Objectives: Smart hospitals involve the application of recent information and communications technology (ICT) innovations to medical services; however, the concept of a smart hospital has not been rigorously defined. In this study, we aimed to derive the definition and service types of smart hospitals and investigate cases of each type. Methods: A literature review was conducted regarding the background and technical characteristics of smart hospitals. On this basis, we conducted a focus group interview with experts in hospital information systems, and ultimately derived eight smart hospital service types.Results: Smart hospital services can be classified into the following types: services based on location recognition and tracking technology that measures and monitors the location information of an object based on short-range communication technology; high-speed communication network-based services based on new wireless communication technology; Internet of Things-based services that connect objects embedded with sensors and communication functions to the internet; mobile health services such as mobile phones, tablets, and wearables; artificial intelligence-based services for the diagnosis and prediction of diseases; robot services provided on behalf of humans in various medical fields; extended reality services that apply hyper-realistic immersive technology to medical practice; and telehealth using ICT. Conclusions: Smart hospitals can influence health and medical policies and create new medical value by defining and quantitatively measuring detailed indicators based on data collected from existing hospitals. Simultaneously, appropriate government incentives, consolidated interdisciplinary research, and active participation by industry are required to foster and facilitate smart hospitals.

Coronary artery disease, which is mostly caused by atherosclerotic narrowing of the coronary artery lumen, is a leading cause of death. Coronary angiography is the standard method to estimate the severity of coronary artery stenosis, but is frequently limited by intra- and inter-observer variations. We propose a deep-learning algorithm that automatically recognizes stenosis in coronary angiographic images. The proposed method consists of key frame detection, deep learning model training for classification of stenosis on each key frame, and visualization of the possible location of the stenosis. Firstly, we propose an algorithm that automatically extracts key frames essential for diagnosis from 452 right coronary artery angiography movie clips. Our deep learning model is then trained with image-level annotations to classify the areas narrowed by over 50 %. To make the model focus on the salient features, we apply a self-attention mechanism. The stenotic locations are visualized using the activated area of feature maps with gradient-weighted class activation mapping. The automatically detected key frame was very close to the manually selected key frame (average distance (1.70 ± 0.12) frame per clip). The model was trained with key frames on internal datasets, and validated with internal and external datasets. Our training method achieved high frame-wise area-under-the-curve of 0.971, frame-wise accuracy of 0.934, and clip-wise accuracy of 0.965 in the average values of cross-validation evaluations. The external validation results showed high performances with the mean frame-wise area-under-the-curve of (0.925 and 0.956) in the single and ensemble model, respectively. Heat map visualization shows the location for different types of stenosis in both internal and external data sets. With the self-attention mechanism, the stenosis could be precisely localized, which helps to accurately classify the stenosis by type. Our automated classification algorithm could recognize and localize coronary artery stenosis highly accurately. Our approach might provide the basis for a screening and assistant tool for the interpretation of coronary angiography.

Background: The advancement of large language models (LLMs) offers significant opportunities for health care, particularly in the generation of medical documentation. However, challenges related to ensuring the accuracy and reliability of LLM outputs, coupled with the absence of established quality standards, have raised concerns about their clinical application. Objective: This study aimed to develop and validate an evaluation framework for assessing the accuracy and clinical applicability of LLM-generated emergency department (ED) records, aiming to enhance artificial intelligence integration in health care documentation. Methods: We organized the Healthcare Prompt-a-thon, a competitive event designed to explore the capabilities of LLMs in generating accurate medical records. The event involved 52 participants who generated 33 initial ED records using HyperCLOVA X, a Korean-specialized LLM. We applied a dual evaluation approach. First, clinical evaluation: 4 medical professionals evaluated the records using a 5-point Likert scale across 5 criteria—appropriateness, accuracy, structure/format, conciseness, and clinical validity. Second, quantitative evaluation: We developed a framework to categorize and count errors in the LLM outputs, identifying 7 key error types. Statistical methods, including Pearson correlation and intraclass correlation coefficients (ICC), were used to assess consistency and agreement among evaluators. Results: The clinical evaluation demonstrated strong interrater reliability, with ICC values ranging from 0.653 to 0.887 (P<.001), and a test-retest reliability Pearson correlation coefficient of 0.776 (P<.001). Quantitative analysis revealed that invalid generation errors were the most common, constituting 35.38% of total errors, while structural malformation errors had the most significant negative impact on the clinical evaluation score (Pearson r=–0.654; P<.001). A strong negative correlation was found between the number of quantitative errors and clinical evaluation scores (Pearson r=–0.633; P<.001), indicating that higher error rates corresponded to lower clinical acceptability. Conclusions: Our research provides robust support for the reliability and clinical acceptability of the proposed evaluation framework. It underscores the framework’s potential to mitigate clinical burdens and foster the responsible integration of artificial intelligence technologies in health care, suggesting a promising direction for future research and practical applications in the field.

Introduction: Several methods have been proposed to evaluate neurological outcome in out-of-hospital cardiac arrest (OHCA) patients. Blood lactate has been recognized as a reliable prognostic marker for trauma, sepsis, or cardiac arrest. The objective of this study was to examine the association between initial lactate level or lactate clearance and neurologic outcome in OHCA survivors who were treated with therapeutic hypothermia. Methods: This retrospective cohort study included patients who underwent protocol-based 24-hour therapeutic hypothermia after OHCA between January 2010 and March 2012. Serum lactate levels were measured at the start of therapy (0 hours), and after 6 hours, 12 hours, 24 hours, 48 hours and 72 hours. The 6 hour and 12 hour lactate clearance were calculated afterwards. Patients’ neurologic outcome was assessed at one month after cardiac arrest; good neurological outcome was defined as Cerebral Performance Category one or two. The primary outcome was an association between initial lactate level and good neurologic outcome. The secondary outcome was an association between lactate clearance and good neurologic outcome in patients with initial lactate level >2.5 mmol/l. Results: Out of the 76 patients enrolled, 34 (44.7%) had a good neurologic outcome. The initial lactate level showed no significant difference between good and poor neurologic outcome groups (6.07 ±4 .09 mmol/L vs 7.13 ± 3.99 mmol/L, P = 0.42), However, lactate levels at 6 hours, 12 hours, 24 hours, and 48 hours in the good neurologic outcome group were lower than in the poor neurologic outcome group (3.81 ± 2.81 vs 6.00 ± 3.22 P <0.01, 2.95 ± 2.07 vs 5.00 ± 3.49 P <0.01, 2.17 ± 1.24 vs 3.86 ± 3.92 P <0.01, 1.57 ± 1.02 vs 2.21 ± 1.35 P = 0.03, respectively). The secondary analysis showed that the 6-hour and 12-hour lactate clearance was higher for good neurologic outcome patients (35.3 ± 34.6% vs 6.89 ± 47.4% P = 0.01, 54.5 ± 23.7% vs 25.6 ± 43.7% P <0.01, respectively). After adjusting for potential confounding variables, the 12-hour lactate clearance still showed a statistically significant difference (P = 0.02). Conclusion: The lactate clearance rate, and not the initial lactate level, was associated with neurological outcome in OHCA patients after therapeutic hypothermia.

The aim of this study was to develop machine learning (ML) and initial nursing assessment (INA)-based emergency department (ED) triage to predict adverse clinical outcome. The retrospective study included ED visits between January 2016 and December 2017 that resulted in either intensive care unit admission or emergency room death. We trained four classifiers using logistic regression and a deep learning model on INA and low dimensional (LD) INA, logistic regression on the Korea Triage and acuity scale (KTAS) and Sequential Related Organ Failure Assessment (SOFA). We varied the outcome ratio for external validation. Finally, variables of importance were identified using the random forest model's information gain. The four most influential variables were used for LD modeling for efficiency. A total of 86,304 patient visits were included, with an overall outcome rate of 3.5%. The area under the curve (AUC) values for the KTAS model were 76.8 (74.9-78.6) with logistic regression and 74.0 (72.1-75.9) for the SOFA model, while the AUC values of the INA model were 87.2 (85.9-88.6) and 87.6 (86.3-88.9) with logistic regression and deep learning, suggesting that the ML and INA-based triage system result more accurately predicted the outcomes. The AUC values for the LD model were 81.2 (79.4-82.9) and 80.7 (78.9-82.5) for logistic regression and deep learning, respectively. We developed an ML and INA-based triage system for EDs. The novel system was able to predict clinical outcomes more accurately than existing triage systems, KTAS and SOFA.

In this study, we aimed to describe the processes of both the donning and the doffing of personal protective equipment for Ebola and evaluate contamination during the doffing process. We recruited study participants among physicians and nurses of the emergency department of Samsung Medical Center in Seoul, Korea. Participants were asked to carry out doffing and donning procedures with a helper after a 50-minute brief training and demonstration based on the 2014 Centers for Disease Control and Prevention protocol. Two separate cameras with high-density capability were set up, and the donning and doffing processes were video-taped. A trained examiner inspected all video recordings and coded for intervals, errors, and contaminations defined as the outside of the equipment touching the clinician's body surface. Overall, 29 participants were enrolled. Twenty (68.9%) were female, and the mean age was 29.2 years. For the donning process, the average interval until the end was 234.2 seconds (standard deviation [SD], 65.7), and the most frequent errors occurred when putting on the outer gloves (27.5%), respirator (20.6%), and hood (20.6%). For the doffing process, the average interval until the end was 183.7 seconds (SD, 38.4), and the most frequent errors occurred during disinfecting the feet (37.9%), discarding the scrubs (17.2%), and putting on gloves (13.7%), respectively. During the doffing process, 65 incidences of contamination occurred (2.2 incidents/person). The most vulnerable processes were removing respirators (79.2%), removing the shoe covers (65.5%), and removal of the hood (41.3%). A significant number of contaminations occur during the doffing process of personal protective equipment.