A noninvasive and unconstrained real-time method to detect the respiration rhythm and pulse rate during sleep is presented. By employing the agrave trous algorithm of the wavelet transformation (WT), the respiration rhythm and pulse rate can be monitored in real-time from a pressure signal acquired with a pressure sensor placed under a pillow. The waveform for respiration rhythm detection is derived from the 2⁶ scale approximation, while that for pulse rate detection is synthesized by combining the 2⁴ and 2⁵ scale details. To minimize the latency in data processing and realize the highest real-time performance, the respiration rhythm and pulse rate are estimated by using waveforms directly derived from the WT approximation and detail components without the reconstruction procedure. This method is evaluated with data collected from 13 healthy subjects. By comparing with detections from finger photoelectric plethysmograms used for pulse rate detection, the sensitivity and positive predictivity were 99.17% and 98.53%, respectively. Similarly, for respiration rhythm, compared with detections from nasal thermistor signals, results were 95.63% and 95.42%, respectively. This study suggests that the proposed method is promising to be used in a respiration rhythm and pulse rate monitor for real-time monitoring of sleep-related diseases during sleep

The conventional zero-heat-flow thermometer, which measures the deep body temperature from the skin surface, is widely used at present. However, this thermometer requires considerable electricity to power the electric heater that compensates for heat loss from the probe; thus, AC power is indispensable for its use. Therefore, this conventional thermometer is inconvenient for unconstrained monitoring. We have developed a new dual-heat-flux method that can measure the deep body temperature from the skin surface without a heater. Our method is convenient for unconstrained and long-term measurement because the instrument is driven by a battery and its design promotes energy conservation. Its probe consists of dual-heat-flow channels with different thermal resistances, and each heat-flow-channel has a pair of IC sensors attached on its top and bottom. The average deep body temperature measurements taken using both the dual-heat-flux and then the zero-heat-flow thermometers from the foreheads of 17 healthy subjects were 37.08 degrees C and 37.02 degrees C, respectively. In addition, the correlation coefficient between the values obtained by the 2 methods was 0.970 (p<0.001). These results show that our method can be used for monitoring the deep body temperature as accurately as the conventional method, and it overcomes the disadvantage of the necessity of AC power supply.

Obstructive sleep apnea (OSA) is a common chronic sleep disorder that disrupts breathing during sleep and is associated with many other medical conditions, including hypertension, coronary heart disease, and depression. Clinically, the standard for diagnosing OSA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of OSA diagnosis in public health sectors. Therefore, electrocardiogram (ECG)-based methods for OSA detection have been proposed to automate the polysomnography procedure and reduce its discomfort. So far, most of the proposed approaches rely on feature engineering, which calls for advanced expert knowledge and experience. This paper proposes a novel fused-image-based technique that detects OSA using only a single-lead ECG signal. In the proposed approach, a convolutional neural network extracts features automatically from images created with one-minute ECG segments. The proposed network comprises 37 layers, including four residual blocks, a dense layer, a dropout layer, and a soft-max layer. In this study, three time–frequency representations, namely the scalogram, the spectrogram, and the Wigner–Ville distribution, were used to investigate the effectiveness of the fused-image-based approach. We found that blending scalogram and spectrogram images further improved the system’s discriminative characteristics. Seventy ECG recordings from the PhysioNet Apnea-ECG database were used to train and evaluate the proposed model using 10-fold cross validation. The results of this study demonstrated that the proposed classifier can perform OSA detection with an average accuracy, recall, and specificity of 92.4%, 92.3%, and 92.6%, respectively, for the fused spectral images.

Flexible endoscopic evaluation of swallowing (FEES) is considered the gold standard in diagnosing oropharyngeal dysphagia. Recent advances in deep learning have led to a resurgence of artificial intelligence-assisted computer-aided diagnosis (AI-assisted CAD) for a variety of applications. AI-assisted CAD would be a remarkable benefit in providing medical services to populations with inadequate access to dysphagia experts, especially in aging societies. This paper presents an AI-assisted CAD named FEES-CAD for aspiration and penetration detection on video recording during FEES. FEES-CAD segments the input FEES video and classifies penetration, aspiration, residue in the vallecula, and residue in the hypopharynx based on the segmented FEES video. We collected and annotated FEES videos from 199 patients to train the network and tested the performance of FEES-CAD using FEES videos from other 40 patients. These patients consecutively underwent FEES between December 2016 and August 2019 at Fukushima Medical University Hospital. FEES videos were deidentified, randomized, and rated by FEES-CAD and laryngologists with over 15 years of experience in performing FEES. FEES-CAD achieved an average Dice similarity coefficient of 98.6 $$\%$$% . FEES-CAD achieved expert-level accuracy performance on penetration (92.5 $$\%$$% ), aspiration (92.5 $$\%$$% ), residue in the vallecula (100 $$\%$$% ), and residue in the hypopharynx (87.5 $$\%$$% ) classification tasks. To the best of our knowledge, FEES-CAD is the first CNN-based system that achieves expert-level performance in detecting aspiration and penetration.

The electrocardiogram (ECG) is widely used for cardiovascular disease diagnosis and daily health monitoring. Before ECG analysis, ECG quality screening is an essential but time-consuming and experience-dependent work for technicians. An automatic ECG quality assessment method can reduce unnecessary time loss to help cardiologists perform diagnosis. This study aims to develop an automatic quality assessment system to search qualified ECGs for interpretation. The proposed system consists of data augmentation and quality assessment parts. For data augmentation, we train a conditional generative adversarial networks model to get an ECG segment generator, and thus to increase the number of training data. Then, we pre-train a deep quality assessment model based on a training dataset composed of real and generated ECG. Finally, we fine-tune the proposed model using real ECG and validate it on two different datasets composed of real ECG. The proposed system has a generalized performance on the two validation datasets. The model’s accuracy is 97.1% and 96.4%, respectively for the two datasets. The proposed method outperforms a shallow neural network model, and also a deep neural network models without being pre-trained by generated ECG. The proposed system demonstrates improved performance in the ECG quality assessment, and it has the potential to be an initial ECG quality screening tool in clinical practice.