithms have the potential to identify and extract features of AF with a high degree of accuracy, given the intricate and distinctive patterns present in electrocardiogram (ECG) recordings of AF. OBJECTIVE: This study aims to develop a clinically valuable machine learning algorithm that can accurately detect AF and compare different leads' performances of AF detection. METHODS: We used 12-lead ECG recordings sourced from the 2020 PhysioNet Challenge data sets. The Welch method was used to extract power spectral features of the 12-lead ECGs within a frequency range of 0.083 to 24.92 Hz. Subsequently, various machine learning techniques were evaluated and optimized to classify sinus rhythm (SR) and AF based on these power spectral features. Furthermore, we compared the effects of different frequency subbands and different lead selections on machine learning performances. RESULTS: The light gradient boosting machine (LightGBM) was found to be the most effective in classifying AF and SR, achieving an average F1-score of 0.988 across all ECG leads. Among the frequency subbands, the 0.083 to 4.92 Hz range yielded the highest F1-score of 0.985. In interlead comparisons, aVR had the highest performance (F1=0.993), with minimal differences observed between leads. CONCLUSIONS: In conclusion, this study successfully used machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs. The performance marked by an average F1-score of 0.988 and minimal interlead variation underscores the potential of machine learning algorithms to bolster real-time AF detection. This advancement could significantly improve patient care in intensive care units as well as facilitate remote monitoring through wearable devices, ultimately enhancing clinical outcomes.