OBJECTIVES: Triage is a process to accurately assess and classify symptoms to identify and provide rapid treatment to patients. The Korean Triage and Acuity Scale (KTAS) is used as a triage instrument in all emergency centers. The aim of this study was to train and compare machine learning models to predict KTAS levels. METHODS: This was a cross-sectional study using data from a single emergency department of a tertiary university hospital. Information collected during triage was used in the analysis. Logistic regression, random forest, and XGBoost were used to predict the KTAS level. RESULTS: The models with the highest area under the receiver operating characteristic curve (AUROC) were the random forest and XGBoost models trained on the entire dataset (AUROC = 0.922, 95% confidence interval 0.917–0.925 and AUROC = 0.922, 95% confidence interval 0.918–0.925, respectively). The AUROC of the models trained on the clinical data was higher than that of models trained on text data only, but the models trained on all variables had the highest AUROC among similar machine learning models. CONCLUSIONS: Machine learning can robustly predict the KTAS level at triage, which may have many possibilities for use, and the addition of text data improves the predictive performance compared to that achieved by using structured data alone.
Cross-Sectional Studies ; Dataset ; Emergencies ; Emergency Service, Hospital ; Forests ; Humans ; Logistic Models ; Machine Learning ; Natural Language Processing ; ROC Curve ; Triage

Coronary artery aneurysms are uncommon, are usually associated with atherosclerosis, and rarely involve all three major coronary arteries. The present report describes a rare case of a young female patient presenting with acute myocardial infarction (AMI). Coronary angiography revealed multiple severe aneurysmal and stenotic changes. Based on clinical feature and angiographic findings, it was strongly suspected that the patient had polyarteritis nodosa (PAN) complicated by AMI. The patient was treated with standard cardiac medications and immunosuppressive agents and has remained stable without further complications during a follow-up period of 6 months.
Aneurysm ; Atherosclerosis ; Coronary Aneurysm ; Coronary Angiography ; Coronary Vessels ; Female ; Follow-Up Studies ; Humans ; Immunosuppressive Agents ; Myocardial Infarction ; Polyarteritis Nodosa ; Vasculitis

Background: Cardiovascular disease is life-threatening yet preventable for patients with type 2 diabetes mellitus (T2DM). Because each patient with T2DM has a different risk of developing cardiovascular complications, the accurate stratification of cardiovascular risk is critical. In this study, we proposed cardiovascular risk engines based on machine-learning algorithms for newly diagnosed T2DM patients in Korea. Methods: To develop the machine-learning-based cardiovascular disease engines, we retrospectively analyzed 26,166 newly diagnosed T2DM patients who visited Seoul St. Mary’s Hospital between July 2009 and April 2019. To accurately measure diabetes-related cardiovascular events, we designed a buffer (1 year), an observation (1 year), and an outcome period (5 years). The entire dataset was split into training and testing sets in an 8:2 ratio, and this procedure was repeated 100 times. The area under the receiver operating characteristic curve (AUROC) was calculated by 10-fold cross-validation on the training dataset. Results: The machine-learning-based risk engines (AUROC XGBoost=0.781±0.014 and AUROC gated recurrent unit [GRU]-ordinary differential equation [ODE]-Bayes=0.812±0.016) outperformed the conventional regression-based model (AUROC=0.723± 0.036). Conclusion GRU-ODE-Bayes-based cardiovascular risk engine is highly accurate, easily applicable, and can provide valuable information for the individualized treatment of Korean patients with newly diagnosed T2DM.

Objective: To review the characteristics of distal middle cerebral artery (MCA) aneurysm treated by microsurgery, the detailed surgical options, and the clinical result. Methods: We retrospectively reviewed cerebral aneurysm in the M2 and M3 segments of the MCA surgically treated between January 2015 and December 2022. The demographic data, aneurysm-related findings, type of surgical approach, surgical technique, and clinical outcomes of the enrolled patients were analyzed. Results: Sixteen distal MCA aneurysms were treated with microneurosurgery (incidence, 1.0%; female, 12; mean age, 58.1 years; ruptured, three). Twelve aneurysms were in the M2 segment (insular segment), two aneurysms at the M2–M3 junction, and two aneurysms in the M3 segment (opercular segment). Twelve aneurysms were saccular (average size, 4.9 mm; multiplicity, 50%; average aneurysms, 3.0; partially thrombosed, 1; sidewall aneurysm, 2). Three aneurysms were fusiform, of which two were ruptured. Of the ruptured aneurysms, one was a ruptured dissecting aneurysm. The trans-sylvian and trans-sulcal approaches were used in fourteen and two patients, respectively. Neck clipping, wrap clipping, and surgical trapping were performed in twelve, one, and one patient, respectively. Proximal occlusion was performed in one patient. Bypass technique was required in two patients (neck clipping and proximal occlusion). The modified Rankin Score was 6 in the two patients with ruptured aneurysms. The remaining patients did not show further neurological deterioration after microneurosurgery. Conclusions Distal MCA aneurysms had a high incidence of being diagnosed with multiple other aneurysms and were relatively non-saccular.