HPC Framework for Performing in Silico Trials Using a 3D Virtual Human Cardiac Population as Means to Assess Drug-Induced Arrhythmic Risk.

Following the 3 R's principles of animal research-replacement, reduction, and refinement-a high-performance computational framework was produced to generate a platform to perform human cardiac in-silico clinical trials as means to assess the pro-arrhythmic risk after the administrations of one or combination of two potentially arrhythmic drugs. The drugs assessed in this study were hydroxychloroquine and azithromycin. The framework employs electrophysiology simulations on high-resolution three-dimensional, biventricular human heart anatomies including phenotypic variabilities, so as to determine if differential QT-prolongation responds to drugs as observed clinically. These simulations also reproduce sex-specific ionic channel characteristics. The derived changes in the pseudo-electrocardiograms, calcium concentrations, as well as activation patterns within 3D geometries were evaluated for signs of induced arrhythmia. The virtual subjects could be evaluated at two different cycle lengths: at a normal heart rate and at a heart rate associated with stress as means to analyze the proarrhythmic risks after the administrations of hydroxychloroquine and azithromycin. Additionally, a series of experiments performed on reanimated swine hearts utilizing Visible Heart® methodologies in a four-chamber working heart model were performed to verify the arrhythmic behaviors observed in the in silico trials.The obtained results indicated similar pro-arrhythmic risk assessments within the virtual population as compared to published clinical trials (21% clinical risk vs 21.8% in silico trial risk). Evidence of transmurally heterogeneous action potential prolongations after providing a large dose of hydroxychloroquine was found as the observed mechanisms for elicited arrhythmias, both in the in vitro and the in silico models. The proposed workflow for in silico clinical drug cardiotoxicity trials allows for reproducing the complex behavior of cardiac electrophysiology in a varied population, in a matter of a few days as compared to the months or years it requires for most in vivo human clinical trials. Importantly, our results provided evidence of the common phenotype variants that produce distinct drug-induced arrhythmogenic outcomes.

ECG Matching: An Approach to Synchronize ECG Datasets for Data Quality Comparisons.

Clinical assessment of newly developed sensors is important for ensuring their validity. Comparing recordings of emerging electrocardiography (ECG) systems to a reference ECG system requires accurate synchronization of data from both devices. Current methods can be inefficient and prone to errors. To address this issue, three algorithms are presented to synchronize two ECG time series from different recording systems: Binned R-peak Correlation, R-R Interval Correlation, and Average R-peak Distance. These algorithms reduce ECG data to their cyclic features, mitigating inefficiencies and minimizing discrepancies between different recording systems. We evaluate the performance of these algorithms using high-quality data and then assess their robustness after manipulating the R-peaks. Our results show that R-R Interval Correlation was the most efficient, whereas the Average R-peak Distance and Binned R-peak Correlation were more robust against noisy data.

Acute pulmonary embolism presenting with electrocardiographic signs and serum biomarkers of ST-segment elevation myocardial infarction: a case report.

Acute pulmonary embolism (APE) with ST-segment elevation and an upward T-wave is rare, and only a few cases have been reported to date. We herein present a case involving a man in his early 70s with an 8-hour history of dyspnea. Serial electrocardiography (ECG) demonstrated ST-segment elevation in leads V1 to V3 with an upward T-wave, laboratory tests revealed a high serum concentration of high-sensitivity cardiac troponin I, and signs of acute myocardial infarction were present. However, emergency coronary angiography revealed normal coronary arteries. A subsequent computed tomography scan of the pulmonary arteries showed findings consistent with APE. The patient's chest tightness was relieved after catheter-directed thrombolysis. Postoperative ECG showed that the ST-segment in leads V1 to V3 had fallen back and that the T-wave was inverted. The patient was discharged on rivaroxaban therapy. Clinically, the ECG findings of ST-segment elevation and an upward T-wave in APE can be easily misdiagnosed as acute myocardial infarction. Physicians should maintain clinical suspicion through risk stratification to identify APE.

Drivers' Mental Engagement Analysis Using Multi-Sensor Fusion Approaches Based on Deep Convolutional Neural Networks.

In this paper, we present a comprehensive assessment of individuals' mental engagement states during manual and autonomous driving scenarios using a driving simulator. Our study employed two sensor fusion approaches, combining the data and features of multimodal signals. Participants in our experiment were equipped with Electroencephalogram (EEG), Skin Potential Response (SPR), and Electrocardiogram (ECG) sensors, allowing us to collect their corresponding physiological signals. To facilitate the real-time recording and synchronization of these signals, we developed a custom-designed Graphical User Interface (GUI). The recorded signals were pre-processed to eliminate noise and artifacts. Subsequently, the cleaned data were segmented into 3 s windows and labeled according to the drivers' high or low mental engagement states during manual and autonomous driving. To implement sensor fusion approaches, we utilized two different architectures based on deep Convolutional Neural Networks (ConvNets), specifically utilizing the Braindecode Deep4 ConvNet model. The first architecture consisted of four convolutional layers followed by a dense layer. This model processed the synchronized experimental data as a 2D array input. We also proposed a novel second architecture comprising three branches of the same ConvNet model, each with four convolutional layers, followed by a concatenation layer for integrating the ConvNet branches, and finally, two dense layers. This model received the experimental data from each sensor as a separate 2D array input for each ConvNet branch. Both architectures were evaluated using a Leave-One-Subject-Out (LOSO) cross-validation approach. For both cases, we compared the results obtained when using only EEG signals with the results obtained by adding SPR and ECG signals. In particular, the second fusion approach, using all sensor signals, achieved the highest accuracy score, reaching 82.0%. This outcome demonstrates that our proposed architecture, particularly when integrating EEG, SPR, and ECG signals at the feature level, can effectively discern the mental engagement of drivers.

Monitoring Inattention in Construction Workers Caused by Physical Fatigue Using Electrocardiograph (ECG) and Galvanic Skin Response (GSR) Sensors.

Physical fatigue is frequent for heavy manual laborers like construction workers, but it causes distraction and may lead to safety incidents. The purpose of this study is to develop predictive models for monitoring construction workers' inattention caused by physical fatigue utilizing electrocardiograph (ECG) and galvanic skin response (GSR) sensors. Thirty participants were invited to complete an attention-demanding task under non-fatigued and physically fatigued conditions. Supervised learning algorithms were utilized to develop models predicting their attentional states, with heart rate variability (HRV) features derived from ECG signals and skin electric activity features derived from GSR signals as data inputs. The results demonstrate that using HRV features alone could obtain a prediction accuracy of 88.33%, and using GSR features alone could achieve an accuracy of 76.67%, both through the KNN algorithm. The accuracy increased to 96.67% through the SVM algorithm when combining HRV and GSR features. The findings indicate that ECG sensors used alone or in combination with GSR sensors can be applied to monitor construction workers' inattention on job sites. The findings would provide an approach for detecting distracted workers at job sites. Additionally, it might reveal the relationships between workers' physiological features and attention.

Combined Cardiac and Respiratory Monitoring from a Single Signal: A Case Study Employing the Fantasia Database.

This study proposes a novel method for obtaining the electrocardiogram (ECG) derived respiration (EDR) from a single lead ECG and respiration-derived cardiogram (RDC) from a respiratory stretch sensor. The research aims to reconstruct the respiration waveform, determine the respiration rate from ECG QRS heartbeat complexes data, locate heartbeats, and calculate a heart rate (HR) using the respiration signal. The accuracy of both methods will be evaluated by comparing located QRS complexes and inspiration maxima to reference positions. The findings of this study will ultimately contribute to the development of new, more accurate, and efficient methods for identifying heartbeats in respiratory signals, leading to better diagnosis and management of cardiovascular diseases, particularly during sleep where respiration monitoring is paramount to detect apnoea and other respiratory dysfunctions linked to a decreased life quality and known cause of cardiovascular diseases. Additionally, this work could potentially assist in determining the feasibility of using simple, no-contact wearable devices for obtaining simultaneous cardiology and respiratory data from a single device.

Quantitative identification of daily mental fatigue levels based on multimodal parameters.

Fatigue has become an important health problem in modern life; excessive mental fatigue may induce various cardiovascular diseases. Most current mental fatigue recognition is based only on specific scenarios and tasks. To improve the accuracy of daily mental fatigue recognition, this paper proposes a multimodal fatigue grading method that combines three signals of electrocardiogram (ECG), photoplethysmography (PPG), and blood pressure (BP). We collected ECG, PPG, and BP from 22 subjects during three time periods: morning, afternoon, and evening. Based on these three signals, 56 characteristic parameters were extracted from multiple dimensions, which comprehensively covered the physiological information in different fatigue states. The extracted parameters were compared with the feature optimization ability of recursive feature elimination (RFE), maximal information coefficient, and joint mutual information, and the optimum feature matrix selected was input into random forest (RF) for a three-level classification. The results showed that the accuracy of classification of fatigue using only one physiological feature was 88.88%, 92.72% using a combination of two physiological features, and 94.87% using all three physiological features. This study indicates that the fusion of multiple physiological traits contains more comprehensive information and better identifies the level of mental fatigue, and the RFE-RF model performs best in fatigue identification. The BP variability index is useful for fatigue classification.

Electrocardiographic Morphology-Voltage-P-Wave-Duration (MVP) Score to Select Patients for Continuous Atrial Fibrillation Screening to Prevent Stroke.

Morphology-voltage-P-wave-duration (MVP) score combining P-wave duration (PWD), P-wave voltage in lead I (PWVI), and interatrial block (IAB) has been demonstrated to predict atrial fibrillation (AF). Therefore, this study aimed to examine MVP score and its P-wave components as potential predictors of AF screening effects on stroke prevention. This was a secondary analysis of the LOOP Study (Atrial Fibrillation detected by Continuous ECG Monitoring using Implantable Loop Recorder to prevent Stroke in High-risk Individuals) which randomized older persons (aged 70 to 90 years) with additional stroke risk factors to either continuous monitoring with implantable loop recorder and anticoagulation upon detection of AF episodes ≥6 minutes (the intervention group), or usual care. A total of 5,759 participants were included in the present analysis, where PWD, PWVI, and IAB were determined through a computerized analysis of 12-lead electrocardiogram and further employed to calculate baseline MVP score (0 to 6) for each participant. In total, 305 (5.3%) had stroke or systemic embolism during follow-up, with a higher risk in the group with MVP score 5 to 6 than those having score 0 to 2 (hazard ratio (HR) 1.54 [95% confidence interval (CI) 1.01 to 2.35]). This risk increase was mainly upheld by participants with IAB (HR 1.62 [95% CI 1.11 to 2.36] for IAB vs no IAB) and with longer PWD (HR 1.37 [95% CI 1.07 to 1.75] for >110 vs ≤110 ms). Compared with usual care, implantable loop recorder screening did not significantly reduce the risk of stroke or systemic embolism in any MVP risk categories (HR 0.80 [95% CI 0.60 to 1.08] for MVP score 0 to 2, 0.54 [95% CI 0.16 to 1.85] for MVP score 3 to 4, and 0.89 [95% CI 0.35 to 2.25] for MVP score 5 to 6; pinteraction = 0.78). In conclusion, a higher MVP score was associated with an increased stroke risk, but it did not demonstrate an association with effects of AF screening on stroke prevention. These findings should be considered hypothesis-generating and warrant further study.

As artificial intelligence goes multimodal, medical applications multiply.

Machines don't have eyes, but you wouldn't know that if you followed the progression of deep learning models for accurate interpretation of medical images, such as x-rays, computed tomography (CT) and magnetic resonance imaging (MRI) scans, pathology slides, and retinal photos. Over the past several years, there has been a torrent of studies that have consistently demonstrated how powerful "machine eyes" can be, not only compared with medical experts but also for detecting features in medical images that are not readily discernable by humans. For example, a retinal scan is rich with information that people can't see, but machines can, providing a gateway to multiple aspects of human physiology, including blood pressure; glucose control; risk of Parkinson's, Alzheimer's, kidney, and hepatobiliary diseases; and the likelihood of heart attacks and strokes. As a cardiologist, I would not have envisioned that machine interpretation of an electrocardiogram would provide information about the individual's age, sex, anemia, risk of developing diabetes or arrhythmias, heart function and valve disease, kidney, or thyroid conditions. Likewise, applying deep learning to a pathology slide of tumor tissue can also provide insight about the site of origin, driver mutations, structural genomic variants, and prognosis. Although these machine vision capabilities for medical image interpretation may seem impressive, they foreshadow what is potentially far more expansive terrain for artificial intelligence (AI) to transform medicine. The big shift ahead is the ability to transcend narrow, unimodal tasks, confined to images, and broaden machine capabilities to include text and speech, encompassing all input modes, setting the foundation for multimodal AI.

Assessment of real-time electrocardiogram effects on interpretation quality by emergency physicians.

BACKGROUND: Electrocardiogram (ECG) is one of the most commonly performed examinations in emergency medicine. The literature suggests that one-third of ECG interpretations contain errors and can lead to clinical adverse outcomes. The purpose of this study was to assess the quality of real-time ECG interpretation by senior emergency physicians compared to cardiologists and an ECG expert. METHODS: This was a prospective study in two university emergency departments and one emergency medical service. All ECGs were performed and interpreted over five weeks by a senior emergency physician (EP) and then by a cardiologist using the same questionnaire. In case of mismatch between EP and the cardiologist our expert had the final word. The ratio of agreement between both interpretations and the kappa (k) coefficient characterizing the identification of major abnormalities defined the reading ability of the emergency physicians. RESULTS: A total of 905 ECGs were analyzed, of which 705 (78%) resulted in a similar interpretation between emergency physicians and cardiologists/expert. However, the interpretations of emergency physicians and cardiologists for the identification of major abnormalities coincided in only 66% (k: 0.59 (95% confidence interval (CI): 0.54-0.65); P-value = 1.64e-92). ECGs were correctly classified by emergency physicians according to their emergency level in 82% of cases (k: 0.73 (95% CI: 0.70-0.77); P-value ≈ 0). Emergency physicians correctly recognized normal ECGs (sensitivity = 0.91). CONCLUSION: Our study suggested gaps in the identification of major abnormalities among emergency physicians. The initial and ongoing training of emergency physicians in ECG reading deserves to be improved.

Artificial intelligence-enhanced electrocardiography for early assessment of coronavirus disease 2019 severity.

Despite challenges in severity scoring systems, artificial intelligence-enhanced electrocardiography (AI-ECG) could assist in early coronavirus disease 2019 (COVID-19) severity prediction. Between March 2020 and June 2022, we enrolled 1453 COVID-19 patients (mean age: 59.7 ± 20.1 years; 54.2% male) who underwent ECGs at our emergency department before severity classification. The AI-ECG algorithm was evaluated for severity assessment during admission, compared to the Early Warning Scores (EWSs) using the area under the curve (AUC) of the receiver operating characteristic curve, precision, recall, and F1 score. During the internal and external validation, the AI algorithm demonstrated reasonable outcomes in predicting COVID-19 severity with AUCs of 0.735 (95% CI: 0.662-0.807) and 0.734 (95% CI: 0.688-0.781). Combined with EWSs, it showed reliable performance with an AUC of 0.833 (95% CI: 0.830-0.835), precision of 0.764 (95% CI: 0.757-0.771), recall of 0.747 (95% CI: 0.741-0.753), and F1 score of 0.747 (95% CI: 0.741-0.753). In Cox proportional hazards models, the AI-ECG revealed a significantly higher hazard ratio (HR, 2.019; 95% CI: 1.156-3.525, p = 0.014) for mortality, even after adjusting for relevant parameters. Therefore, application of AI-ECG has the potential to assist in early COVID-19 severity prediction, leading to improved patient management.

"Profiles of motor competence and its perception accuracy among children: Association with physical fitness and body fat".

The main goals of this study were to identify profiles in school-aged children based on actual Motor Competence (MC) and accuracy of Perceived Motor Competence (PMC) and to examine how children with different profiles differ in terms of Physical Fitness (PF) and Body Fat percentage (BF%). The MC of a total of 287 children (51.6% boys, aged between 6 and 10 years-old) was assessed using the Motor Competence Assessment (MCA) instrument, and the accuracy of the PMC was measured using motor tasks (standing long jump, throwing, kicking, and walking backwards). PF and BF% were assessed using the 20m shuttle run test and TANITA, respectively. Cluster (C) analysis revealed four profiles, two of which were aligned - high MC-accurate PMC (C4) and low-inaccurate (C2), and two that were non-aligned - high-inaccurate (C1) and low-accurate (C3). Children in C4 performed better on PF and had less BF% than children in C3 and C2.

[Electrocardiogram classification algorithm based on CvT-13 and multimodal image fusion].

Electrocardiogram (ECG) signal is an important basis for the diagnosis of arrhythmia and myocardial infarction. In order to further improve the classification effect of arrhythmia and myocardial infarction, an ECG classification algorithm based on Convolutional vision Transformer (CvT) and multimodal image fusion was proposed. Through Gramian summation angular field (GASF), Gramian difference angular field (GADF) and recurrence plot (RP), the one-dimensional ECG signal was converted into three different modes of two-dimensional images, and fused into a multimodal fusion image containing more features. The CvT-13 model could take into account local and global information when processing the fused image, thus effectively improving the classification performance. On the MIT-BIH arrhythmia dataset and the PTB myocardial infarction dataset, the algorithm achieved a combined accuracy of 99.9% for the classification of five arrhythmias and 99.8% for the classification of myocardial infarction. The experiments show that the high-precision computer-assisted intelligent classification method is superior and can effectively improve the diagnostic efficiency of arrhythmia as well as myocardial infarction and other cardiac diseases.

ECG and EEG based detection and multilevel classification of stress using machine learning for specified genders: A preliminary study.

Mental health, especially stress, plays a crucial role in the quality of life. During different phases (luteal and follicular phases) of the menstrual cycle, women may exhibit different responses to stress from men. This, therefore, may have an impact on the stress detection and classification accuracy of machine learning models if genders are not taken into account. However, this has never been investigated before. In addition, only a handful of stress detection devices are scientifically validated. To this end, this work proposes stress detection and multilevel stress classification models for unspecified and specified genders through ECG and EEG signals. Models for stress detection are achieved through developing and evaluating multiple individual classifiers. On the other hand, the stacking technique is employed to obtain models for multilevel stress classification. ECG and EEG features extracted from 40 subjects (21 females and 19 males) were used to train and validate the models. In the low&high combined stress conditions, RBF-SVM and kNN yielded the highest average classification accuracy for females (79.81%) and males (73.77%), respectively. Combining ECG and EEG, the average classification accuracy increased to at least 87.58% (male, high stress) and up to 92.70% (female, high stress). For multilevel stress classification from ECG and EEG, the accuracy for females was 62.60% and for males was 71.57%. This study shows that the difference in genders influences the classification performance for both the detection and multilevel classification of stress. The developed models can be used for both personal (through ECG) and clinical (through ECG and EEG) stress monitoring, with and without taking genders into account.

Cardiac hydatid disease; a systematic review.

BACKGROUND AND OBJECTIVES: Human cystic echinococcosis (CE), is a common health problem in low- and middle-income countries. Cardiac involvement is a relatively rare manifestation of Echinococcus infection. This study aims to summarize the evidence regarding the features of cardiac CE. METHODS: Case series of the patients with cardiac CE, were included in this study. Non-English papers, case reports, reviews, letters, , commentaries, and conference abstracts were not included. A systematic search was conducted in PubMed and EMBASE databases and the risk of bias in the included studies was assessed using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist. RESULTS: Out of 3985 results of the searches, finally 37 studies were included in this systematic review. Based on available evidence, cardiac involvement is an uncommon but serious presentation of CE which presents with some non-specific signs and symptoms. Dyspnea, chest pain, and palpitation are the most common symptoms of the disease and normal sinus rhythm is the most common Electrocardiogram (ECG) feature. The disease is not associated with high mortality in case of timely diagnosis and appropriate management. DISCUSSION: Consecutive and complete inclusion of participants, statistical analysis, and appropriate reporting of the demographics were the sources of bias in the included studies. The exclusion of non-English papers was a limitation during the review process. FUNDING: The research protocol was approved and supported by the Student Research Committee, Tabriz University of Medical Sciences (grant number: 69380). REGISTRATION: This study was registered in the International prospective register of systematic reviews (PROSPERO ID: CRD42022381204).

Nitrogen-Phosphorus-Potassium containing liquid fertilizer intoxication presenting with extreme hyperkalemia, metabolic acidosis and ECG changes.

Liquid fertilizers are widely used for fertilizing in- and outdoor vegetation. Despite the easy accessibility and widespread use, serious intoxications are rare. This case report describes a 61-year-old woman who was treated for life-threatening hyperkalemia, metabolic acidosis and ECG changes after intentional ingestion of liquid fertilizer. Our case shows that intake of liquid fertilizer, though infrequent, can cause serious, life threatening complications.

Static electricity-based motion artifact-free electrocardiography with novel Ti3C2Tx MXene/Ag nanowire/polymer hybrid dry electrodes.

With wearable devices featuring electrocardiogram (ECG) capabilities increasingly common, demand for accurate, simple ECG measurements has escalated. Although single-lead ECGs, which capture real-time heart rate and rhythm, are typically used in such devices, they encounter challenges related to the device-skin contact state, complicating serious heart disease prediction. While 12-lead ECGs provide superior measurements, they require wet electrodes, which are unsuitable for long-term use due to skin irritation and signal degradation over time. Dry electrodes have been explored as a potential resolution to this issue, yet they necessitate a substantial conductive surface area coupled with a stable contact to achieve low contact impedance with the skin. For the first time, we hereby propose a novel approach that simultaneously addresses the exigencies for substantial conductive surface coverage and remarkable contact stability, facilitating an ECG free from motion artifacts. The electrodes we propose are constituted by silver nanowires (AgNWs) entrenched beneath the surface of a polymer film, thereby displaying superior mechanical flexibility and lateral electrical conductivity. To counterbalance the restricted surface coverage of the embedded AgNW electrode, we integrated Ti3C2-based MXene nanosheets on the surface, thereby significantly enhancing the conductive coverage of the electrode surface. The electrostatic interaction between the functional groups on the MXene nanosheets' surface and the positively charged human skin facilitates spontaneous contact, yielding stable contact and diminished vulnerability to motion artifacts. This novel electrode design holds considerable potential for the long-term monitoring of cardiac health, offering signal quality superior to that of existing wet and dry electrodes.

A randomized trial: The safety, pharmacokinetics and preliminary pharmacodynamics of ropivacaine oil delivery depot in healthy subjects.

INTRODUCTION: Ropivacaine oil delivery depot (RODD) can slowly release ropivacaine and block nerves for a long timejavascript:;. The aim of the present work was to investigate the safety, pharmacokinetics, and preliminary pharmacodynamics of RODD in subcutaneous injection among healthy subjects. METHODS: The abdomens of 3 subjects were subcutaneously administered with a single-needle RODD containing 12~30 mg of ropivacaine. The irritation, nerve blocking range and optimum dose were investigated. Forty-one subjects were divided into RODD groups containing 150, 230, 300, 350 and 400 mg of ropivacaine and a ropivacaine hydrochloride injection (RHI) 150 mg group. Multineedle subcutaneous injection of RODD or RHI was performed in the abdomens of the subjects. The primary endpoint was a safe dose or a maximum dose of ropivacaine (400 mg). Subjects' vital signs were observed; their blood was analyzed; their cardiovascular system and nervous systems were monitored, and their dermatological reactions were observed and scored. Second, the ropivacaine concentrations in plasma were determined, pharmacokinetic parameters were calculated, and the anesthetic effects of RODD were studied, including RODD onset time, duration and intensity of nerve block. RESULTS: Single-needle injection of RODD 24 mg was optimal for 3 subjects, and the range of nerve block was 42.5±20.8 mm. Multineedle subcutaneous injection of RODD in the abdomens of subjects was safe, and all adverse events were no more severe than grade II. The incidence rate of grade II adverse events, such as pain, and abnormal ST and ST-T segment changes on electrocardiography, was approximately 1%. The incidence rate of grade I adverse events, including erythema, papules, hypertriglyceridemia, and hypotension was greater than 10%. Erythema and papules were relieved after 24 h and disappeared after 72 h. Other adverse reactions disappeared after 7 days. The curve of ropivacaine concentration-time in plasma presented a bimodal profile. The results showed that ropivacaine was slowly released from the RODD. Compared with the 150 mg RHI group, Tmax was longer in the RODD groups. In particular, Tmax in the 400 mg RODD group was longer than that in the RHI group (11.8±4.6 h vs. 0.77±0.06 h). The Cmax in the 150 mg RODD group was lower than that in the 150 mg RHI group (0.35±0.09 vs. 0.58±0.13 µg·mL-1). In particular, the Cmax increased by 48% when the dose was increased by 2.6 times in the 400 mg group. Cmax, the AUC value and the intensity of the nerve block increased with increasing doses of RODD. Among them, the 400 mg RODD group presented the strongest nerve block (the percentage of level 2 and 3, 42.9%). The corresponding median onset time was 0.42 h, and the duration median was 35.7⁓47.7 h. CONCLUSIONS: RODD has a sustained release effect. Compared with the RHI group, Tmax was delayed in the RODD groups, and the duration of nerve block was long. No abnormal reaction was found in the RODD group containing 400 mg of ropivacaine after subcutaneous injection among healthy subjects, suggesting that RODD was adequately safe. TRIAL REGISTRATION: Chictr.org: CTR2200058122; Chinadrugtrials.org: CTR20192280.

SelANet: decision-assisting selective sleep apnea detection based on confidence score.

BACKGROUND: One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of labor, cost, and time. Therefore, studies have been conducted to develop automated detection algorithms using limited biological signals that can be more easily diagnosed. However, the lack of information from limited signals can result in uncertainty from artificial intelligence judgments. Therefore, we performed selective prediction by using estimated respiratory signals from electrocardiogram and oxygen saturation signals based on confidence scores to classify only those sleep apnea occurrence samples with high confidence. In addition, for samples with high uncertainty, this algorithm rejected them, providing a second opinion to the clinician. METHOD: Our developed model utilized polysomnography data from 994 subjects obtained from Massachusetts General Hospital. We performed feature extraction from the latent vector using the autoencoder. Then, one dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was designed and trained to measure confidence scores for input, with an additional selection function. We set a confidence score threshold called the target coverage and performed optimization only on samples with confidence scores higher than the target coverage. As a result, we demonstrated that the empirical coverage trained in the model converged to the target coverage. RESULT: To confirm whether the model has been optimized according to the objectives, the coverage violation was used to measure the difference between the target coverage and the empirical coverage. As a result, the value of coverage violation was found to be an average of 0.067. Based on the model, we evaluated the classification performance of sleep apnea and confirmed that it achieved 90.26% accuracy, 91.29% sensitivity, and 89.21% specificity. This represents an improvement of approximately 7.03% in all metrics compared to the performance achieved without using a selective prediction. CONCLUSION: This algorithm based on selective prediction utilizes confidence measurement method to minimize the problem caused by limited biological information. Based on this approach, this algorithm is applicable to wearable devices despite low signal quality and can be used as a simple detection method that determine the need for polysomnography or complement it.