Publications by authors named "Migyeong Ji"
Article Synopsis
- Cancer patients face high risks of short-term deterioration due to their treatments and complications, prompting the use of a rapid response system (RRS) to identify at-risk individuals.
- A retrospective study analyzed data from nearly 20,000 oncology patients admitted between 2016 and 2020 to develop a deep learning-based early warning score (Can-EWS) for predicting clinical deterioration.
- Two models were created, with Can-EWS V2 showing significantly better performance in predicting deterioration than existing methods, achieving a high area under the receiver operating curve (AUROC) of 0.898, demonstrating its effectiveness in clinical settings.
Most recent survival prediction has been based on TNM staging, which does not provide individualized information. However, clinical factors including performance status, age, sex, and smoking might influence survival. Therefore, we used artificial intelligence (AI) to analyze various clinical factors to precisely predict the survival of patients with larynx squamous cell carcinoma (LSCC).
View Article and Find Full Text PDF