RESUMEN

Aim: We assessed the efficacy of anti-hyperkalemic agents for alleviating hyperkalemia and improving clinical outcomes in patients with out-of-hospital cardiac arrest (OHCA). Methods: This was a single-center, retrospective observational study of OHCA patients treated at tertiary hospitals between 2010 and 2020. Adult patients aged 18 or older who were in cardiac arrest at the time of arrival and had records of potassium levels measured during cardiac arrest were included. A linear regression model was used to evaluate the relationship between changes in potassium levels and use of anti-hyperkalemic medications. Cox proportional hazards regression analysis was performed to analyze the relationship between the use of anti-hyperkalemic agents and the achievement of return of spontaneous circulation (ROSC). Results: Among 839 episodes, 465 patients received anti-hyperkalemic medication before ROSC. The rate of ROSC was higher in the no anti-hyperkalemic group than in the anti-hyperkalemic group (55.9 % vs 47.7 %, P = 0.019). The decrease in potassium level in the anti-hyperkalemic group from pre-ROSC to post-ROSC was significantly greater than that in the no anti-hyperkalemic group (coefficient 0.38, 95 % confidence interval [CI], 0.13-0.64, P = 0.003). In Cox proportional hazards regression analysis, the use of anti-hyperkalemic medication was related to a decreased ROSC rate in the overall group (adjusted hazard ratio [aHR] 0.66, 95 % CI, 0.54-0.81, P < 0.001), but there were no differences among subgroups classified according to initial potassium levels. Conclusions: Anti-hyperkalemic agents were associated with substantial decreases in potassium levels in OHCA patients. However, administration of anti-hyperkalemic agents did not affect the achievement of ROSC.

RESUMEN

BACKGROUND: Effective communication between patients and healthcare providers in the emergency department (ED) is challenging due to the dynamic nature of the ED environment. This study aimed to trial a chat service enabling patients in the ED and their family members to ask questions freely, exploring the service's feasibility and user experience. OBJECTIVES: To identify the types of needs and inquiries from patients and family members in the ED that could be addressed through the chat service and to assess the user experience of the service. METHODS: We enrolled patients and family members aged over 19 years in the ED, providing the chat service for up to 4 h per ED visit. Trained research nurses followed specific guidelines to respond to messages from the participants. After participation, participants were required to complete a survey. Those who agreed also participated in interviews to provide insights on their experiences with the ED chat service. RESULTS: A total of 40 participants (20 patients and 20 family members) sent 305 messages (72 by patients and 233 by family members), with patients sending an average of 3.6 messages and family members 11.7. Research nurses resolved 41.4% of patient inquiries and 70.9% of family member inquiries without further healthcare provider involvement. High usability was reported, with positive feedback on communication with healthcare workers, information accessibility, and emotional support. CONCLUSIONS: The ED chat service was found to be feasible and led to positive user experiences for both patients and their family members.

Asunto(s)

RESUMEN

OBJECTIVE: Drug incompatibility, a significant subset of medication errors, threaten patient safety during the medication administration phase. Despite the undeniably high prevalence of drug incompatibility, it is currently poorly understood because previous studies are focused predominantly on intensive care unit (ICU) settings. To enhance patient safety, it is crucial to expand our understanding of this issue from a comprehensive viewpoint. This study aims to investigate the prevalence and mechanism of drug incompatibility by analysing hospital-wide prescription and administration data. METHODS: This retrospective cross-sectional study, conducted at a tertiary academic hospital, included data extracted from the clinical data warehouse of the study institution on patients admitted between January 1, 2021, and May 31, 2021. Potential contacts in drug pairs (PCs) were identified using the study site clinical workflow. Drug incompatibility for each PC was determined by using a commercial drug incompatibility database, the Trissel's™ 2 Clinical Pharmaceutics Database (Trissel's 2 database). Drivers of drug incompatibility were identified, based on a descriptive analysis, after which, multivariate logistic regression was conducted to assess the risk factors for experiencing one or more drug incompatibilities during admission. RESULTS: Among 30,359 patients (representing 40,061 hospitalisations), 24,270 patients (32,912 hospitalisations) with 764,501 drug prescriptions (1,001,685 IV administrations) were analysed, after checking for eligibility. Based on the rule for determining PCs, 5,813,794 cases of PCs were identified. Among these, 25,108 (0.4 %) cases were incompatible PCs: 391 (1.6 %) PCs occurred during the prescription process and 24,717 (98.4 %) PCs during the administration process. By classifying these results, we identified the following drivers contributing to drug incompatibility: incorrect order factor; incorrect administration factor; and lack of related research. In multivariate analysis, the risk of encountering incompatible PCs was higher for patients who were male, older, with longer lengths of stay, with higher comorbidity, and admitted to medical ICUs. CONCLUSIONS: We comprehensively described the current state of drug incompatibility by analysing hospital-wide drug prescription and administration data. The results showed that drug incompatibility frequently occurs in clinical settings.

Asunto(s)

RESUMEN

OBJECTIVES: Sepsis is a leading global cause of mortality, and predicting its outcomes is vital for improving patient care. This study explored the capabilities of ChatGPT, a state-of-the-art natural language processing model, in predicting in-hospital mortality for sepsis patients. METHODS: This study utilized data from the Korean Sepsis Alliance (KSA) database, collected between 2019 and 2021, focusing on adult intensive care unit (ICU) patients and aiming to determine whether ChatGPT could predict all-cause mortality after ICU admission at 7 and 30 days. Structured prompts enabled ChatGPT to engage in in-context learning, with the number of patient examples varying from zero to six. The predictive capabilities of ChatGPT-3.5-turbo and ChatGPT-4 were then compared against a gradient boosting model (GBM) using various performance metrics. RESULTS: From the KSA database, 4,786 patients formed the 7-day mortality prediction dataset, of whom 718 died, and 4,025 patients formed the 30-day dataset, with 1,368 deaths. Age and clinical markers (e.g., Sequential Organ Failure Assessment score and lactic acid levels) showed significant differences between survivors and non-survivors in both datasets. For 7-day mortality predictions, the area under the receiver operating characteristic curve (AUROC) was 0.70-0.83 for GPT-4, 0.51-0.70 for GPT-3.5, and 0.79 for GBM. The AUROC for 30-day mortality was 0.51-0.59 for GPT-4, 0.47-0.57 for GPT-3.5, and 0.76 for GBM. Zero-shot predictions using GPT-4 for mortality from ICU admission to day 30 showed AUROCs from the mid-0.60s to 0.75 for GPT-4 and mainly from 0.47 to 0.63 for GPT-3.5. CONCLUSIONS: GPT-4 demonstrated potential in predicting short-term in-hospital mortality, although its performance varied across different evaluation metrics.

RESUMEN

INTRODUCTION: Preparing appropriate red blood cells (RBCs) before surgery is crucial for improving both the efficacy of perioperative workflow and patient safety. In particular, thoracic surgery (TS) is a procedure that requires massive transfusion with high variability for each patient. Hence, the precise prediction of RBC requirements for individual patients is becoming increasingly important. This study aimed to 1) develop and validate a machine learning algorithm for personalized RBC predictions for TS patients and 2) assess the usability of a clinical decision support system (CDSS) integrating this artificial intelligence model. METHODS: Adult patients who underwent TS between January 2016 and October 2021 were included in this study. Multiple models were developed by employing both traditional statistical- and machine-learning approaches. The primary outcome evaluated the model's performance in predicting RBC requirements through root mean square error and adjusted R2. Surgeons and informaticians determined the precision MSBOS-Thoracic Surgery (pMSBOS-TS) algorithm through a consensus process. The usability of the pMSBOS-TS was assessed using the System Usability Scale (SUS) survey with 60 clinicians. RESULTS: We identified 7,843 cases (6,200 for training and 1,643 for test sets) of TSs. Among the models with variable performance indices, the extreme gradient boosting model was selected as the pMSBOS-TS algorithm. The pMSBOS-TS model showed statistically significant lower root mean square error (mean: 3.203 and 95% confidence interval [CI]: 3.186-3.220) compared to the calculated Maximum Surgical Blood Ordering Schedule (MSBOS) and a higher adjusted R2 (mean: 0.399 and 95% CI: 0.395-0.403) compared to the calculated MSBOS, while requiring approximately 200 fewer packs for RBC preparation compared to the calculated MSBOS. The SUS score of the pMSBOS-TS CDSS was 72.5 points, indicating good acceptability. CONCLUSIONS: We successfully developed the pMSBOS-TS capable of predicting personalized RBC transfusion requirements for perioperative patients undergoing TS.

Asunto(s)

RESUMEN

BACKGROUND: Accurate prediction of renal function following kidney donation and careful selection of living donors are essential for living-kidney donation programs. We aimed to develop a prediction model for post-donation renal function following living kidney donation using machine learning. METHODS: This retrospective cohort study was conducted with 823 living kidney donors between 2009 and 2020. The dataset was randomly split into training (80%) and test sets (20%). The main outcome was the post-donation estimated glomerular filtration rate (eGFR) 12 months after nephrectomy. We compared the performance of machine learning techniques, traditional regression models, and models from previous studies. The best-performing model was selected based on the mean absolute error (MAE) and root mean square error (RMSE). RESULTS: The mean age of the participants was 45.2 ± 12.3 years, and 48.4% were males. The mean pre-donation and post-donation eGFRs were 101.3 ± 13.0 and 68.8 ± 12.7 mL/min/1.73 m2, respectively. The XGBoost model with the eGFR, age, serum creatinine, 24-h urine creatinine, 24-h urine sodium, creatinine clearance, cystatin C, cystatin C-based eGFR, computed tomography volume of the remaining kidney/body weight, normalized GFR of the remaining kidney measured through a diethylenetriaminepentaacetic acid scan, and sex, showed the best performance with a mean absolute error of 6.23 and root mean square error of 8.06. An easy-to-use web application titled Kidney Donation with Nephrologic Intelligence (KDNI) was developed. CONCLUSIONS: The prediction model using XGBoost accurately predicted the post-donation eGFR after living kidney donation. This model can be applied in clinical practice using KDNI, the developed web application.

RESUMEN

As point-of-care ultrasound (POCUS) is increasingly being used in clinical settings, ultrasound education is expanding into student curricula. We aimed to determine the status and awareness of POCUS education in Korean medical schools using a nationwide cross-sectional survey. In October 2021, a survey questionnaire consisting of 20 questions was distributed via e-mail to professors in the emergency medicine (EM) departments of Korean medical schools. The questionnaire encompassed 19 multiple-choice questions covering demographics, current education, perceptions, and barriers, and the final question was an open-ended inquiry seeking suggestions for POCUS education. All EM departments of the 40 medical schools responded, of which only 13 (33%) reported providing POCUS education. The implementation of POCUS education primarily occurred in the third and fourth years, with less than 4 hours of dedicated training time. Five schools offered a hands-on education. Among schools offering ultrasound education, POCUS training for trauma cases is the most common. Eight schools had designated professors responsible for POCUS education and only 2 possessed educational ultrasound devices. Of the respondents, 64% expressed the belief that POCUS education for medical students is necessary, whereas 36%, including those with neutral opinions, did not anticipate its importance. The identified barriers to POCUS education included faculty shortages (83%), infrastructure limitations (76%), training time constraints (74%), and a limited awareness of POCUS (29%). POCUS education in Korean medical schools was limited to a minority of EM departments (33%). To successfully implement POCUS education in medical curricula, it is crucial to clarify learning objectives, enhance faculty recognition, and improve the infrastructure. These findings provide valuable insights for advancing ultrasound training in medical schools to ensure the provision of high-quality POCUS education for future healthcare professionals.

Asunto(s)

RESUMEN

BACKGROUND: In the wake of challenges brought by the COVID-19 pandemic to conventional medical education, the demand for innovative teaching methods has surged. Nurse training, with its focus on hands-on practice and self-directed learning, encountered significant hurdles with conventional approaches. Augmented reality (AR) offers a potential solution to addressing this issue. OBJECTIVE: The aim of this study was to develop, introduce, and evaluate an AR-based educational program designed for nurses, focusing on its potential to facilitate hands-on practice and self-directed learning. METHODS: An AR-based educational program for nursing was developed anchored by the Kern six-step framework. First, we identified challenges in conventional teaching methods through interviews and literature reviews. Interviews highlighted the need for hands-on practice and on-site self-directed learning with feedback from a remote site. The training goals of the platform were established by expert trainers and researchers, focusing on the utilization of a ventilator and extracorporeal membrane oxygenation system. Intensive care nurses were enrolled to evaluate AR education. We then assessed usability and acceptability of the AR training using the System Usability Scale and Technology Acceptance Model with intensive care nurses who agreed to test the new platform. Additionally, selected participants provided deeper insights through semistructured interviews. RESULTS: This study highlights feasibility and key considerations for implementing an AR-based educational program for intensive care unit nurses, focusing on training objectives of the platform. Implemented over 2 months using Microsoft Dynamics 365 Guides and HoloLens 2, 28 participants were trained. Feedback gathered through interviews with the trainers and trainees indicated a positive reception. In particular, the trainees mentioned finding AR particularly useful for hands-on learning, appreciating its realism and the ability for repetitive practice. However, some challenges such as difficulty in adapting to the new technology were expressed. Overall, AR exhibits potential as a supplementary tool in nurse education. CONCLUSIONS: To our knowledge, this is the first study to substitute conventional methods with AR in this specific area of critical care nursing. These results indicate the multiple principal factors to take into consideration when adopting AR education in hospitals. AR is effective in promoting self-directed learning and hands-on practice, with participants displaying active engagement and enhanced skill acquisition. TRIAL REGISTRATION: ClinicalTrials.gov NCT05629663; https://clinicaltrials.gov/study/NCT05629663.

RESUMEN

Prevention of drug allergies is important for patient safety. The objective of this study was to evaluate the outcomes of antibiotic allergy-checking clinical decision support system (CDSS), K-CDSTM. A retrospective chart review study was performed in 29 hospitals and antibiotic allergy alerts data were collected from May to August 2022. A total of 15,535 allergy alert cases from 1586 patients were reviewed. The most frequently prescribed antibiotics were cephalosporins (48.5%), and there were more alerts of potential cross-reactivity between beta-lactam antibiotics than between antibiotics with the same ingredients or of the same class. Regarding allergy symptoms, dermatological disorders were the most common (38.8%), followed by gastrointestinal disorders (28.4%). The 714 cases (4.5%) of immune system disorders included 222 cases of anaphylaxis and 61 cases of severe cutaneous adverse reactions. Alerts for severe symptoms were reported in 6.4% of all cases. This study confirmed that K-CDS can effectively detect antibiotic allergies and prevent the prescription of potentially allergy-causing antibiotics among patients with a history of antibiotic allergies. If K-CDS is expanded to medical institutions nationwide in the future, it can prevent an increase in allergy recurrence related to drug prescriptions through cloud-based allergy detection CDSSs.

RESUMEN

[This corrects the article DOI: 10.1016/j.lanwpc.2023.100733.].

RESUMEN

Emergency departments (ED) are complex, triage is a main task in the ED to prioritize patient with limited medical resources who need them most. Machine learning (ML) based ED triage tool, Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable ML framework with single center. We aimed to develop SERP with 3 Korean multicenter cohorts based on common data model (CDM) without data sharing and compare performance with inter-hospital validation design. This retrospective cohort study included all adult emergency visit patients of 3 hospitals in Korea from 2016 to 2017. We adopted CDM for the standardized multicenter research. The outcome of interest was 2-day mortality after the patients' ED visit. We developed each hospital SERP using interpretable ML framework and validated inter-hospital wisely. We accessed the performance of each hospital's score based on some metrics considering data imbalance strategy. The study population for each hospital included 87,670, 83,363 and 54,423 ED visits from 2016 to 2017. The 2-day mortality rate were 0.51%, 0.56% and 0.65%. Validation results showed accurate for inter hospital validation which has at least AUROC of 0.899 (0.858-0.940). We developed multicenter based Interpretable ML model using CDM for 2-day mortality prediction and executed Inter-hospital external validation which showed enough high accuracy.

Asunto(s)

RESUMEN

BACKGROUND: Emergency departments (ED) nurses experience high mental workloads because of unpredictable work environments; however, research evaluating ED nursing workload using a tool incorporating nurses' perception is lacking. Quantify ED nursing subjective workload and explore the impact of work experience on perceived workload. METHODS: Thirty-two ED nurses at a tertiary academic hospital in the Republic of Korea were surveyed to assess their subjective workload for ED procedures using the National Aeronautics and Space Administration Task Load Index (NASA-TLX). Nonparametric statistical analysis was performed to describe the data, and linear regression analysis was conducted to estimate the impact of work experience on perceived workload. RESULTS: Cardiopulmonary resuscitation (CPR) had the highest median workload, followed by interruption from a patient and their family members. Although inexperienced nurses perceived the 'special care' procedures (CPR and defibrillation) as more challenging compared with other categories, analysis revealed that nurses with more than 107 months of experience reported a significantly higher workload than those with less than 36 months of experience. CONCLUSION: Addressing interruptions and customizing training can alleviate ED nursing workload. Quantified perceived workload is useful for identifying acceptable thresholds to maintain optimal workload, which ultimately contributes to predicting nursing staffing needs and ED crowding.

Asunto(s)

RESUMEN

Background: Due to the ongoing effects of climate change, the incidence of heatwave-related mortality is rising globally. Improved allocation and utilization of healthcare resources could help alleviate this issue. This study aimed to identify healthcare resource factors associated with heatwave-related mortality in seven major cities of South Korea. Methods: We analyzed daily time-series data on mean temperature and all-cause mortality from 2011 to 2019. Using principal component analysis (PCA), we clustered district-level healthcare resource indicators into three principal components (PCs). To estimate district-specific heatwave-mortality risk, we used a distributed lag model with a quasi-Poisson distribution. Furthermore, a meta-regression was performed to examine the association between healthcare resources and heatwave-mortality risk. Findings: A total of 310,363 deaths were analyzed in 74 districts. The lag-cumulative heatwave-related mortality (RRs) ranged from 1.12 (95% confidence interval [CI]: 1.07, 1.17) to 1.21 (95% CI 1.05, 1.38), depending on the definitions used for heatwaves. Of the three PCs for healthcare resources (PC1: pre-hospital emergency medical service, PC2: hospital resources, PC3: timely access), timely access was associated with reduced risk of heatwave-related mortality, particularly among the elderly. Specifically, timely access to any emergency room (ER) exhibited the strongest association with lower heatwave-related mortality. Interpretation: Our findings suggest that timely access to any ER is more effective in reducing heatwave-related mortality risk than access to higher-level healthcare facilities, especially among the elderly. Therefore, healthcare resource factors and ER accessibility should be prioritized when identifying vulnerable populations for heatwaves, along with known individual and socio-demographic factors. Funding: This work was supported by the Research Program funded by the Korea Disease Control and Prevention Agency (2022-12-303), the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2022R1A2C2092353) and the MD-PhD/Medical Scientist Training Program through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea.

RESUMEN

OBJECTIVES: Medical artificial intelligence (AI) has recently attracted considerable attention. However, training medical AI models is challenging due to privacy-protection regulations. Among the proposed solutions, federated learning (FL) stands out. FL involves transmitting only model parameters without sharing the original data, making it particularly suitable for the medical field, where data privacy is paramount. This study reviews the application of FL in the medical domain. METHODS: We conducted a literature search using the keywords "federated learning" in combination with "medical," "healthcare," or "clinical" on Google Scholar and PubMed. After reviewing titles and abstracts, 58 papers were selected for analysis. These FL studies were categorized based on the types of data used, the target disease, the use of open datasets, the local model of FL, and the neural network model. We also examined issues related to heterogeneity and security. RESULTS: In the investigated FL studies, the most commonly used data type was image data, and the most studied target diseases were cancer and COVID-19. The majority of studies utilized open datasets. Furthermore, 72% of the FL articles addressed heterogeneity issues, while 50% discussed security concerns. CONCLUSIONS: FL in the medical domain appears to be in its early stages, with most research using open data and focusing on specific data types and diseases for performance verification purposes. Nonetheless, medical FL research is anticipated to be increasingly applied and to become a vital component of multi-institutional research.

RESUMEN

A knowledgebase (KB) transition of a clinical decision support (CDS) system occurred at the study site. The transition was made from one commercial database to another, provided by a different vendor. The change was applied to all medications in the institute. The aim of this study was to analyze the effect of KB transition on medication-related orders and alert patterns in an emergency department (ED). Data of patients, medication-related orders and alerts, and physicians in the ED from January 2018 to December 2020 were analyzed in this study. A set of definitions was set to define orders, alerts, and alert overrides. Changes in order and alert patterns before and after the conversion, which took place in May 2019, were assessed. Overall, 101,450 patients visited the ED, and 1325 physicians made 829,474 prescription orders to patients during visit and at discharge. Alert rates (alert count divided by order count) for periods A and B were 12.6% and 14.1%, and override rates (alert override count divided by alert count) were 60.8% and 67.4%, respectively. Of the 296 drugs that were used more than 100 times during each period, 64.5% of the drugs had an increase in alert rate after the transition. Changes in alert rates were tested using chi-squared test and Fisher's exact test. We found that the CDS system knowledgebase transition was associated with a significant change in alert patterns at the medication level in the ED. Careful consideration is advised when such a transition is performed.

Asunto(s)

RESUMEN

To save time during transport, where resuscitation quality can degrade in a moving ambulance, it would be prudent to continue the resuscitation on scene if there is a high likelihood of ROSC occurring at the scene. We developed the pre-hospital real-time cardiac arrest outcome prediction (PReCAP) model to predict ROSC at the scene using prehospital input variables with time-adaptive cohort. The patient survival at discharge from the emergency department (ED), the 30-day survival rate, and the final Cerebral Performance Category (CPC) were secondary prediction outcomes in this study. The Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes out-of-hospital cardiac arrest (OHCA) patients transferred by emergency medical service in Asia between 2009 and 2018, was utilized for this study. From the variables available in the PAROS database, we selected relevant variables to predict OHCA outcomes. Light gradient-boosting machine (LightGBM) was used to build the PReCAP model. Between 2009 and 2018, 157,654 patients in the PAROS database were enrolled in our study. In terms of prediction of ROSC on scene, the PReCAP had an AUROC score between 0.85 and 0.87. The PReCAP had an AUROC score between 0.91 and 0.93 for predicting survived to discharge from ED, and an AUROC score between 0.80 and 0.86 for predicting the 30-day survival. The PReCAP predicted CPC with an AUROC score ranging from 0.84 to 0.91. The feature importance differed with time in the PReCAP model prediction of ROSC on scene. Using the PAROS database, PReCAP predicted ROSC on scene, survival to discharge from ED, 30-day survival, and CPC for each minute with an AUROC score ranging from 0.8 to 0.93. As this model used a multi-national database, it might be applicable for a variety of environments and populations.

Asunto(s)

RESUMEN

BACKGROUND: Anxiety and communication difficulties in the emergency department (ED) may increase for various reasons, including isolation due to coronavirus disease 2019 (COVID-19). However, little research on anxiety and communication in EDs exists. This study explored the isolation-related anxiety and communication experiences of ED patients during the COVID-19 pandemic. METHODS: A prospective mixed-methods study was conducted from May to August 2021 at the Samsung Medical Center ED, Seoul. There were two patient groups: isolation and control. Patients measured their anxiety using the State-Trait Anxiety Inventory (STAI X1) at two time points, and we surveyed patients at two time points about factors contributing to their anxiety and communication experiences. These were measured through a mobile web-based survey. Researchers interviewed patients after their discharge. RESULTS: ED patients were not anxious regardless of isolation, and there was no statistical significance between each group at the two time points. STAI X1 was 48.4 (standard deviation [SD], 8.0) and 47.3 (SD, 10.9) for early follow-up and 46.3 (SD, 13.0) and 46.2 (SD, 13.6) for late follow-up for the isolation and control groups, respectively. The clinical process was the greatest factor contributing to anxiety as opposed to the physical environment or communication. Communication was satisfactory in 71.4% of the isolation group and 66.7% of the control group. The most important aspects of communication were information about the clinical process and patient status. CONCLUSION: ED patients were not anxious and were generally satisfied with medical providers' communication regardless of their isolation status. However, patients need clinical process information for anxiety reduction and better communication.

Asunto(s)

Asunto(s)

RESUMEN

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.

RESUMEN

ABSTRACT: Objective/Introduction : Sequential vital-sign information and trends in vital signs are useful for predicting changes in patient state. This study aims to predict latent shock by observing sequential changes in patient vital signs. Methods : The dataset for this retrospective study contained a total of 93,194 emergency department (ED) visits from January 1, 2016, and December 31, 2020, and Medical Information Mart for Intensive Care (MIMIC)-IV-ED data. We further divided the data into training and validation datasets by random sampling without replacement at a 7:3 ratio. We carried out external validation with MIMIC-IV-ED. Our prediction model included logistic regression (LR), random forest (RF) classifier, a multilayer perceptron (MLP), and a recurrent neural network (RNN). To analyze the model performance, we used area under the receiver operating characteristic curve (AUROC). Results : Data of 89,250 visits of patients who met prespecified criteria were used to develop a latent-shock prediction model. Data of 142,250 patient visits from MIMIC-IV-ED satisfying the same inclusion criteria were used for external validation of the prediction model. The AUROC values of prediction for latent shock were 0.822, 0.841, 0.852, and 0.830 with RNN, MLP, RF, and LR methods, respectively, at 3 h before latent shock. This is higher than the shock index or adjusted shock index. Conclusion : We developed a latent shock prediction model based on 24 h of vital-sign sequence that changed with time and predicted the results by individual.

Asunto(s)