Clinical support system for triage based on federated learning for the Korea triage and acuity scale.

Background and aims: This study developed a clinical support system based on federated learning to predict the need for a revised Korea Triage Acuity Scale (KTAS) to facilitate triage. Methods: This was a retrospective study that used data from 11,952,887 patients in the Korean National Emergency Department Information System (NEDIS) from 2016 to 2018 for model development. Separate cohorts were created based on the emergency medical center level in the NEDIS: regional emergency medical center (REMC), local emergency medical center (LEMC), and local emergency medical institution (LEMI). External and temporal validation used data from emergency department (ED) of the study site from 2019 to 2021. Patient features obtained during the triage process and the initial KTAS scores were used to develop the prediction model. Federated learning was used to rectify the disparity in data quality between EDs. The patient's demographic information, vital signs in triage, mental status, arrival information, and initial KTAS were included in the input feature. Results: 3,626,154 patients' visits were included in the regional emergency medical center cohort; 8,278,081 patients' visits were included in the local emergency medical center cohort; and 48,652 patients' visits were included in the local emergency medical institution cohort. The study site cohort, which is used for external and temporal validation, included 135,780 patients visits. Among the patients in the REMC and study site cohorts, KTAS level 3 patients accounted for the highest proportion at 42.4% and 45.1%, respectively, whereas in the LEMC and LEMI cohorts, KTAS level 4 patients accounted for the highest proportion. The area under the receiver operating characteristic curve for the prediction model was 0.786, 0.750, and 0.770 in the external and temporal validation. Patients with revised KTAS scores had a higher admission rate and ED mortality rate than those with unaltered KTAS scores. Conclusions: This novel system might accurately predict the likelihood of KTAS acuity revision and support clinician-based triage.

Prognostic Accuracy of SpO2-based Respiratory Sequential Organ Failure Assessment for Predicting In-hospital Mortality.

Introduction: In this study we aimed to investigate the prognostic accuracy for predicting in-hospital mortality using respiratory Sequential Organ Failure Assessment (SOFA) scores by the conventional method of missing-value imputation with normal partial pressure of oxygen (PaO2)- and oxygen saturation (SpO2)-based estimation methods. Methods: This was a single-center, retrospective cohort study of patients with suspected infection in the emergency department. The primary outcome was in-hospital mortality. We compared the area under the receiver operating characteristics curve (AUROC) and calibration results of the conventional method (normal value imputation for missing PaO2) and six SpO2-based methods: using methods A, B, PaO2 is estimated by dividing SpO2 by a scale; with methods C and D, PaO2 was estimated by a mathematical model from a previous study; with methods E, F, respiratory SOFA scores was estimated by SpO2 thresholds and respiratory support use; with methods A, C, E are SpO2-based estimation for all PaO2 values, while methods B, D, F use such estimation only for missing PaO2 values. Results: Among the 15,119 patients included in the study, the in-hospital mortality rate was 4.9%. The missing PaO2was 56.0%. The calibration plots were similar among all methods. Each method yielded AUROCs that ranged from 0.735-0.772. The AUROC for the conventional method was 0.755 (95% confidence interval [CI] 0.736-0.773). The AUROC for method C (0.772; 95% CI 0.754-0.790) was higher than that of the conventional method, which was an SpO2-based estimation for all PaO2 values. The AUROC for total SOFA score from method E (0.815; 95% CI 0.800-0.831) was higher than that from the conventional method (0.806; 95% CI 0.790-0.822), in which respiratory SOFA was calculated by the predefined SpO2 cut-offs and oxygen support. Conclusion: In non-ICU settings, respiratory SOFA scores estimated by SpO2 might have acceptable prognostic accuracy for predicting in-hospital mortality. Our results suggest that SpO2-based respiratory SOFA score calculation might be an alternative for evaluating respiratory organ failure in the ED and clinical research settings.

Impact of the 24-hour time target policy for emergency departments in South Korea: a mixed method study in a single medical center.

BACKGROUND: In South Korea, after the spread of the Middle East Respiratory Syndrome epidemic was aggravated by long stays in crowded emergency departments (EDs), a 24-hour target policy for EDs was introduced to prevent crowding and reduce patients' length of stay (LOS). The policy requires at least 95% of all patients to be admitted, discharged or transferred from an ED within 24 hours of arrival. This study analyzes the effects of the 24-hour target policy on ED LOS and compliance rates and describes the consequences of the policy. METHODS: A mixed-methods approach was applied to a retrospective observational study of ED visits combined with a survey of medical professionals. The primary measure was ED LOS, and the secondary measure was policy compliance rate which refers to the proportion of patient visits with a LOS shorter than 24 hours. Patient flow, quality of care, patient safety, staff workload, and staff satisfaction were also investigated through surveys. Mann-Whitney U and χ2 tests were used to compare variables before and after the introduction of the policy. RESULTS: The median ED LOS increased from 3.9 hours (interquartile range [IQR] = 2.1-7.6) to 4.5 hours (IQR = 2.5-8.5) after the policy was introduced. This was likely influenced by the average monthly number of patients, which greatly increased from 4819 (SD = 340) to 5870 (SD = 462) during the same period. The proportion of patients with ED LOS greater than 24 hours remained below5% only after 6 months of policy implementation, but the number of patients whose disposition was decided at 23 hours increased by 4.84 times. Survey results suggested that patient flow and quality of care improved slightly, while the workload of medical staff worsened. CONCLUSIONS: After implementing the 24-hour target policy, the proportion of patients whose ED LOS exceeded 24 hours decreased, even though the median ED LOS increased. However, the unintended consequences of the policy were observed such as increased medical professional workload and abrupt expulsion of patients before 24 hours.

Prediction of vasopressor requirement among hypotensive patients with suspected infection: usefulness of diastolic shock index and lactate.

OBJECTIVE: We evaluated the performance of diastolic shock index (DSI) and lactate in predicting vasopressor requirement among hypotensive patients with suspected infection in an emergency department. METHODS: This was a single-center, retrospective observational study for adult patients with suspected infection and hypotension in the emergency department from 2018 to 2019. The study population was split into derivation and validation cohorts (70/30). We derived a simple risk score to predict vasopressor requirement using DSI and lactate cutoff values determined by Youden index. We tested the score by the area under the receiver operating characteristic curve (AUC). We performed a multivariable regression analysis to evaluate the association between the timing of vasopressor treatment and 28-day mortality. RESULTS: A total of 1,917 patients were included. We developed a score, assigning 1 point each for the high DSI (≥2.0) and high lactate (≥2.5 mmol/L) criteria. The AUCs of the score were 0.741 (95% confidence interval [CI], 0.715-0.768) at hypotension and 0.736 (95% CI, 0.708-0.763) after initial fluid challenge in the derivation cohort and 0.676 (95% CI, 0.631-0.719) at hypotension and 0.688 (95% CI, 0.642-0.733) after initial fluid challenge in the validation cohort, respectively. In patients with scores of 2 points, early vasopressor therapy initiation was significantly associated with decreased 28-day mortality (adjusted odds ratio, 0.37; 95% CI, 0.14-0.94). CONCLUSION: A prediction model with DSI and lactate levels might be useful to identify patients who are more likely to need vasopressor administration among hypotensive patients with suspected infection.

Intervention in the Timeliness of Two Electrocardiography Types for Patients in the Emergency Department With Chest Pain: Randomized Controlled Trial.

BACKGROUND: In the emergency department (ED), the result obtained using the 12-lead electrocardiography (ECG) is the basis for diagnosing and treating patients with chest pain. It was found that performing ECG at the appropriate time could improve treatment outcomes. Hence, a wearable ECG device with a timer can ensure that the findings are continuously recorded. OBJECTIVE: We aimed to compare the time accuracy of a single-patch 12-lead ECG (SP-ECG) with that of conventional ECG (C-ECG). We hypothesized that SP-ECG would result in better time accuracy. METHODS: Adult patients who visited the emergency room with chest pain but were not in shock were randomly assigned to one of the following 2 groups: the SP-ECG group or the C-ECG group. The final analysis included 33 (92%) of the 36 patients recruited. The primary outcome was the comparison of the time taken by the 2 groups to record the ECG. The average ages of the participants in the SP-ECG and C-ECG groups were 63.7 (SD 18.4) and 58.1 (SD 12.4) years, respectively. RESULTS: With a power of 0.95 and effect sizes of 0.05 and 1.36, the minimum number of samples was calculated. The minimum sample size for each SP-ECG and C-ECG group is 15.36 participants, assuming a 20% dropout rate. As a result, 36 patients with chest pain participated, and 33 of them were analyzed. The timeliness of SP-ECG and C-ECG for the first follow-up ECG was 87.5% and 47.0%, respectively (P=.74). It was 75.0% and 35.2% at the second follow-up, respectively (P=.71). CONCLUSIONS: Continuous ECG monitoring with minimal interference from other examinations is feasible and essential in complex ED situations. However, the precision of SP-ECG has not yet been proved. Nevertheless, the application of SP-ECG is expected to improve overcrowding and human resource shortages in EDs, though more research is needed. TRIAL REGISTRATION: ClinicalTrials.gov NCT04114760; https://clinicaltrials.gov/ct2/show/NCT04114760.

Effect of fever or respiratory symptoms on leaving without being seen during the COVID-19 pandemic in South Korea.

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.

Prehospital airway management for out-of-hospital cardiac arrest: A nationwide multicenter study from the KoCARC registry.

AIM: This study investigated whether prehospital advanced airway management (AAM) is associated with improved survival of out-of-hospital cardiac arrest (OHCA) compared with conventional bag-valve-mask (BVM) ventilation. METHODS: We investigated the neurologically favorable survival of adult patients with OHCA who underwent BVM or AAM using the Korean Cardiac Arrest Research Consortium (KoCARC), a multicenter OHCA registry of Korea. The differences in clinical characteristics were adjusted by matching or weighting the clinical propensity for use of AAM or by least absolute shrinkage and selection operator (LASSO). The primary outcome was 30-day survival with neurologically favorable status defined by cerebral performance category 1 or 2. RESULTS: Of the 9,616 patients enrolled (median age = 71 years; 65% male), there were 6,243 AAM and 3,354 BVM patients. In unadjusted analysis, the 30-day neurologically favorable survival was lower in the AAM group compared with the BVM group (5.5% vs. 10.0%; hazard ratio [HR] = 1.21, 95% confidence interval [CI] = 1.16 to 1.27; all p < 0.001). In propensity score matching-adjusted analysis, these differences were not found (9.6% vs. 10.0%; HR = 0.98, 95% CI = 0.93 to 1.03, p > 0.05). Inverse probability of treatment weighting- and LASSO-adjusted analyses replicated these results. CONCLUSIONS: In this nationwide real-world data analysis of OHCA, the 30-day neurologically favorable survival did not differ between prehospital AAM and BVM after adjustment for clinical characteristics.

Impact of Personal Protective Equipment on Out-of-Hospital Cardiac Arrest Resuscitation in Coronavirus Pandemic.

Background and Objectives: This retrospective study evaluated the clinical impact of enhanced personal protective equipment (PPE) on the clinical outcomes in patients with out-of-hospital cardiac arrest. Moreover, by focusing on the use of a powered air-purifying respirator (PAPR), we investigated the medical personnel's perceptions of wearing PAPR during cardiopulmonary resuscitation. Materials and Methods: According to the arrival time at the emergency department, the patients were categorized into a conventional PPE group (1 August 2019 to 20 January 2020) and an enhanced PPE group (21 January 2020, to 31 August 2020). The primary outcomes of this analysis were the return of spontaneous circulation (ROSC) rate. Additionally, subjective perception of the medical staff regarding the effect of wearing enhanced PPE during cardiopulmonary resuscitation (CPR) was evaluated by conducting a survey. Results: This study included 130 out-of-hospital cardiac arrest (OHCA) patients, with 73 and 57 patients in the conventional and enhanced PPE groups, respectively. The median time intervals to first intubation and to report the first arterial blood gas analysis results were longer in the enhanced PPE group than in the conventional PPE group (3 min vs. 2 min; p = 0.020 and 8 min vs. 3 min; p < 0.001, respectively). However, there were no significant differences in the ROSC rate (odds ratio (OR) = 0.79, 95% confidence interval (CI): 0.38-1.67; p = 0.542) and 1 month survival (OR 0.38, 95% CI: 0.07-2.10; p = 0.266) between the two groups. In total, 67 emergent department (ED) professionals responded to the questionnaire. Although a significant number of respondents experienced inconveniences with PAPR use, they agreed that PAPR was necessary during the CPR procedure for protection and reduction of infection transmission. Conclusion: The use of enhanced PPE, including PAPR, affected the performance of CPR to some extent but did not alter patient outcomes. PAPR use during the resuscitation of OHCA patients might positively impact the psychological stability of the medical staff.

Combination of neuron-specific enolase measurement and initial neurological examination for the prediction of neurological outcomes after cardiac arrest.

This study aimed to investigate the efficacy of the combination of neuron-specific enolase (NSE) measurement and initial neurological examination in predicting the neurological outcomes of patients with cardiac arrest (CA) by retrospectively analyzing data from the Korean Hypothermia Network prospective registry. NSE levels were recorded at 48 and 72 h after CA. The initial Full Outline of UnResponsiveness (FOUR) and Glasgow Coma Scale (GCS) scores were recorded. These variables were categorized using the scorecard method. The primary endpoint was poor neurological outcomes at 6 months. Of the 475 patients, 171 (36%) had good neurological outcomes at 6 months. The areas under the curve (AUCs) of the categorized NSE levels at 72 h, GCS score, and FOUR score were 0.889, 0.722, and 0.779, respectively. The AUCs of the combinations of categorized NSE levels at 72 h with categorized GCS scores and FOUR score were 0.910 and 0.912, respectively. Each combination was significantly higher than the AUC value of the categorized NSE level at 72 h alone (with GCS: p = 0.015; with FOUR: p = 0.026). Combining NSE measurement and initial neurological examination improved the prediction of neurological outcomes.

Twelve-Lead Electrocardiogram Acquisition With a Patchy-Type Wireless Device in Ambulance Transport: Simulation-Based Randomized Controlled Trial.

BACKGROUND: Cardiovascular disease is the leading cause of death worldwide. Early recognition, diagnosis, and reperfusion are the key elements of treatment for ST-segment elevation myocardial infarction. The absence of a prehospital 12-lead electrocardiogram (P12ECG) can cause definitive treatment delay and repeated transfer. Although guidelines highly recommend the measurement and transmission of P12ECG data, P12ECG use has not been widely established. OBJECTIVE: The aim of this study was to verify the time-efficiency and feasibility of the use of a patchy-type 12-lead ECG measuring and transmitting device (P-ECG) by an emergency medical technician (EMT) in an ambulance during patient transport. METHODS: This was a simulation-based prospective randomized crossover-controlled study that included EMTs. The participants were randomly assigned to one of two groups. Group A began the experiment with a conventional 12-lead ECG (C-ECG) device and then switched to the intervention device (P-ECG), whereas group B began the experiment with the P-ECG and then switched to the C-ECG. All simulations were performed inside an ambulance driving at 30 km/h. The time interval was measured from the beginning of ECG application to completion of sending the results. After the simulation, participants were administered the System Usability Scale questionnaire about usability of the P-ECG. RESULTS: A total of 18 EMTs were recruited for this study with a median age of 35 years. The overall interval time for the C-ECG was 254 seconds (IQR 247-270), whereas the overall interval time for the P-ECG was 130 seconds (IQR 112-150), with a significant difference (P<.001). Significant differences between the C-ECG and P-ECG were identified at all time intervals, in which the P-ECG device was significantly faster in all intervals, except for the preparation interval in which the C-ECG was faster (P=.03). CONCLUSIONS: Performance of 12-lead ECG examination and transmission of the results using P-ECG are faster than those of C-ECG during ambulance transport. With the additional time afforded, EMTs can provide more care to patients and transport patients more rapidly, which may help reduce the symptoms-to-balloon time for patients with acute coronary syndrome. TRIAL REGISTRATION: ClinicalTrials.gov NCT04114760; https://www.clinicaltrials.gov/ct2/show/NCT04114760.

Association between wide QRS pulseless electrical activity and hyperkalemia in cardiac arrest patients.

AIM: We evaluated the relationship between hyperkalemia and wide QRS complex in patients with pulseless electrical activity (PEA) cardiac arrest. METHODS: This was a single-center, retrospective observational study of patients over the age of 18 treated for cardiac arrest at a tertiary referral hospital whose initial electrocardiogram rhythm was PEA from February 2010 to December 2019. Wide QRS PEA was defined as a QRS interval of 120 ms or more. Hyperkalemia was defined as serum potassium level > 5.5 mmol/L. The primary outcome was hyperkalemia. Multivariable logistic regression analysis was used to evaluate the relationship between wide QRS and hyperkalemia. RESULTS: Among 617 patients, we analyzed 111 episodes in the wide QRS group and 506 episodes in the narrow QRS group. The potassium level in the wide QRS group was significantly higher than in the narrow QRS group (5.4 mmol/L, IQR 4.4-6.7 vs. 4.6 mmol/L, IQR 4.0-5.6, P < 0.001). Among all patients, 49.6% (n = 55/111) in the wide QRS group had hyperkalemia, which was significantly higher than the 26.7% (n = 135/506) in the narrow QRS group (P < 0.001). In multivariable logistic regression analysis, wide QRS PEA was significantly associated with hyperkalemia (odds ratio = 2.86, 95% confidence interval: 1.80-4.53, P < 0.001). CONCLUSIONS: Wide QRS PEA as an initial cardiac rhythm was significantly associated with hyperkalemia in cardiac arrest patients.

Prognostic implication of elevated cardiac troponin I in patients visiting emergency department without diagnosis of coronary artery disease.

OBJECTIVES: Elevated cardiac troponin is not uncommon in patients visiting emergency department (ED) even without coronary artery disease, but its prognostic implication is not well understood in such patients. METHODS: In this retrospective single-center registry, we investigated clinical outcome of patients visiting ED without documented coronary artery disease. Patients were categorized according to the maximal value of Siemens ADVIA Centaur TnI-Ultra assay (TnI) within 24 h after visit. Primary endpoint was 180-day all-cause death that included cardiac and non-cardiac death. RESULTS: A total of 35,205 patients with median age 61 years and male gender 54.7% were included. Below the lowest level of detection (LOD) (≤0.006 ng/mL), between LOD and assay-specific <99th percentile (0.007-0.039 ng/mL), below median of ≥99th percentile (0.040-0.149 ng/mL), and above median of ≥99th percentile (≥0.150 ng/mL) TnI were found in 18,502 (52.6%), 11,338 (32.2%), 3,029 (8.6%), and 2,336 (6.6%) patients. In the 180-day follow-up period, 4,341 (12.3%) all-cause death including 694 (2.0%) cardiovascular death and 3,647 (10.4%) non-cardiovascular death developed. The risks of all-cause, cardiovascular, and non-cardiovascular death increased across higher TnI strata (hazard ratio [HR]=1.3 to 2.4; 2.0 to 9.3; 1.3 to 1.7; p<0.001, all). Analyses of multivariate models showed consistent results. CONCLUSIONS: In patients visiting ED, elevated TnI was associated with higher risk of 180-day cardiovascular and non-cardiovascular death. Patients with elevated TnI may need additional evaluation or careful follow-up even without primary diagnosis of coronary artery disease.

Are loose-fitting powered air-purifying respirators safe during chest compression? A simulation study.

BACKGROUND: The application of appropriate personal protective equipment for respiratory protection to health care workers is a cornerstone for providing safe healthcare in emergency departments. We investigated the protective effect and usefulness of loose-fitting powered air-purifying respirators (PAPRs) during chest compression. METHODS: This was a single-center simulation study performed from May 2019 to July 2019 in a tertiary hospital. We measured the concentrations of ambient aerosol and particles inside the loose-fitting PAPR during chest compression, and this ratio was set as the simulated workplace protecting factor (SWPF). According to the National Institute for Occupational Safety and Health regulations, the assigned protection factor (APF) of loose-fitting PAPRs is 25. Thus, the loose-fitting PAPRs were assumed to have a protective effect when the SWPF were ≥ 250 (APF × 10). We measured the SWPF of PAPR in real time during chest compression and also investigated the problems encountered during its use. RESULTS: Ninety-one participants (median age 29 [interquartile range (IQR): 26-32] years; 74% female) completed the simulation. None of the participants failed with SWPF below 250 during three sessions of chest compression. The median (IQR) values of SWPF at three cycles were 17,063 (10,145-26,373), 15,683 (9477-32,394), and 16,960 (7695-27,279). There was no disconnection of equipment or mechanical failures during chest compression. In addition, most participants (83%) replied that they rarely or never experienced difficulty in verbal communication and felt that the loose-fitting PAPR was comfortable. CONCLUSIONS: The loose-fitting PAPRs provided sufficient respiratory protection without disturbances during chest compression.

Gender difference in the clinical outcomes of patients with out-of-hospital cardiac arrest: A report using data from a national Korean registry.

ABSTRACT: We explored gender differences in the characteristics and outcomes of patients with out-of-hospital cardiac arrest (OHCA) in Korea.We retrospectively analyzed a nationwide multicenter registry of out-of-hospital cardiac arrest patients that prospectively collected from January to December 2014, and explored the clinical outcomes of 670 successfully resuscitated adult patients with OHCA who were transferred to 27 hospitals. The effect of gender on the 30-day neurologically favorable survival (cerebral performance category 1 or 2) was analyzed after propensity score matching (PSM) of each patient in terms of clinical characteristics.We included 670 patients with OHCA, of whom 482 (72%) were male and 182 (28%) were female. The frequency of witnessed arrests and proportion of home arrests were similar between men and women (73.7% vs 71.3%, P = .59, and 55.0% vs 60.6% P = .21, respectively). Women were older than men (mean age, 65.9 vs 59.7 years, P < .001) and less likely to present with an initial shockable rhythm (27.7% vs 45.0%, P < .001). Women were less likely to undergo targeted temperature management (19.1% vs 35.9%, P < .001), coronary angiography (14.9% vs 36.1%, P < .001), or revascularization (7.4% vs 19.3%, P < .001). Compared with men, women exhibited poorer 30-day neurologically favorable survival (69.7% vs 83.0%, P = .001). However, the gender difference was not significant on PSM or inverse probability of treatment weighting (IPTW) analyses (P = .48 and P = .63, respectively).Female patients with OHCA exhibited poorer clinical characteristics and were less likely to receive treatment than men. After accounting for these differences, clinical outcomes did not differ by gender.

Developing a Time-Adaptive Prediction Model for Out-of-Hospital Cardiac Arrest: Nationwide Cohort Study in Korea.

BACKGROUND: Out-of-hospital cardiac arrest (OHCA) is a serious public health issue, and predicting the prognosis of OHCA patients can assist clinicians in making decisions about the treatment of patients, use of hospital resources, or termination of resuscitation. OBJECTIVE: This study aimed to develop a time-adaptive conditional prediction model (TACOM) to predict clinical outcomes every minute. METHODS: We performed a retrospective observational study using data from the Korea OHCA Registry in South Korea. In this study, we excluded patients with trauma, those who experienced return of spontaneous circulation before arriving in the emergency department (ED), and those who did not receive cardiopulmonary resuscitation (CPR) in the ED. We selected patients who received CPR in the ED. To develop the time-adaptive prediction model, we organized the training data set as ongoing CPR patients by the minute. A total of 49,669 patients were divided into 39,602 subjects for training and 10,067 subjects for validation. We compared random forest, LightGBM, and artificial neural networks as the prediction model methods. Model performance was quantified using the prediction probability of the model, area under the receiver operating characteristic curve (AUROC), and area under the precision recall curve. RESULTS: Among the three algorithms, LightGBM showed the best performance. From 0 to 30 min, the AUROC of the TACOM for predicting good neurological outcomes ranged from 0.910 (95% CI 0.910-0.911) to 0.869 (95% CI 0.865-0.871), whereas that for survival to hospital discharge ranged from 0.800 (95% CI 0.797-0.800) to 0.734 (95% CI 0.736-0.740). The prediction probability of the TACOM showed similar flow with cohort data based on a comparison with the conventional model's prediction probability. CONCLUSIONS: The TACOM predicted the clinical outcome of OHCA patients per minute. This model for predicting patient outcomes by the minute can assist clinicians in making rational decisions for OHCA patients.

Relationship Between Daily Sedentary Behaviors and Metabolic Syndrome in Middle-Aged Adults: Results from a Health Survey in Taean-Gun, Republic of Korea.

Background: It is unclear whether sedentary behavior is associated with metabolic risk, being independent of physical activity and other possible confounders. This study aimed to evaluate an association between sedentary behaviors and metabolic syndrome (MetS). Methods: A community-based cross-sectional study was conducted in a total of 987 Korean adults aged 40 years or older. Information on study variables, including physical activity, awake and sitting time, and components of MetS, was collected by a self-administered questionnaire, physical measurement, and laboratory test. MetS was defined according to the modified National Cholesterol Education Program's Adult Treatment Panel III and Korean Society for the Study of Obesity. Multiple logistic regression analysis was used to estimate the odds ratios (ORs) and 95% confidence intervals (CIs) for MetS associated with absolute sitting time, high sedentary ratio (>0.5), and other selected covariates, including age, sex, smoking, alcohol intake, educational attainment, daily meal times, regular exercise, intensity of physical activities, and sleep and nap duration. Results: After considering other selected variables, the risk of MetS was found to be higher by about 54% among subjects who had a higher sedentary ratio (OR: 1.54, 95% CI: 1.04-2.28). Every hour increase in sitting time was associated with increased risk of MetS (OR: 1.05, 95% CI: 0.99-1.11) with borderline significance (P = 0.119). Conclusions: Sedentary behavior was independently associated with an increased risk of MetS, suggesting that efforts to reduce the sedentary time might be also important for metabolic health in addition to encouraging adequate physical exercise. Clinical trial number is not applicable to this study.

Impact of COVID-19 Pandemic on the Overall Diagnostic and Therapeutic Process for Patients of Emergency Department and Those with Acute Cerebrovascular Disease.

(1) Background: During a pandemic, patients and processes in the emergency department (ED) change. These circumstances affect the length of stay (LOS) or degree of crowding in the ED. The processes for patients with acute critical illness, such as cerebrovascular disease (CVD), can be also delayed. Using the process mining (PM) method, this study aimed to evaluate LOS, ED processes for CVD, and delayed processes during the coronavirus disease 2019 (COVID-19) pandemic. (2) Methods: Data were collected from the Clinical Data Warehouse of a medical center. Phase 1 included patients who visited the ED before the COVID-19 outbreak. In Phase 2, post-COVID-19 ED patients were divided into the COVID-19 tested group (CTG) and COVID-19 not tested group (CNTG) according to whether polymerase chain reaction test was performed. We analyzed patients' ED processes before and after COVID-19 using the PM method. We analyzed patients with acute CVD separately to determine whether the process and LOS of patients with acute critical illness were changed or delayed. (3) Results: After the COVID-19 outbreak, the overall LOS was delayed and all processes in CTG patients were delayed. Registration to triage and triage were delayed in both CTG and CNTG patients. The brain imaging process for CTG patients with acute CVD was also delayed. (4) Conclusion: After a pandemic, some processes were changed, new processes were developed, and processes for patients with acute CVD who needed proper time management were not exempted.

Predicting 30-day mortality of patients with pneumonia in an emergency department setting using machine-learning models.

OBJECTIVE: This study aimed to confirm the accuracy of a machine-learning-based model in predicting the 30-day mortality of patients with pneumonia and evaluating whether they were required to be admitted to the intensive care unit (ICU). METHODS: The study conducted a retrospective analysis of pneumonia patients at an emergency department (ED) in Seoul, Korea, from January 1, 2016 to December 31, 2017. Patients aged 18 years or older with a pneumonia registry designation on their electronic medical record were enrolled. We collected their demographic information, mental status, and laboratory findings. Three models were used: the pre-existing CURB-65 model, and the CURB-RF and Extensive CURB-RF models, which were machine-learning models that used a random forest algorithm. The primary outcomes were ICU admission from the ED or 30-day mortality. Receiver operating characteristic curves were constructed for the models, and the areas under these curves were compared. RESULTS: Out of the 1,974 pneumonia patients, 1,732 patients were eligible to be included in the study; from these, 473 patients died within 30 days or were initially admitted to the ICU from the ED. The area under receiver operating characteristic curves of CURB-65, CURB-RF, and extensive-CURB-RF were 0.615 (0.614-0.616), 0.701 (0.700-0.702), and 0.844 (0.843-0.845), respectively. CONCLUSION: The proposed machine-learning models could predict the mortality of patients with pneumonia more accurately than the pre-existing CURB-65 model and can help decide whether the patient should be admitted to the ICU.

Cardiac troponin I predicts clinical outcome of patients with cancer at emergency department.

BACKGROUND: The prognostic ability of cardiac troponin I (TnI) has been demonstrated in general populations and among cardiovascular disease patients, but it has not been evaluated in cancer patients. HYPOTHESIS: This study assumes to have the prognostic ability of cardiac troponin in cancer patients visiting the emergency department. METHODS: Cancer patients visiting the emergency department were enrolled in this retrospective cohort study. Patients with previously known coronary artery disease or clinically indicated coronary angiography were not included. The maximal value from Siemens ADVIA Centaur troponin I Ultra assay within 24 hours was assessed. The primary endpoint was 180-day all-cause death, including cardiovascular and noncardiovascular death. RESULTS: A total of 9135 cancer patients (mean age: 63 years, male gender: 60%) were enrolled. Lowest (0.006 ng/mL), assay-specific <99th % (0.007-0.039 ng/mL), below median ≥ 99th % (0.040-0.129 ng/mL), and above median ≥ 99th % (≥0.130 ng/mL) TnI were found in 4487 (49.1%), 3158 (34.6%), 852 (9.3%), and 638 (7.0%) patients, respectively. There was 3192 (34.9%) all-cause deaths including 137 (1.5%) cardiovascular and 3047 (33.4%) noncardiovascular deaths in the 180-day follow-up period. The risks of all-cause, cardiovascular, and noncardiovascular death increased across higher TnI strata (hazard ratio [HR] = 1.3-2.9; 2.1-9.3; 1.3-1.8; P < .001, all). These findings were consistent within clinical subgroups including solid and hematologic cancers. CONCLUSIONS: Cancer patients visiting the emergency department with elevated troponin I were at increased risk of 180-day death. Cancer patients with elevated TnI may need additional evaluation or careful follow-up even without cardiovascular disease diagnosis.

Vasospasm-related Sudden Cardiac Death Has Outcomes Comparable with Coronary Stenosis in Out-of-Hospital Cardiac Arrest.

BACKGROUND: Characteristics of coronary vasospasm-related sudden cardiac death are not well understood. We aimed to compare the characteristics and clinical outcomes between coronary vasospasm and stenosis, in out-of-hospital cardiac arrest (OHCA) survivors, who underwent coronary angiogram (CAG). METHODS: We conducted a multicenter retrospective observational registry-based study at 8 Korean tertiary care centers. Data of OHCA survivors undergoing CAG between 2010 and 2015 were extracted. Patients were divided into vasospasm and stenosis (stenosis > 50%) groups based on CAG findings. The primary and the secondary outcomes were survival and a good neurologic outcome at 30 days after OHCA. Patients in the vasospasm and stenosis groups were propensity score matched. RESULTS: Of the 413 included patients, vasospasm and stenosis groups comprised 87 and 326 patients, respectively. There were 279 (66.7%) survivors and 206 (49.3%) patients with good neurologic outcomes. The vasospasm group had better clinical characteristics for outcome (younger age, less diabetes and hypertension, more prehospital restoration of spontaneous circulation, higher Glasgow Coma Scale, less ST segment elevation, and less requirement of circulatory support). The vasospasm group had better survival (75/87 vs. 204/326, P < 0.001) and good neurologic outcomes (62/87 vs. 144/326, P < 0.001). However, vasospasm was not independently associated with survival (odds ratio [OR], 0.980; 95% confidence interval [CI], 0.400-2.406) or neurologic outcomes (OR, 0.870; 95% CI, 0.359-2.108) after adjustment and vasospasm was not associated with survival and neurologic outcome in propensity score-matched cohorts. CONCLUSION: Our analysis of propensity score-matched cohorts finds that vasospasm OHCA survivors have survival and neurologic outcomes comparable with those of stenotic OHCA survivors.