Objective To demonstrate the potential of machine learning and capability of natural language processing (NLP) to predict disposition of patients based on triage notes in the ED. Methods A retrospective cohort of ED triage notes from St Vincent's Hospital (Melbourne) was used to develop a deep‐learning algorithm that predicts patient disposition. Bidirectional Encoder Representations from Transformers, a recent language representation model developed by Google, was utilised for NLP. Eighty percent of the dataset was used for training the model and 20% was used to test the algorithm performance. Ktrain library, a wrapper for TensorFlow Keras, was employed to develop the model. Results The accuracy of the algorithm was 83% and the area under the curve was 0.88. Sensitivity, specificity, precision and F1‐score of the algorithm were 72%, 86%, 56% and 63%, respectively. Conclusion Machine learning and NLP can be together applied to the ED triage note to predict patient disposition with a high level of accuracy. The algorithm can potentially assist ED clinicians in early identification of patients requiring admission by mitigating the cognitive load, thus optimises resource allocation in EDs.
Purpose To evaluate static and dynamic cyclotorsions during photorefractive keratotomy (PRK) surgery in refractive surgery candidates and their correlations with preoperative factors. Methods This cross-sectional case series was performed in 138 eyes of 77 patients who underwent PRK surgery by Technolas 217z100. Iris registration was used to evaluate the degree of static and dynamic cyclotorsion. Wavefront measurements were performed in sitting position using Zywave (versions 3.1 and 3.2, Bausch & Lomb) Hartmann Shack aberrometer (Bausch & Lomb), and the cyclotorsion from upright to supine position was measured using iris image comparison. Dynamic cyclotorsions were measured by Advanced Cyclotorsional Eye Tracker (ACE) mounted on Excimer laser machine Technolas 217z100 during surgery. Results The mean absolute static cyclotorsion that was captured in surgery time was 3.37 ± 2.38° (range, 0.00 to 11.30), and the mean absolute dynamic cyclotorsion was 2.54 ± 2.50° (range, 0.00 to 13.60). There was a significant correlation between dynamic cyclotorsions and static cyclotorsions ( P < 0.001 and R = 0.704). There was a strong association between preoperative refractive astigmatism and range dynamic cyclotorsion. Total pulses ( P = 0.009), ablation depth ( P = 0.012), gender ( P = 0.008) had significant correlations with cyclotorsional movements. Conclusion The measurements of static and dynamic cyclotorsions are highly recommended for refractive surgery candidates with significant preoperative refractive astigmatism.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.