RESUMEN
The triage process in emergency departments (EDs) relies on the subjective assessment of medical practitioners, making it unreliable in certain aspects. There is a need for a more accurate and objective algorithm to determine the urgency of patients. This paper explores the application of advanced data-synthesis algorithms, machine learning (ML) algorithms, and ensemble models to predict patient mortality. Patients predicted to be at risk of mortality are in a highly critical condition, signifying an urgent need for immediate medical intervention. This paper aims to determine the most effective method for predicting mortality by enhancing the F1 score while maintaining high area under the receiver operating characteristic curve (AUC) score. This study used a dataset of 7325 patients who visited the Yonsei Severance Hospital's ED, located in Seoul, South Korea. The patients were divided into two groups: patients who deceased in the ED and patients who didn't. Various data-synthesis techniques, such as SMOTE, ADASYN, CTGAN, TVAE, CopulaGAN, and Gaussian Copula, were deployed to generate synthetic patient data. Twenty two ML models were then utilized, including tree-based algorithms like Decision tree, AdaBoost, LightGBM, CatBoost, XGBoost, NGBoost, TabNet, which are deep neural network algorithms, and statistical algorithms such as Support Vector Machine, Logistic Regression, Random Forest, k-nearest neighbors, and Gaussian Naive Bayes, as well as Ensemble Models which use the results from the ML models. Based on 21 patient information features used in the pandemic influenza triage algorithm (PITA), the models explained previously were applied to aim for the prediction of patient mortality. In evaluating ML algorithms using an imbalanced medical dataset, conventional metrics like accuracy scores or AUC can be misleading. This paper emphasizes the importance of using the F1 score as the primary performance measure, focusing on recall and specificity in detecting patient mortality. The highest-ranked model for predicting mortality utilized the Gaussian Copula data-synthesis technique and the CatBoost classifier, achieving an AUC of 0.9731 and an F1 score of 0.7059. These findings highlight the effectiveness of machine learning algorithms and data-synthesis techniques in improving the prediction performance of mortality in EDs.
Asunto(s)
Cubomedusas , Aprendizaje Profundo , Humanos , Animales , Teorema de Bayes , Servicio de Urgencia en Hospital , Algoritmos , BenchmarkingRESUMEN
STUDY DESIGN: A retrospective radiological study. OBJECTIVE: To analyze the course of intra-axial vertebral artery (IAVA) and evaluate the relationship between the 3-dimensional (3D) courses for IAVA with respect to safe trajectory for C2 pedicle screw (C2PS). SUMMARY OF BACKGROUND DATA: The VA at the level of C2 has a distinct 3D course. The traditional concept of "high riding (HR)" VA was based on sagittal plane but does not provide all the 3D course of IAVA for safe C2PS placement. However, 3D course of IAVA has not been previously analyzed. METHODS: Three-dimensional, vascular-enhanced computed tomographic scans on the cervical spine of 100 patients, 200 IAVA (male to female ratio = 50:50; mean age, 58.4 yr) were analyzed. (1) The arterial parameters including (1) "medial-shifting (MS)" (A: lateral, B: neutral, C: medial to C3 transverse foramen [TF]) and (2) "HR" (0: below C2TF, 1 within C2TF, 2: above C2TF) of IAVA was measured. (2) The bony parameters including pedicle diameter, medial convergence angle, and sagittal angle of C2PS were measured. Correlation between the arterial and bony parameters, differences between sex, laterality, dominance of VA, and age were analyzed. RESULTS: MS (grade A, 37.5%; B, 37%; and C, 25.5%) and HR (grade 0 in 34%, 1 in 42%, and 2 in 24%) showed significant correlation with each other (P < 0.001). The main patterns of IAVA were A-0 (26%), B-1 (26.5%), and C-2 (18.5%). Higher grade of MS and HR showed significantly smaller pedicle diameter, larger medial convergence angle, and smaller sagittal angle (P < 0.001). Female sex and older age are factors that showed significantly higher grade of MS and HR (P < 0.001). CONCLUSION: Tortuosity of IAVA was greater in the female sex and it also increased with aging. The different IAVA courses significantly influenced the pedicle diameter and the safe trajectory for C2PS; therefore, these factors should be considered before planning C2 pedicle screw placement. LEVEL OF EVIDENCE: 3.