Examining patient flow in a tertiary hospital's emergency department at a low coronavirus prevalence region.

BACKGROUND: Taiwan's successful containment of the COVID-19 outbreak prior to 2021 provided a unique environment for the surveillance of unnecessary emergency medical use. The aim of the study is to examine the impact of the coronavirus disease (COVID-19) pandemic on the patient flow in the emergency department (ED) of a tertiary hospital over 1 year in southern Taiwan, a region with low COVID-19 prevalence. METHODS: Cross-sectional observational study was conducted from January to December 2020. Essential parameters of patient flow in the ED between January and February 2020 and the subsequent 11-month period were compared to data from 2019. Data were analyzed with descriptive statistics, using an independent sample t-test or Mann-Whitney U test, as applicable. RESULTS: The ED census showed an acute decline (- 30.8%) from January to February 2020, reaching its nadir (- 40.5%) in April 2020. From February to December 2020, there was an average decrease of 20.3% in ED attendance (p < 0.001). The impact was most significant in ambulatory visits, lower-urgency acuity (level III) visits, and pediatric visits, without change in the acuity proportion. The length of stay shortened mainly in the adult division, which typically had an overcrowding problem (median, 5.7-4.4 hours in discharge; 24.8-16.9 hours in hospitalization; p < 0.001). The incidence of 72-hour unscheduled return visits was also reduced (4.1-3.5%, p = 0.002). CONCLUSIONS: In contrast to devastated regions, the impact on the ED patient flow in regions having low COVID-19 prevalence highlights a remodeling process of emergency medical care that would improve overcrowding.

Risk Prediction of Barrett's Esophagus in a Taiwanese Health Examination Center Based on Regression Models.

Determining the target population for the screening of Barrett's esophagus (BE), a precancerous condition of esophageal adenocarcinoma, remains a challenge in Asia. The aim of our study was to develop risk prediction models for BE using logistic regression (LR) and artificial neural network (ANN) methods. Their predictive performances were compared. We retrospectively analyzed 9646 adults aged ≥20 years undergoing upper gastrointestinal endoscopy at a health examinations center in Taiwan. Evaluated by using 10-fold cross-validation, both models exhibited good discriminative power, with comparable area under curve (AUC) for the LR and ANN models (Both AUC were 0.702). Our risk prediction models for BE were developed from individuals with or without clinical indications of upper gastrointestinal endoscopy. The models have the potential to serve as a practical tool for identifying high-risk individuals of BE among the general population for endoscopic screening.

Emergency department disposition prediction using a deep neural network with integrated clinical narratives and structured data.

BACKGROUND: Emergency department (ED) overcrowding has been a serious issue and demands effective clinical decision-making of patient disposition. In previous studies, emergency clinical narratives provide a rich context for clinical decisions. We aimed to develop the disposition prediction model using deep learning modeling strategy with the heterogeneous data, including the physicians' narratives. METHODS: We constructed a retrospective cohort of all 104,083 ED visits of non-trauma adults during 2017-18 from an academically affiliated ED in Taiwan. 18,308 visits were excluded based on the completeness of each record and the unpredictable dispositions, such as out-of-hospital cardiac arrest, against-advice discharge, and escapes. We integrated subjective section of the first physicians' clinical narratives and structured data (e.g., demographics, triage vital signs, etc.) as available predictors at the first physician-patient encounter. To predict final patient disposition (i.e., hospitalization or discharge), a deep neural network (DNN) model was developed with word embedding, a common natural language processing method. We compared the proposed model to a reference model using the Rapid Emergency Medicine Score, a logistic regression model with structured data, and a DNN model with paragraph vectors. F1 score was used to measure the predictive performance for each model. RESULTS: The F1 score (with 95 % CI) for the proposed model, the reference model, the logistic regression model with structured data, and the DNN model with paragraph vectors were 0.674 (0.669-0.679), 0.474 (0.469-0.479), 0.547 (0.543-0.551), and 0.602 (0.596-0.607), respectively. While analyzing the relationship between context length and predictive performance under the proposed model, the F1 score at 95th percentile of the word counts was higher than that at 25th percentile of the word counts in chief complaint [0.634 (0.629-0.640) vs. 0.624 (0.620-0.628)] and in present illness [0.671 (0.667-0.674) vs. 0.654 (0.651-0.658)], but not in past medical history [0.674 (0.669-0.679) vs. 0.673 (0.666-0.679)]. CONCLUSIONS: The proposed deep learning model with the usage of the first physicians' clinical narratives and structured data based on natural language processing outperformed the commonly used ones in terms of F1 score. It also evidenced the importance of the subjective section of clinical narratives, which serve as vital predictors for ED clinical decision-making.

Early short-term prediction of emergency department length of stay using natural language processing for low-acuity outpatients.

BACKGROUND: Low-acuity outpatients constitute the majority of emergency department (ED) patients, and these patients often experience an unpredictable length of stay (LOS). Effective LOS prediction might improve the quality of ED care and reduce ED crowding. OBJECTIVE: The objective of this study was to explore the potential of natural language processing (NLP) of the first ED physicians' clinical notes and to evaluate NLP-based short-term prediction models based on mixed-type clinical data. METHODS: A retrospective study was conducted at an ED of a tertiary teaching hospital in Taiwan from January 2017 to June 2017. In total, 12,962 low-acuity outpatients were enrolled. Using structured data (e.g., demographic variables and vital signs) and different sections of the first SOAP notes as predictors, we developed six NLP-based prediction models (i.e., term frequency-inverse document frequency (TF-IDF) and truncated singular value decomposition (SVD)) to predict LOS. The metric for model evaluation is the mean squared error (MSE). RESULTS: Of the six NLP-based models, the model using structured data and all the sections of the first SOAP notes processed by the TF-IDF and truncated SVD method performed the best, with an MSE of 3.00 [95% CI: 2.94-3.06]. In addition, ten important topics extracted by the TF-IDF and truncated SVD method had significant effects on the LOS (p < 0.001). CONCLUSION: NLP-based models can be used as an early short-term prediction of LOS and have the potential for mixed-type clinical data analysis. The proposed models would likely aid ED physicians' decision-making processes and improve ED quality of care.

Risk factors for Barrett's esophagus in young adults who underwent upper gastrointestinal endoscopy in a health examination center.

BACKGROUND: Barrett's esophagus (BE) is a premalignant condition with increased incidence worldwide both in old and young individuals. However, the role of certain potential risk factors remains unclear in young adults (< 50 years). We aimed to determine the risk factors of BE in young adults. METHODS: A total of 4943 young adults who underwent upper gastrointestinal endoscopy at our health check-up center were enrolled. The diagnosis of BE was based on histological confirmation. We analyzed demographic factors, laboratory data, potential risk factors such as smoking, alcohol consumption, presence of gastroesophageal reflux disease (GERD) symptoms, and metabolic syndrome for the risk of BE by using binary logistic regression analysis. RESULTS: The prevalence of BE was 1.8% (88/4943). Male sex, the presence of GERD symptoms, and smoking were three significant risk factors related to BE. Furthermore, participants who had smoked for 10 pack-years or more had increased risk of BE with dose-dependent phenomenon (p trend < 0.001). The proportion of BE in male participants with both GERD symptoms and a smoking history of 10 pack-years or more was as high as 10.3% (16/155). CONCLUSIONS: Significant risk factors of BE in young adults are male sex, the presence of GERD symptoms, and smoking. The risk also increases with an increase in cumulative exposure to smoking.

Prevalence and risk factors for colonization by extended-spectrum ß-lactamase-producing or ST 131 Escherichia coli among asymptomatic adults in community settings in Southern Taiwan.

Purpose: Fecal carriage of extended-spectrum ß-lactamase-producing Escherichia coli (ESBL-EC) is common in Asia, especially in China and Southeast Asia. There are no data about fecal carriage of ESBL-EC and mcr-1-positive E. coli in Taiwan, and few studies focusing on the risk factors of asymptomatic fecal carriage of epidemic ST131 E. coli have been published. Patients and methods: From healthy inhabitants attending health examinations at a medical center in southern Taiwan in 2017, we collected 724 stool samples, which were examined for ESBL-EC fecal carriage using chromogenic medium. ST131 and mcr1-positive E. coli were also investigated using multiplex PCR. Clinical data from all participating adults were collected to analyze the risk factors for fecal ESBL-EC or ST131 E. coli carriage. Results: The prevalence rate of asymptomatic ESBL-EC fecal carriage in adults was 1.9% (14/724). ST131 was found in 22 (3.0%) adults and mcr-1-positive E. coli was found in three (0.4%) adults. A multivariate analysis showed that the risk factors associated with ESBL-EC carriage were diabetes mellitus (adjusted odds ratio [aOR]: 5.5, 95% confidence interval [CI]: 1.3-22.7), a history of colonic polyps (aOR: 6.4, 95% CI: 1.6-24.9), and chronic renal insufficiency (aOR: 20.7, 95% CI: 1.4-305.7). Underlying cancer (aOR: 4.8, 95% CI: 1.0-22.5) and stroke (aOR: 18.0, 95% CI: 1.6-207.5) were associated with ST131 E. coli fecal carriage. In our cohort, travel to Asian countries and food habit were not associated with ST131 or ESBL-EC fecal carriage. Conclusions: The ESBL-EC or ST131 E. coli fecal carriage rate is low among asymptomatic adults in Taiwan. Certain underlying medical conditions were associated with their fecal carriage.

Prevotella brain abscesses and stroke following dental extraction in a young patient: a case report and review of the literature.

A brain abscess is a life-threatening infection. There are few reports describing Prevotella bacteremia with middle cerebral artery (MCA) occlusion and brain abscess following dental extraction in the literature. We herein describe a 32-year-old healthy man who experienced headache after tooth extraction. He was not correctly diagnosed until he experienced a stroke and a blood culture revealed Prevotella denticola weeks later. This case and our detailed review of related cases highlight the importance of thorough medical history-taking and clinical evaluations. Brain abscess formation should be considered in previously healthy patients with fever, stroke, and a recent history of tooth extraction.