Abstract Background A favorable neurological outcome is closely related to patient characteristics and total cardiopulmonary resuscitation (CPR) duration. The CPR duration consists of pre-hospital in-hospital durations. To date, consensus lacking on the optimal Therefore, this study aimed determine upper limit duration, cut-off time at level, switch from conventional alternative such as extracorporeal CPR. Methods We conducted a retrospective observational using prospective, multi-center...

Shock is a life-threatening condition characterized by generalized circulatory failure, which can have devastating consequences if not promptly treated. Thus, early prediction and continuous monitoring of physiological signs are essential for timely intervention. While previous machine learning research in clinical settings has primarily focused on predicting the onset deteriorating events, importance ongoing state patient's post-onset often been overlooked. In this study, we introduce novel...

To develop and evaluate deep learning models for cardiac arrest rhythm classification during cardiopulmonary resuscitation (CPR), we analyzed 508 electrocardiogram (ECG) segments (each 4 s in duration, recorded at 250 Hz) from 131 patients. Compression-affected were chest compressions, while non-compression extracted compression pauses or immediately after return of spontaneous circulation (ROSC) declaration. One-dimensional convolutional neural network (1D-CNN) recurrent (RNN) employed four...

Acute kidney injury (AKI) presents a public health challenge with profound short and long-term morbidity mortality. Early prediction severity identification of AKI are crucial for improving clinical outcomes through timely interventions efficient resource allocation. Previous studies have predominantly focused on serum creatinine, neglecting the significance urine output, which, combined delayed rise in creatinine post-AKI onset, hinders detection AKI. To address these shortcomings, we...

Introduction The evaluation of acute poisoning is challenging due to varied toxic substances and clinical presentations. new-Poisoning Mortality Score was recently developed assess patients with showed good performance in predicting in-hospital mortality. objective this study externally validate the compare it Modified Early Warning Score.

Background: The early diagnosis and prompt treatment of sepsis can enhance clinical outcomes. This study aimed to assess the relationship between point-of-care testing (POCT) for lactate levels both adherence Surviving Sepsis Campaign (SSC) guidelines mortality rates among patients in emergency department (ED). We hypothesized that bedside POCT would lead better Methods: conducted a pre–post observational utilizing data from prospectively collected registry. Following introduction POCT, were...

Overcrowding of emergency department (ED) has put a strain on national healthcare systems and adversely affected the clinical outcomes critically ill patients. Early identification patients prior to ED visits can help induce optimal patient flow allocate medical resources effectively. This study aims develop ML-based models for predicting critical illness in community, paramedic, hospital stages using Korean National Emergency Department Information System (NEDIS) data. Random forest light...

Background: Despite advancements in emergency medical systems, inter-hospital transfer (IHT) remains a critical component. Several studies have analyzed the impact of IHT on patient outcomes. Some reported positive effects, indicating that transfers can improve prognosis. However, other suggested may worsen We investigated whether is associated with in-hospital mortality. Methods: This retrospective observational study utilized data outcomes from National Emergency Department Information...

We attempted to determine the impact of extracorporeal membrane oxygenation (ECMO) on short-term and long-term outcomes find potential resource utilization differences between ECMO non-ECMO groups, using National Health Insurance Service database. selected adult patients (≥20 years old) with non-traumatic cardiac arrest from 2007 2015. Data age, sex, insurance status, hospital volume, residential area urbanization, pre-existing diseases were extracted A total 1.5% (n = 3859) 253,806...

Survival and post-cardiac arrest care vary considerably by hospital, region, country. In the current study, we aimed to analyze mortality in patients who underwent cardiac hospital level, reveal differences patient characteristics factors, including care, costs, adherence changes resuscitation guidelines.We enrolled adult (≥ 20 years) suffered non-traumatic from 2006 2015. Patient demographics, insurance type, admission route, comorbidities, treatments, costs were extracted National Health...

Purpose: The Korea University Anam Hospital Seoul Poison Control Center (SeoulPCC) was established in accordance with Metropolitan Government Ordinance No. 7524 “Seoul on the Prevention of Toxic Substances Poisoning and Accident Safety.” Herein, center’s annual performance terms project results consultation information for 2022 are reported.Methods: SeoulPCC operates a helpline (Help Call, 1855-2221) that general public can use from 9:00 AM to 5:00 PM weekdays, as well chatting chatbot...

This study develops machine learning-based algorithms that facilitate accurate prediction of cerebral oxygen saturation using waveform data in the near-infrared range from a multi-modal sensor. Data were obtained 150,000 observations popular oximeter, Masimo O3™ regional oximetry (Co., United States) and Votem (Inc., Korea). Among these observations, 112,500 (75%) 37,500 (25%) used for training test sets, respectively. The dependent variable was value (0–100%). independent variables time...

<title>Abstract</title> <bold>Background: </bold>Accurate and timely cardiac rhythm classification during cardiopulmonary resuscitation (CPR) is crucial for improving outcomes in arrest patients. This study aimed to develop evaluate deep learning models real-time ongoing CPR. <bold>Methods: </bold>We analyzed 508 ECG segments from 131 patients, including both artifact-free CPR-corrupted data. 1 dimensional convolutional neural network (1D-CNN) recurrent (RNN) were developed compared four...

As delayed treatment of septic shock can lead to an irreversible health state, timely identification holds immense value. While numerous approaches have been proposed build early warning systems, these primarily focus on predicting the future risk shock, irrespective its precise onset timing. Such prediction systems without consideration timeliness fall short in assisting clinicians taking proactive measures. To address this limitation, we establish a system for with data-task engineering,...

Background/Objectives: This study uses machine learning and multicenter registry data for analyzing the determinants of a favorable neurological outcome in patients with out-of-hospital cardiac arrest (OHCA) developing decision support systems various subgroups. Methods: The came from Korean Cardiac Arrest Research Consortium registry, 2679 who underwent OHCA aged 18 or above return spontaneous circulation (ROSC). dependent variable was (Cerebral Performance Category score 1–2), 68...

Purpose: The Korea University Anam Hospital Seoul Poison Control Center (Seoul PCC) has provided counseling services and poisoning prevention projects for the public medical professionals since January 2022. This report summarizes center’s performance consultation data 2023.Methods: PCC operates a helpline (1855-2221) on weekdays from 9 AM to 5 PM, along with chat chatbot via KakaoTalk, 1:1 online through its website, engagement social media. Data collected December 2023 were analyzed in...

Purpose: Suicide ranks among the top causes of death youth in South Korea. This study aimed to identify characteristics suicidal individuals treated at emergency departments between 2011 and 2020.Methods: A retrospective analysis was conducted using data from January December 2020 Injury Surveillance Cohort, a prospective registry. Patients’ sex, age, mortality, methods self-harm, previous suicide attempts were analyzed. The self-harm categorized into falls, asphyxiation, blunt injuries,...

Objectives: We intended to determine the association between hospital-level and mortality, reveal differences in patient characteristics potential resource utilization using National health Insurance Service database. Methods: selected adult patients (&gt;20 years old) with non-traumatic cardiac arrest from 2006 2015 national The were categorized into ‘Tertiary’, ‘Secondary’ ‘Primary’ groups by level of hospital where they treated. Demographics, insurance type, urbanization level, previous...