Objective Coronavirus disease 2019 (COVID-19) has notably altered the emergency department isolation protocol, imposing stricter requirements on probable infectious disease patients that enter the department. This has caused adverse effects, such as an increased rate of leave without being seen (LWBS). This study describes the effect of fever/respiratory symptoms as the main cause of isolation regarding LWBS after the COVID-19 pandemic.Methods We retrospectively analyzed emergency department visits before (March to July 2019) and after (March to July 2020) the COVID-19 pandemic. Patients were grouped based on existing fever or respiratory symptoms, with the LWBS rate as the primary outcome. Logistic regression analysis was used to identify the risk factors of LWBS. Logistic regression was performed using interaction terminology (fever/respiratory symptom patient [FRP] × post–COVID-19) to determine the interaction between patients with FRPs and the COVID-19 pandemic period.Results A total of 60,290 patients were included (34,492 in the pre–COVID-19, and 25,298 in the post–COVID-19 group). The proportion of FRPs decreased significantly after the pandemic (P < 0.001), while the LWBS rate in FRPs significantly increased from 2.8% to 19.2% (P < 0.001). Both FRPs (odds ratio, 1.76; 95% confidence interval, 1.59–1.84 (P < 0.001) and the COVID-19 period (odds ratio, 2.29; 95% confidence interval, 2.15–2.44; P < 0.001) were significantly associated with increased LWBS. Additionally, there was a significant interaction between the incidence of LWBS in FRPs and the COVID-19 pandemic period (P < 0.001).Conclusion The LWBS rate has increased in FRPs after the COVID-19 pandemic; additionally, the effect observed was disproportionate compared with that of nonfever/respiratory symptom patients.

Background Alert fatigue is unavoidable when many irrelevant alerts are generated in response to a small number of useful alerts. It is necessary to increase the effectiveness of the clinical decision support system (CDSS) by understanding physicians’ responses. Objective This study aimed to understand the CDSS and physicians’ behavior by evaluating the clinical appropriateness of alerts and the corresponding physicians’ responses in a medication-related passive alert system. Methods Data on medication-related orders, alerts, and patients’ electronic medical records were analyzed. The analyzed data were generated between August 2019 and June 2020 while the patient was in the emergency department. We evaluated the appropriateness of alerts and physicians’ responses for a subset of 382 alert cases and classified them. Results Of the 382 alert cases, only 7.3% (n=28) of the alerts were clinically appropriate. Regarding the appropriateness of the physicians’ responses about the alerts, 92.4% (n=353) were deemed appropriate. In the classification of alerts, only 3.4% (n=13) of alerts were successfully triggered, and 2.1% (n=8) were inappropriate in both alert clinical relevance and physician’s response. In this study, the override rate was 92.9% (n=355). Conclusions We evaluated the appropriateness of alerts and physicians’ responses through a detailed medical record review of the medication-related passive alert system. An excessive number of unnecessary alerts are generated, because the algorithm operates as a rule base without reflecting the individual condition of the patient. It is important to maximize the value of the CDSS by comprehending physicians’ responses.

Background and objectives: The aim of this study is to describe the temporal change in alert override with a minimally interruptive clinical decision support (CDS) on a Next-Generation electronic medical record (EMR) and analyze factors associated with the change. Materials and Methods: The minimally interruptive CDS used in this study was implemented in the hospital in 2016, which was a part of the new next-generation EMR, Data Analytics and Research Window for Integrated kNowledge (DARWIN), which does not generate modals, ‘pop-ups’ but show messages as in-line information. The prescription (medication order) and alerts data from July 2016 to December 2017 were extracted. Piece-wise regression analysis and linear regression analysis was performed to determine the temporal change and factors associated with it. Results: Overall, 2,706,395 alerts and 993 doctors were included in the study. Among doctors, 37.2% were faculty (professors), 17.2% were fellows, and 45.6% trainees (interns and residents). The overall override rate was 61.9%. There was a significant change in an increasing trend at month 12 (p < 0.001). We found doctors’ positions and specialties, along with the number of alerts and medication variability, were significantly associated with the change. Conclusions: In this study, we found a significant temporal change of alert override. We also found factors associated with the change, which had statistical significance.

The study aims to measure the effectiveness of an AI-based traumatic intracranial hemorrhage prediction model in the decisions of emergency physicians regarding ordering head computed tomography (CT) scans. We developed a deep-learning model for predicting traumatic intracranial hemorrhages (DEEPTICH) using a national trauma registry with 1.8 million cases. For simulation, 24 cases were selected from previous emergency department cases. For each case, physicians made decisions on ordering a head CT twice: initially without the DEEPTICH assistance, and subsequently with the DEEPTICH assistance. Of the 528 responses from 22 participants, 201 initial decisions were different from the DEEPTICH recommendations. Of these 201 initial decisions, 94 were changed after DEEPTICH assistance (46.8%). For the cases in which CT was initially not ordered, 71.4% of the decisions were changed (p < 0.001), and for the cases in which CT was initially ordered, 37.2% (p < 0.001) of the decisions were changed after DEEPTICH assistance. When using DEEPTICH, 46 (11.6%) unnecessary CTs were avoided (p < 0.001) and 10 (11.4%) traumatic intracranial hemorrhages (ICHs) that would have been otherwise missed were found (p = 0.039). We found that emergency physicians were likely to accept AI based on how they perceived its safety.