Publications by authors named "Pei-Hsin Chiu"
Objectives: This study aimed to predict mortality in children with pneumonia who were admitted to the intensive care unit (ICU) to aid decision-making.
Study Design: Retrospective cohort study conducted at a single tertiary hospital.
Patients: This study included children who were admitted to the pediatric ICU at the National Taiwan University Hospital between 2010 and 2019 due to pneumonia.
Article Synopsis
- Researchers created machine learning models to predict common respiratory pathogens in hospitalized children with acute respiratory infections (ARIs) using clinical data collected shortly after admission.
- The study analyzed 12,694 hospital admissions and identified critical features like age, fever, and blood test results that improved model accuracy for pathogens such as RSV, influenza, and adenovirus.
- The findings suggest that AI can enhance clinical decision-making by predicting ARI pathogens, potentially leading to better patient outcomes and cost savings in medical testing.
Physiological warmup plays an important role in reducing the injury risk in different sports. In response to the associated temperature increase, the muscle and tendon soften and become easily stretched. In this study, we focused on type I collagen, the main component of the Achilles tendon, to unveil the molecular mechanism of collagen flexibility upon slight heating and to develop a model to predict the strain of collagen sequences.
View Article and Find Full Text PDFArticle Synopsis
- - The study aimed to assess how well deep learning algorithms based on convolutional neural networks (CNN) can identify shoulder ultrasound images as either having or not having supraspinatus calcific tendinopathy (SSCT).
- - Researchers analyzed 133,619 ultrasound images from over 7,800 patients, with labeling done by experienced physiatrists to differentiate images with and without SSCT.
- - The CNN model, specifically DenseNet-121, showed high accuracy (91.32%) and effectiveness in diagnosing SSCT, outperforming simpler models, suggesting it could be a useful tool for doctors during ultrasound exams.
In order to accurately diagnose the health of high-order statically indeterminate structures, most existing structural health monitoring (SHM) methods require multiple sensors to collect enough information. However, comprehensive data collection from multiple sensors for high degree-of-freedom structures is not typically available in practice. We propose a method that reconciles the two seemingly conflicting difficulties.
View Article and Find Full Text PDF