DSpace Collection:

Ocular Torticollis Detection and Management Based on OpenPose

Mon, 01 Jan 2024 00:00:00 GMT

Title: Ocular Torticollis Detection and Management Based on OpenPose Authors: Tsai, Jia-Yi; Chen, Heng-Shuen; Yang, Wen-Chieh; SU, MEI-JU Abstract: Due to the frequent use of 3C products (Computers, Communications, and Consumer Electronics), the issue of vision problems is becoming increasingly severe. It is important for preschoolers' vision to improve, which is why the period before the age of 8 is considered the golden corrective period. Early stage strabismus is not easily detected and is often overlooked. Strabismus can cause patients to excessively rely on one eye, leading to the gradual development of 'lazy eye,' also known as amblyopia. Utilizing OpenPose, a model for pose estimation and face landmark detection, this system aims to analyze facial landmarks and upper-body joints. Its primary goal is to develop a non-invasive solution for the detection and correction of strabismus. The study adopted a computer camera to capture real-time eye-head behavior data. The system can detect abnormal torticollis or unconscious overreliance on one eye, which is a big issue when using a computer or smartphone. Our system could assist ophthalmologists in diagnosing cases of congenital amblyopia in preschoolers and individuals with strabismus. It not only provides the early detection of strabismus for preschooler children but also prevents the vision problem from getting more serious. Therefore, the system will improve remote precision vision care. Traditional strabismus assessment manually in the clinic by physicians, not at home by the patient himself. In rural areas, the medical resources are limited, especially few ophthalmologists. Therefore, our system provides support to medically underserved areas by rural area telemedicine, vision tracking and monitoring.

Ehnhancing Antibiotic Stewardship with Power BI Visualization Dashboards: A User Experience Evaluation

Mon, 01 Jan 2024 00:00:00 GMT

Title: Ehnhancing Antibiotic Stewardship with Power BI Visualization Dashboards: A User Experience Evaluation Authors: Hung, Ka Yee; SU, MEI-JU; Lee, Ya Chi Abstract: As patient numbers rise, managing antibiotic usage and adhering to Antimicrobial Stewardship Program (ASP) guidelines becomes increasingly challenging for healthcare professionals. This study integrates Power BI with Clinical Decision Support Systems (CDSS) to create an Antibiotic Utilization Dashboard, transforming Electronic Health Records (EHR) data into actionable insights. By standardizing data and using interactive visualizations, the dashboard enhances quick-response decision-making, tracks antibiotic trends, and monitors resistance patterns. A five-year dataset was processed in Python and visualized with Power BI, yielding a tool that supports ASP compliance. User feedback via the User Experience Questionnaire (UEQ) showed strengths in Attractiveness and Efficiency but noted security as an area for improvement. To address this, future work includes transitioning the database to MySQL for better data security. This system offers a valuable approach to improving antibiotic stewardship in healthcare settings.

Dysfunction in sensorimotor and default mode networks in major depressive disorder with insights from global brain connectivity

Mon, 01 Jan 2024 00:00:00 GMT

Title: Dysfunction in sensorimotor and default mode networks in major depressive disorder with insights from global brain connectivity Authors: Zhang, Yajuan; Huang, Chu-Chung; Zhao, Jiajia; Liu, Yuchen; Xia, Mingrui; Wang, Xiaoqin; Wei, Dongtao; Chen, Yuan; Liu, Bangshan; Zheng, Yanting; Wu, Yankun; Chen, Taolin; Cheng, Yuqi; Xu, Xiufeng; Gong, Qiyong; Si, Tianmei; Qiu, Shijun; Cheng, Jingliang; Tang, Yanqing; Wang, Fei; Qiu, Jiang; Xie, Peng; Li, Lingjiang; He, Yong; Lin, Ching-Po; DIDA-Major Depressive Disorder Working Grp, Chun-Yi Zac; Lo, Chun-Yi Zac Abstract: Major depressive disorder (MDD) is recognized as a severe mental illness with imbalanced interactions among brain networks. However, the detailed mechanisms of large-scale network dysfunction and their clinical implications are not fully understood. To explore the neurological basis of altered connectivity within the brain, the current case-control study aimed to examine large-scale connectivity coherence in MDD using resting-state functional magnetic resonance imaging data from 1,148 individuals with MDD and 1,079 healthy volunteers across nine research centers. Global brain connectivity (GBC) was estimated and compared between groups. Compared with healthy volunteers, individuals with MDD had decreased GBC in sensorimotor/visual networks and increased GBC mainly in default mode networks (DMNs) (voxel-level P < 0.001, cluster-level P < 0.05). These main findings were consistent across different clinical states of MDD, indicating their independence from clinical factors (P < 0.05, FDR-corrected). Further seed connectivity revealed that individuals with MDD had heightened connectivity between DMNs and primary sensory cortices, but reduced connectivity within primary sensory cortices (voxel-level P < 0.001, cluster-level P < 0.05). The findings suggest a network imbalance toward the DMNs at the expense of the sensorimotor/visual networks in individuals with MDD experiencing a depressive episode. These alterations, involving both higher-order cognitive systems and low-level sensory systems, could provide insights into understanding the multifaceted clinical and cognitive deficits observed in MDD.

Automated sleep apnea detection from snoring and carotid pulse signals using an innovative neck wearable piezoelectric sensor

Wed, 01 Jan 2025 00:00:00 GMT

Title: Automated sleep apnea detection from snoring and carotid pulse signals using an innovative neck wearable piezoelectric sensor Authors: Chao, Yi-Ping; Chuang, Hai-Hua; Lo, Yu-Lun; Huang, Shu-Yi; Zhan, Wan-Ting; Lee, Guo-She; Li, Hsueh-Yu; Shyu, Liang-Yu; Lee, Li-Ang Abstract: This study introduces an innovative wearable neck piezoelectric sensor (NPS) that measures snoring vibrations and carotid pulsations, offering a significant advancement in sleep apnea syndrome (SAS) diagnosis. Utilizing advanced algorithms like discrete wavelet transform and dynamic thresholding, the NPS detects snoring events with 83% accuracy, comparable to polysomnography, and calculates key metrics such as the snoring index (SI) and normalized snoring vibration energy (SVE%). Unlike traditional methods, the SVE% from NPS directly correlates with subjective assessments of snoring severity. It also measures carotid pulsation metrics such as pulse rate and the standard deviation of normal-to-normal intervals, achieving 85% accuracy in sleep phase determination against polysomnography. Moreover, NPS surpasses traditional methods in SI and SVE% accuracy, closely aligning with clinical evaluations of SAS severity. This user-friendly technology automates the measurement of critical snoring metrics, transforming SAS diagnosis and treatment by enhancing accessibility and efficiency for healthcare providers and patients.