Related Experiment Video
Updated: Jan 10, 2026
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
Published on: April 7, 2023
Generative AI-enhanced nomogram predicts left without being seen among ambulance-transported emergency department
Hao Wang1, Emily Drone1, Devin Sandlin1
1Department of Emergency Medicine, JPS Health Network, Integrative Emergency Service, 1500 S. Main St., Fort Worth, TX 76104, United States of America.
Background:
Left without being seen (LWBS) is a key quality metric for evaluating emergency department (ED) performance. LWBS is associated with increased liability risks, diminished patient satisfaction, and wasted healthcare resources, often resulting in suboptimal patient outcomes, particularly among patients transported by ambulance. This study aimed to develop and validate a nomogram to predict the risk of LWBS in ambulance-transported patients with less urgent conditions.
Methods:
A total of 54,380 patient visits (32,582 unique patients) were included and randomly divided into a training set (37,996) and a testing set (16,384). A generative AI tool based on large language models (LLM) was used to convert unstructured chief complaint data into structured data. Independent predictors were identified using Least Absolute Shrinkage and Selection Operator (LASSO) regression and analyzed through multivariable logistic regression to construct a nomogram. The nomogram's performance was evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), calibration curve, decision curve analysis (DCA), sensitivity, and specificity.
Results:
Seven predictive factors were identified through LASSO regression analysis. The derived nomogram predicted LWBS probabilities ranging from 10 % to 70 %. The AUC values for the nomogram were 0.804 in the training set and 0.802 in the testing set, indicating strong discriminatory performance. Calibration curves and the Hosmer-Lemeshow test confirmed good calibration. Decision curve analysis demonstrated the clinical utility of the nomogram, showing a net benefit across various threshold probabilities.
Conclusion:
This study presents a validated nomogram for predicting LWBS among ambulance-transported patients with less urgent conditions. The nomogram provides valuable insights to support healthcare providers in making informed clinical decisions and optimizing patient management.
