Chest X-ray for Clinical Evaluation

This study investigates if single lung ventilation on cardiopulmonary bypass can mitigate postoperative lung water accumulation determined by lung ultrasound in the ventilated lung as compared to the non-ventilated lung in patients at high-risk for developing severe pulmonary complications after cardiac surgery.

Congenital heart disease (CHD) is a common condition affecting newborns that can be serious if not caught early. While echocardiograms are the best way to diagnose CHD, they are not always immediately available. Chest X-rays are widely available and are often the first test used when a newborn has breathing problems, a heart murmur, or a bluish skin tint. The purpose of this study is to determine how accurate standard chest X-rays are at finding congenital heart disease in newborns. Researchers will observe 60 newborns (up to 28 days old) admitted to the Neonatal Intensive Care Unit (NICU) who have signs or symptoms that suggest they might have a heart problem. Each baby in the study will receive a standard chest X-ray within 24 hours of their clinical presentation. Within 72 hours, they will also receive an echocardiogram, which is the standard, definitive test used to confirm if there is a heart defect. By comparing the initial chest X-ray results to the final echocardiogram results, researchers hope to figure out exactly which X-ray patterns are best at predicting specific heart diseases. This could help doctors make faster decisions about treating newborns, potentially reducing delays in diagnosis and improving care.

X-ray examination is one of the most commonly used imaging modalities, especially chest X-ray, which is routinely performed for hospitalized patients. However, due to the low density resolution of X-ray images, radiologists' ability to diagnose diseases-particularly small lesions-is often affected. Studies have shown that the diagnostic accuracy of radiologists using chest X-rays is only around 70%, which does not meet clinical demands. Based on this, we developed an artificial intelligence model to assist radiologists in interpreting X-ray images and generating reports, with the aim of improving diagnostic accuracy and reducing interpretation time.

The goal of this observational study is to develop an AI-based early warning system for Kawasaki Disease (KD) using chest X-rays (CXR) in children diagnosed with Kawasaki Disease. The main question\[s\] it aims to answer are: 1. Can AI modeling of CXR features help identify high-risk KD patients earlier than current diagnostic methods? 2. Can the AI system predict the optimal IVIG treatment window and coronary artery risks in KD patients? Participants will: Provide retrospective data on chest X-rays and clinical data (CRP, coronary ultrasound, etc.) Allow analysis of CXR features using deep learning models to extract relevant patterns Have their data incorporated into a federated learning model to ensure privacy and data security