Yu-Ting Tsai

This research aims to offer a deep learning-based diagnostic approach for hemorrhagic complications linked to patent ductus arteriosus (PDA) in preterm infants. Utilizing the You Only Look Once (YOLO) algorithm, this research analyzed five key cardiac parameters derived from echocardiographic ultrasonic waves: the left ventricular ejection time (LVET), left ventricular internal dimension at diastole (LVIDd), left ventricular internal dimension at systole (LVIDs), posterior wall thickness at end-systole (HES), and RR interval between two successive R-waves. The proposed ensemble model achieved best-in-class detection accuracies for each parameter, with rates of 97.56% (LVET), 88.69% (LVIDd), 99.50% (LVIDs), 82.29% (HES), and 81.15% (RR interval). Furthermore, assessment of cardiac function using derived indices—end-systolic wall stress (ESWS) and rate-corrected mean velocity of circumferential fiber shortening (mVcfc)—achieved mean accuracy rates of 82.33% and 90.16%, respectively. This approach enables physicians to accurately evaluate cardiac function in preterm infants and facilitates the diagnosis of PDA-related hemorrhagic complications.

Background/Objectives: For aging men experiencing lower urinary tract symptoms (LUTS), bladder diaries (BD) and uroflowmetry (UFM) are commonly used non-invasive diagnostic tools. However, bladder diaries often suffer from subjectivity and incomplete data, while traditional hospital-based uroflowmetry lacks convenience and repeatability. Therefore, there is a growing need for a user-friendly, artificial intelligence (AI)-powered at-home uroflow monitoring solution. This study aims to develop a novel, vibration-based home uroflowmetry system capable of recognizing uroflow curve patterns and measuring voiding parameters, and to compare its performance with other existing home-based uroflowmetry methods. Methods: Seventy-six male participants, all of whom provided informed consent, underwent uroflowmetry to assess voiding symptoms. An accelerometer affixed to the uroflowmeter’s urine container captured vibration signals, which were used to calculate the root mean square (RMS) values and maximum amplitude (Mmax). Simultaneously, the uroflowmeter recorded standard voiding parameters and generated uroflow curves. These vibration signals were then analyzed using a convolutional neural network (CNN) to classify six distinct uroflow curve patterns, aiding in diagnostic evaluation. Results: Seventy-six participants’ voiding volume ranged from 50 mL to 690 mL (median [Q1, Q3]: 160 [70.00, 212.50] mL). The correlation analysis revealed positive correlations between the vibration signals and voiding parameters, including the voided volume and RMS (R = 0.768, p < 0.001), Qmax and Mmax (R = 0.684, p < 0.001), voiding time and signal time (R = 0.838, p < 0.001), time to Qmax and time to Mmax (R = 0.477, p < 0.001). AI pattern recognition demonstrated high accuracy with all three indicators (precision, recall, and F1 score) surpassing 0.97. Conclusions: This AI-assisted vibration-based home uroflowmetry enables accurate voiding parameter measurement and uroflow pattern recognition, showing high precision, recall, and F1-score. It might offer a convenient solution for continuous and subjective bladder monitoring outside clinical settings.

Although uroflowmetry and bladder diaries are widely used for noninvasive evaluation of lower urinary tract symptoms, they still have limitations in diagnostic capability and users’ convenience. The aim of this paper is to discuss potential solutions by reviewing (1) the evolution and current clinical use of uroflowmetry and bladder diary, including clinical guidelines, daily practice applications, and their historical development; (2) a growing trend toward using home devices with various technologies; and (3) a comprehensive comparison of the strengths and weaknesses of these home devices. In our opinion, the following points can be highlighted: (1) the emerging trend of using home devices can enhance diagnostic capabilities through repeated measurements and the convenience of at-home testing and (2) home devices, which provide both frequency-volume and uroflowmetry information, have the potential to transform the management of lower urinary tract symptoms.

BACKGROUND With an aging population, patients complaining about low urinary tract symptoms (LUTS) increased year by year. For functional evaluation of low urinary tract (LUT), bladder diary (BD) and uroflowmetry (UFM) are both common non-invasive examinations for patients with LUTS. Voiding pattern of a patient is currently measured by hospital uroflowmetry and/or home bladder diaries. However, bladder diaries are less objective and often contain missed data, while hospital uroflowmetry lacks repeated measurements and convenience. Thus, it is important to develop a convenient and artificial intelligence(AI) based at-home uroflow monitoring. OBJECTIVE This study developed an innovative home vibration-based uroflowmetry for uroflow-curve pattern recognition and voiding parameters measurement and compared it with other home uroflowmetry. METHODS Seventy-six male participants with informed consents received uroflowmetry for voiding symptoms. An accelerometer attached on the urine bucket of the uroflowmeter detects vibration signals generating root mean square (RMS), maximal amplitude (Mmax) and the uroflowmeter measures voiding parameters and creates uroflow curves simultaneously. Vibration signals were processed with an artificial intelligence (AI) model (Convolution Neural Network) to recognize six patterns of uroflow curves to assist diagnosis. RESULTS Seventy-six participants’ voiding volume ranged from 50 ml to 690 ml (average: 192.50 ±155.58 ml). The correlation analysis revealed positive correlations between voided volume and RMS (R=0.768, p<.001), maximal flow rate (Qmax) and Mmax (R=0.684, p<.001), voiding time and signal time (R=0.838, p<.001), time to Qmax and time to Mmax (R=0.477, p<.001). AI pattern recognition demonstrated high accuracy with all three indicators (precision, recall, and F1 score) surpassing 0.97. CONCLUSIONS Usage of home uroflowmetry increases because of convenience, repeated measurement, and big data application. This vibration-based home uroflowmetry with AI assistance is feasible for at-home voiding parameters measurement and uroflow-curve pattern recognition. Compared with other technologies, vibration-based uroflowmetry demonstrates advantages for intuitive and contact-free usage of home uroflowmetry. CLINICALTRIAL The research protocol was approved by the institutional review board (IRB: 107-B-10-01).

UNSTRUCTURED Although uroflowmetry and bladder diaries are widely used for noninvasive evaluation of lower urinary tract symptoms, they still have limitations in diagnostic capability and users’ convenience. The aim of this paper is to discuss potential solutions by reviewing (1) the evolution and current clinical use of uroflowmetry and bladder diary, including clinical guidelines, daily practice applications, and their historical development; (2) a growing trend toward using home devices with various technologies; and (3) a comprehensive comparison of the strengths and weaknesses of these home devices. In our opinion, the following points can be highlighted: (1) the emerging trend of using home devices can enhance diagnostic capabilities through repeated measurements and the convenience of at-home testing and (2) home devices, which provide both frequency-volume and uroflowmetry information, have the potential to transform the management of lower urinary tract symptoms.

The healthcare industry has made significant progress in the diagnosis of heart conditions due to the use of intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that use artificial intelligence (AI) technology, such as convolutional neural networks (CNNs). Over the past few decades, methods for automated segmentation and classification of heart sounds have been widely studied. In many cases, both experimental and clinical data require electrocardiography (ECG)-labeled phonocardiograms (PCGs) or several feature extraction techniques from the mel-scale frequency cepstral coefficient (MFCC) spectrum of heart sounds to achieve better identification results with AI methods. Without good feature extraction techniques, the CNN may face challenges in classifying the MFCC spectrum of heart sounds. To overcome these limitations, we propose a capsule neural network (CapsNet), which can utilize iterative dynamic routing methods to obtain good combinations for layers in the translational equivariance of MFCC spectrum features, thereby improving the prediction accuracy of heart murmur classification. The 2016 PhysioNet heart sound database was used for training and validating the prediction performance of CapsNet and other CNNs. Then, we collected our own dataset of clinical auscultation scenarios for fine-tuning hyperparameters and testing results. CapsNet demonstrated its feasibility by achieving validation accuracies of 90.29% and 91.67% on the test dataset.

Deep learning techniques have revolutionized the field of artificial intelligence by enabling accurate predictions of complex natural scenarios. This paper proposes a novel convolutional neural network (CNN) model that involves deep learning technologies, such as the bottleneck residual block, layer normalization, and dropout layer, to predict wave overtopping at coastal structures under a wide range of conditions. To optimize the performance of the CNN model, the hyperparameter tuning process via Bayesian optimization is used. The results of validation demonstrate that the proposed CNN model is highly accurate in estimating wave overtopping discharge from hydraulic and structural parameters. The testing accuracy of the overtopping predictions using a prototype dataset shows that the proposed CNN model outperforms those existing machine learning models. An example application of the CNN model is presented for predicting prototype overtopping considering various crest freeboards of coastal structures.

In a clinical context, there are increasing numbers of people with voiding dysfunction. To date, the methods of monitoring the voiding status of patients have included voiding diary records at home or urodynamic examinations at hospitals. The former is less objective and often contains missing data, while the latter lacks frequent measurements and is an invasive procedure. In light of these shortcomings, this study developed an innovative and contact-free technique that assists in clinical voiding dysfunction monitoring and diagnosis. Vibration signals during urination were first detected using an accelerometer and then converted into the mel-frequency cepstrum coefficient (MFCC). Lastly, an artificial intelligence model combined with uniform manifold approximation and projection (UMAP) dimensionality reduction was used to analyze and predict six common patterns of uroflowmetry to assist in diagnosing voiding dysfunction. The model was applied to the voiding database, which included data from 76 males aged 30 to 80 who required uroflowmetry for voiding symptoms. The resulting system accuracy (precision, recall, and f1-score) was around 98% for both the weighted average and macro average. This low-cost system is suitable for at-home urinary monitoring and facilitates the long-term uroflow monitoring of patients outside hospital checkups. From a disease treatment and monitoring perspective, this article also reviews other studies and applications of artificial intelligence-based methods for voiding dysfunction monitoring, thus providing helpful diagnostic information for physicians.

With the advancement of industrial intelligence, defect recognition has become an indispensable part of facilitating surface quality in the steel manufacturing process. To assure product quality, most previous studies were typically trained with many defect samples. Nonetheless, a large quantity of defect samples is difficult to obtain, owing to the rare occurrence of defects. In general, deep learning-based methods underperformed as they have inherent limitations due to inadequate information, thereby restraining the application of models. In this study, a two-level Gaussian pyramid is applied to decompose raw data into different resolution levels simultaneously filtering the noises to acquire compact and representative features. Subsequently, a multi-receptive field fusion-based network (MRFFN) is developed to learn the hierarchical features and synthesize the respective prediction scores to form the final recognition result. As a result, the proposed method is capable of exhibiting an outstanding performance of 99.75% when trained using a lightweight dataset. In addition, the experiments conducted using the disturbance defect dataset showed the robustness of the proposed MRFFN against common noises and motion blur.