Machine Learning for Risk Stratification in the Emergency Department (MARS-ED)
Acute PainEmergenciesRationale Identifying emergency department (ED) patients at high and low risk shortly after admission could help decision-making regarding patient care. Several clinical risk scores and triage systems for stratification of patients have been developed, but often underperform in clinical practice. Moreover, most of these risk scores only have been diagnostically validated in an observational cohort, but never have been evaluated for their actual clinical impact. In a recent retrospective study that was conducted in the Maastricht University Medical Center (MUMC+), a novel clinical risk score, the RISKINDEX, was introduced that predicted 31-day mortality of sepsis patients presenting to an ED. The RISKINDEX hereby also outperformed internal medicine specialists. Observational follow-up studies underlined the potential of the risk score. However, it remains unknown to what extent these models have any beneficial value when it is actually implemented in clinical practice. Objective To determine the diagnostic accuracy, policy changes and clinical impact of the RISKINDEX as basis to conduct a large scale, multi-center randomised trial. Study design The MARS-ED study is designed as a multi-center, randomized, open-label, non-inferiority pilot clinical trial. Study population Adult patients who are assessed and treated by an internal medicine specialist in the ED of whom a minimum of 4 different laboratory results (hematology or clinical chemistry, required for calculation of ML risk score) are available within the first two hours of the ED visit. Intervention Physicians will be presented with the ML risk score (the RISKINDEX) of the patients they are actively treating, directly after assessment of regular diagnostics has taken place. Main study parameters Primary - Diagnostic accuracy, policy changes and clinical impact of a novel clinical risk score (the RISKINDEX) Secondary Policy changes due to presentation of ML score (treatment policy, requesting ancillary investigations, treatment restrictions (i.e., no intubation or resuscitation) Intensive care (ICU) and medium care (MC) admission Length of admission Mortality within 31 days Readmission Patient preference Feasibility of novel clinical risk score
Prospective Deployment of a Cardiac Arrest Response System (EDICARS) in the Emergency Department...
Cardiac ArrestBased on data from the American Heart Association's (AHA) Get With the Guidelines-Resuscitation (GTWG-R) registry, the incidence of adult treated in-hospital cardiac arrest (IHCA) was about 10 per 1,000 bed-days (290,000 patients per year), and 15 to 20% of adult IHCA patients survived to hospital discharge (i.e., ~80% mortality). Despite the significant morbidity and mortality caused by IHCA, ED-based IHCA is surprisingly less studied. The investigators have utilized electronic medical record (EMR)'s big data (>700,000 visits) from our hospital to investigate, for the first time, the epidemiology and outcome of IHCA in the ED in Taiwan. The investigators also have developed and validated a simple prediction tool for ED-based IHCA, the Emergency Department In-hospital Cardiac Arrest Score (EDICAS). This tool has also been externally validated using Far Eastern Memorial Hospital's ED data. In addition, the investigators also have developed and validated a vital-sign trajectory-based longitudinal model (group-based trajectory modeling [GBTM]) to predict ED-based IHCA. Based on these studies, the investigators now propose to (1) Embed the EDICAS into our hospital information system (HIS) in real-time at ED triage to identify high-risk patients (EDICAS 6+); and (2) Distribute wearable smart wristbands to high-risk patients to augment vital signs monitoring and send alerts based on GBTM results. The detection and intervention components together form the rapid response system, the Emergency Department In-hospital Cardiac Arrest Response System (EDICARS). In this study, the investigators will enroll and randomize 10 attending physicians into the EDICARS or the usual care arm for 3 months, with each of them treating 100 patients (patients clustered within physicians). The trial will stop for 2 months as a wash-out period, and an interim analysis will be performed. The physicians will then cross over, and each of them will treat 100 patients for another 3 months. A total of 2,000 adult patients will be enrolled. The primary outcome is a composite rate of ED-based IHCA and intensive care unit (ICU) admission. The secondary outcomes include time from ED triage to ED-based cardiac arrest, ICU and hospital length of stay, early ward-based IHCA, and early ICU transfer.
The Impact of MeMed BV® on Management of Patients With Suspected Lower Respiratory Tract Infections...
Lower Respiratory Tract InfectionThis is a Prospective, multi-center study enrolling adults subjects presented to the ED/Urgent care, with symptoms consistent with lower respiratory infection (LRTI). The reason of this study is to demonstrate the MeMed BV can help clinicians make decisions about using antibiotics in patients with lower respiratory track infections and see how it would impact clinical outcomes, antibiotics use, hospitalizations, ED clinicians find ways to improve health and medical care.
The Geriatric Acute & Post-acute Care Coordination Program for Fall Prevention in the Emergency...
FallIn brief, this K76 study consists of a small open trial to refine the study protocol and train study personnel on study procedures (Aim 1.b.). In Aim 2, we will recruit older adults into a multidisciplinary fall prevention pilot study. Participants will be randomly assigned to usual care with a traditional fall evaluation by an ED clinician (i.e., ED medical staff member) or an intervention. In the intervention, participants will receive an in-ED consultation by a physical therapist and pharmacist to determine reasons for the fall and offer additional education and training. Participants will be provided an Apple Watch to record measures of fitness and falls, if possible, in the following 12 months. Recurrent falls will be measured in twelve-month follow-up.
Outcomes of High-volume Saline Irrigation VS Povidone-Iodine Solution Cleaning of IOWI in Preventing...
Surgical Site InfectionSurgical Wound6 moreThe goal of this clinical trial is to compare the outcomes of High-volume saline irrigation vs Povidone-iodine solution cleaning of the intraoperative incision wound in preventing superficial surgical site infections in patients undergoing emergency laparotomies. The main question it aims to answer are: Incidence of SSI after intervention Length of hospital stay Participants will be randomly assigned to two groups receiving either of the two groups: Group A: 1000ml of IOWI with saline solution prior to incision closure Group B: The incisional wound will be closed conventionally without irrigation. Researchers will compare groups A( experimental group) and B (control group) to compare the incidence of superficial surgical site infections after intervention.
Developing a Support Application for Food Pantries (SAFPAS) to Improve Client Access to Healthy...
Improving Healthy Food Access in Food Insecurity Populations in Normal and Emergency SituationsFood pantries face many challenges, including recruitment and training of staff/volunteers, communications with staff/volunteers and clients, providing client choice, and emergency preparedness. The investigators will develop, implement, and evaluate the Support Application for Food Pantries (SAFPAS), a mobile application to address these concerns under normal and emergency operations, and assess its impact on 20 Baltimore food pantries, and on the healthiness of foods received by 360 food pantry clients using a randomized controlled trial design. If successful, the tested and refined app will support local food assistance programs throughout the United States.
Feasibility of 5% Albumin Compared With Balanced Crystalloid, as Intravenous Fluid Resuscitation...
SepsisThe aim of this research study is to compare two different fluids (Human Albumin Solution (HAS) and Balanced Crystalloid that are given via a drip to patients with severe infection (sepsis). The investigators plan to see which fluid is better, and to see if they have a role in improving a patient's recovery time, reducing complications and the length of time they stay in hospital. This study plans to find out if there is evidence that one fluid is better overall to determine the need for a subsequent definitive trial.
Feasibility and Accuracy of an Ultrasound Algorithm for Acute Dyspnea Diagnosis in the Emergency...
DyspneaThe management of chest pain has revolutionized its prognosis, primarily by improving urgent diagnosis of myocardial infarction. Currently, acute dyspnea is twice as frequent as chest pain and its associated mortality is much higher (16% of acute dyspnea admitted to emergency departments (ED) ). Inappropriate treatment of acute dyspnea in the ED is frequent (30%) and is associated with a tripling of intra-hospital mortality after adjustment for confounding factors (2.83, IC 1.48 to 5.41, p=0.002). Other elements have also highlighted the importance of a quick and appropriate acute dyspnea diagnosis: The 2015 European Guidelines on acute heart failure emphasize the need for appropriate treatment within 90 minutes after the first medical contact. Inadequate treatment of chronic bronchitis decompensation is associated with a doubling of intra-hospital mortality. An initiation of antibiotic treatment within 4 hours of admission for pneumonia is recommended. 30% of pulmonary embolisms are not diagnosed during the initial emergency department visit, whereas their mortality in the absence of treatment is 25%. Lung, venous and (simplified) cardiac ultrasound is associated with improved diagnostic performance in ED. However, no ultrasound algorithm dedicated to emergency physicians has been formally validated. The Blue Protocol (Lichtenstein et al., Chest 2008) has been validated in intensive care patients with very different phenotypes than those admitted to the ED. Pivetta et al. (Chest 2015) proposed an algorithm focused solely for the diagnosis of heart failure, thus not providing a diagnosis for all the other causes of dyspnea in ED. Finally, Zanbonetti et al. (Chest 2017) proposed an "unguided" ultrasound use, notably integrating inferior vena cava evaluation. However, measuring the inferior vena cava is difficult at the start of ED management when patients are in acute respiratory distress.
Assessment of the Contribution of an Artificial Intelligence Tool to Help the Diagnosis of Limb...
FracturesBoneLimb fracture is a common pathology in children. It represents the first complaint in traumatology among children in developed countries. Failure to diagnose a fracture can have severe consequences in pediatric patients with growing bones, that can lead to delayed treatment, pain and poor functional recovery. X-ray is the first tool used by doctors to diagnose a fracture. However, the diagnosis of fracture in the emergency room can be challenging. Most images are interpreted and processed by emergency pediatricians before being reviewed by radiologists (most often the day after). Previous studies have reported the rate of misdiagnosis in fracture by emergency physicians from 5% to 15%. A tool to investigate in diagnosing limb fractures could be helpful for any emergency physicians exposed to this condition
Point-Of-Care Ultrasound-Driven vs Standard Diagnostic Pathway in Emergency Department Patients...
DyspneaThe POCUS PATHWAY-trial is a multi-center, randomized, investigator-initiated, open labelled, pragmatic, controlled trial of a point-of-care ultrasound-driven diagnostic pathway vs standard diagnostic pathway in dyspneic emergency department patients. The primary outcome will be 24-hour hospital stay and 642 patients will be included. Key secondary outcomes include overall hospital length of stay, image resources, and 72-hour revisits.