Utilizing risk-controlling prediction calibration to reduce false alarm rates in epileptic seizure prediction.

Introduction: Epilepsy is a neurological disease characterized by sudden, unprovoked seizures. The unexpected nature of epileptic seizures is a major component of the disease burden. Predicting seizure onset and alarming patients may allow timely intervention, which would improve clinical outcomes and patient quality of life. Currently, algorithms aiming to predict seizures suffer from a high false alarm rate, rendering them unsuitable for clinical use. Methods: We adopted here a risk-controlling prediction calibration method called Learn then Test to reduce false alarm rates of seizure prediction. This method calibrates the output of a "black-box" model to meet a specified false alarm rate requirement. The method was initially validated on synthetic data and subsequently tested on publicly available electroencephalogram (EEG) records from 15 patients with epilepsy by calibrating the outputs of a deep learning model. Results and discussion: Validation showed that the calibration method rigorously controlled the false alarm rate at a user-desired level after our adaptation. Real data testing showed an average of 92% reduction in the false alarm rate, at the cost of missing four of nine seizures of six patients. Better-performing prediction models combined with the proposed method may facilitate the clinical use of real-time seizure prediction systems.

Double-sided asymmetric method for automated fetal heart rate baseline calculation.

The fetal heart rate (FHR) signal is used to assess the well-being of a fetus during labor. Manual interpretation of the FHR is subject to high inter- and intra-observer variability, leading to inconsistent clinical decision-making. The baseline of the FHR signal is crucial for its interpretation. An automated method for baseline determination may reduce interpretation variability. Based on this claim, we present the Auto-Regressed Double-Sided Improved Asymmetric Least Squares (ARDSIAsLS) method as a baseline calculation algorithm designed to imitate expert obstetrician baseline determination. As the FHR signal is prone to a high rate of missing data, a step of gap interpolation in a physiological manner was implemented in the algorithm. The baseline of the interpolated signal was determined using a weighted algorithm of two improved asymmetric least squares smoothing models and an improved symmetric least squares smoothing model. The algorithm was validated against a ground truth determined from annotations of six expert obstetricians. FHR baseline calculation performance of the ARDSIAsLS method yielded a mean absolute error of 2.54 bpm, a max absolute error of 5.22 bpm, and a root mean square error of 2.89 bpm. In a comparison between the algorithm and 11 previously published methods, the algorithm outperformed them all. Notably, the algorithm was non-inferior to expert annotations. Automating the baseline FHR determination process may help reduce practitioner discordance and aid decision-making in the delivery room.

Ca2+ pushes and pulls energetics to maintain ATP balance in atrial cells: computational insights.

To maintain atrial function, ATP supply-to-demand matching must be tightly controlled. Ca2+ can modulate both energy consumption and production. In light of evidence suggesting that Ca2+ affects energetics through "push" (activating metabolite flux and enzymes in the Krebs cycle to push the redox flux) and "pull" (acting directly on ATP synthase and driving the redox flux through the electron transport chain and increasing ATP production) pathways, we investigated whether both pathways are necessary to maintain atrial ATP supply-to-demand matching. Rabbit right atrial cells were electrically stimulated at different rates, and oxygen consumption and flavoprotein fluorescence were measured. To gain mechanistic insight into the regulators of ATP supply-to-demand matching in atrial cells, models of atrial electrophysiology, Ca2+ cycling and force were integrated with a model of mitochondrial Ca2+ and a modified model of mitochondrial energy metabolism. The experimental results showed that oxygen consumption increased in response to increases in the electrical stimulation rate. The model reproduced these findings and predicted that the increase in oxygen consumption is associated with metabolic homeostasis. The model predicted that Ca2+ must act both in "push" and "pull" pathways to increase oxygen consumption. In contrast to ventricular trabeculae, no rapid time-dependent changes in mitochondrial flavoprotein fluorescence were measured upon an abrupt change in workload. The model reproduced these findings and predicted that the maintenance of metabolic homeostasis is due to the effects of Ca2+ on ATP production. Taken together, this work provides evidence of Ca2+ "push" and "pull" activity to maintain metabolic homeostasis in atrial cells.

Visualizing and Quantifying Irregular Heart Rate Irregularities to Identify Atrial Fibrillation Events.

BACKGROUND: Screening the general public for atrial fibrillation (AF) may enable early detection and timely intervention, which could potentially decrease the incidence of stroke. Existing screening methods require professional monitoring and involve high costs. AF is characterized by an irregular irregularity of the cardiac rhythm, which may be detectable using an index quantifying and visualizing this type of irregularity, motivating wide screening programs and promoting the research of AF patient subgroups and clinical impact of AF burden. METHODS: We calculated variability, normality and mean of the difference between consecutive RR interval series (denoted as modified entropy scale-MESC) to quantify irregular irregularities. Based on the variability and normality indices calculated for long 1-lead ECG records, we created a plot termed a regularogram (RGG), which provides a visual presentation of irregularly irregular rates and their burden in a given record. To inspect the potency of these indices, they were applied to train and test a machine learning classifier to identify AF episodes in gold-standard, publicly available databases (PhysioNet) that include recordings from both patients with AF and/or other rhythm disturbances, and from healthy volunteers. The classifier was trained and validated on one database and tested on three other databases. RESULTS: Irregular irregularities were identified using normality, variability and mean MESC indices. The RGG displayed visually distinct differences between patients with vs. without AF and between patients with different levels of AF burden. Training a simple, explainable machine learning tool integrating these three indices enabled AF detection with 99.9% accuracy, when trained on the same person, and 97.8%, when trained on patients from a different database. Comparison to other RR interval-based AF detection methods that utilize signal processing, classic machine learning and deep learning techniques, showed superiority of our suggested method. CONCLUSION: Visualizing and quantifying irregular irregularities will be of value for both rapid visual inspection of long Holter recordings for the presence and the burden of AF, and for machine learning classification to identify AF episodes. A free online tool for calculating the indices, drawing RGGs and estimating AF burden, is available.

Automatic classification of healthy and disease conditions from images or digital standard 12-lead electrocardiograms.

Standard 12-lead electrocardiography (ECG) is used as the primary clinical tool to diagnose changes in heart function. The value of automated 12-lead ECG diagnostic approaches lies in their ability to screen the general population and to provide a second opinion for doctors. Yet, the clinical utility of automated ECG interpretations remains limited. We introduce a two-way approach to an automated cardiac disease identification system using standard digital or image 12-lead ECG recordings. Two different network architectures, one trained using digital signals (CNN-dig) and one trained using images (CNN-ima), were generated. An open-source dataset of 41,830 classified standard ECG recordings from patients and volunteers was generated. CNN-ima was trained to identify atrial fibrillation (AF) using 12-lead ECG digital signals and images that were also transformed to mimic mobile device camera-acquired ECG plot snapshots. CNN-dig accurately (92.9-100%) identified every possible combination of the eight most-common cardiac conditions. Both CNN-dig and CNN-ima accurately (98%) detected AF from standard 12-lead ECG digital signals and images, respectively. Similar classification accuracy was achieved with images containing smartphone camera acquisition artifacts. Automated detection of cardiac conditions in standard digital or image 12-lead ECG signals is feasible and may improve current diagnostic methods.