Browse
Submit Data
Databases
API
Help

Dataset Information

32 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Real-time AI prediction for major adverse cardiac events in emergency department patients with chest pain.

ABSTRACT: BACKGROUND:A big-data-driven and artificial intelligence (AI) with machine learning (ML) approach has never been integrated with the hospital information system (HIS) for predicting major adverse cardiac events (MACE) in patients with chest pain in the emergency department (ED). Therefore, we conducted the present study to clarify it. METHODS:In total, 85,254 ED patients with chest pain in three hospitals between 2009 and 2018 were identified. We randomized the patients into a 70%/30% split for ML model training and testing. We used 14 clinical variables from their electronic health records to construct a random forest model with the synthetic minority oversampling technique preprocessing algorithm to predict acute myocardial infarction (AMI)

SUBMITTER: Zhang PI

PROVIDER: S-EPMC7488862 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Real-time AI prediction for major adverse cardiac events in emergency department patients with chest pain.

Zhang Pei-I PI Hsu Chien-Chin CC Kao Yuan Y Chen Chia-Jung CJ Kuo Ya-Wei YW Hsu Shu-Lien SL Liu Tzu-Lan TL Lin Hung-Jung HJ Wang Jhi-Joung JJ Liu Chung-Feng CF Huang Chien-Cheng CC

Scandinavian journal of trauma, resuscitation and emergency medicine 20200911 1

<h4>Background</h4>A big-data-driven and artificial intelligence (AI) with machine learning (ML) approach has never been integrated with the hospital information system (HIS) for predicting major adverse cardiac events (MACE) in patients with chest pain in the emergency department (ED). Therefore, we conducted the present study to clarify it.<h4>Methods</h4>In total, 85,254 ED patients with chest pain in three hospitals between 2009 and 2018 were identified. We randomized the patients into a 70% ...[more]

PMID: 32917261

Similar Datasets

Major adverse cardiovascular events in older emergency department patients presenting with non-cardiac medical complaints.

Project description:ObjectiveThe risk of major adverse cardiovascular events (MACE) for older emergency department (ED) patients presenting with non-cardiac medical complaints is unknown. To apply preventive measures timely, early identification of high-risk patients is incredibly important. We aimed at investigating the incidence of MACE within one year after their ED visit and the predictive value of high-sensitivity cardiac troponin T (hs-cTnT) and N‑terminal pro-B-type natriuretic peptide (NT-proBNP) for subsequent MACE.MethodsThis is a substudy of a Dutch prospective cohort study (RISE UP study) in older (≥ 65 years) medical ED patients who presented with non-cardiac complaints. Biomarkers were measured upon ED arrival. Cox-regression analysis was used to determine the predictive value of the biomarkers, when corrected for other possible predictors of MACE, and area under the curves (AUCs) were calculated.ResultsOf 431 patients with a median age of 79 years, 86 (20.0%) developed MACE within 1 year. Both hs-cTnT and NT-proBNP were predictive of MACE with an AUC of 0.74 (95% CI 0.68-0.80) for both, and a hazard ratio (HR) of 2.00 (95% CI 1.68-2.39) and 1.82 (95% CI 1.57-2.11) respectively. Multivariate analysis correcting for other possible predictors of MACE revealed NT-proBNP as an independent predictor of MACE.ConclusionOlder medical ED patients are at high risk of subsequent MACE within 1 year after their ED visit. While both hs-cTnT and NT-proBNP are predictive, only NT-proBNP is an independent predictor of MACE. It is likely that early identification of those at risk offers a window of opportunity for prevention.

| S-EPMC9691805 | biostudies-literature

Symptoms and coronary risk factors predictive of adverse cardiac events in chest pain patients in an Asian emergency department: the need for a local prediction score.

Project description:IntroductionClinical assessment is pivotal in diagnosing acute coronary syndrome. Our study aimed to identify clinical characteristics predictive of major adverse cardiac events (MACE) in an Asian population and to derive a risk score for MACE.MethodsPatients presenting to the emergency department (ED) with chest pain and non-diagnostic 12-lead electrocardiograms were recruited. Clinical history was recorded in a predesigned template. Random glucose and direct low-density lipoprotein measurements were taken, in addition to serial troponin. We derived the age, coronary risk factors (CRF), sex and symptoms (ACSS) risk score based on multivariate analysis results, considering age, CRF, sex and symptoms and classifying patients into very low, low, moderate and high risk for MACE. Comparison was made with the ED Assessment of Chest Pain Score (EDACS) and the history, electrocardiogram, age, risk factors, troponin (HEART) score. We also modified the HEART score with the CRF that we had identified. The outcomes were 30-day and 1-year MACE.ResultsThere were a total of 1689 patients, with 172 (10.2%) and 200 (11.8%) having 30-day and 1-year MACE, respectively. Symptoms predictive of MACE included central chest pain, radiation to the jaw/neck, associated diaphoresis, and symptoms aggravated by exertion and relieved by glyceryl trinitrate. The ACSS score had an area under the curve of 0.769 (95% confidence interval [CI]: 0.735-0.803) and 0.760 (95% CI: 0.727-0.793) for 30-day and 1-year MACE, respectively, outperforming EDACS. Those in the very-low-risk and low-risk groups had <1% risk of 30-day MACE.ConclusionThe ACSS risk score shows potential for use in the local ED or primary care setting, potentially reducing unnecessary cardiac investigations and admission.

| S-EPMC11321542 | biostudies-literature

Efficacy of HEAR and HEART score to rule out major adverse cardiac events in patients presenting to the emergency department with chest pain: study protocol of the eCARE stepped-wedge randomised control trial.

Project description:IntroductionCurrent guidelines for patients presenting to the emergency department (ED) with chest pain without ST-segment elevation myocardial infarction (STEMI) on ECG are based on serial troponin measurements. A clinical tool able to identify very low-risk patients who could forgo a troponin test and low-risk patients requiring only one troponin measurement would be of great interest. To do so, the HEAR and HEART score, standing for history, ECG, age, risk factors±troponin were prospectively assessed, but not combined and implemented in clinical practice. The objective of the eCARE study is to assess the impact of implementing a diagnostic strategy based on a HEAR score <2 or a HEART score <4 (HEAR-T strategy) to rule out non-STEMI without or with a single troponin measurement in patients presenting to the ED with chest pain without obvious diagnosis after physical examination and an ECG.Methods and analysisStepped-wedge cluster-randomised control trial in 10 EDs. Patients with non-traumatic chest pain and no formal diagnosis were included and followed for 30 days. In the interventional phase, the doctor will be asked not to perform a troponin test to look for an acute coronary if the HEAR score is <2 and not to perform an additional troponin test if the HEAR score is ≥2 and HEART score is <4. The main endpoint is the non-inferiority of the rates of major adverse cardiac events occurring between a patient's discharge and the 30-day follow-up against current recommended guidelines.Ethics and disseminationThe study was approved by an institutional review board for all participating centres. If successful, the eCARE study will cover a gap in the evidence, proving that it is safe and efficient to rule out the hypothesis of an acute myocardial infarction in some selected very low-risk patients or based on a single troponin measurement in some low-risk patients.Trial registration numberNCT04157790.

| S-EPMC9730388 | biostudies-literature

Illness representations, psychological distress and non-cardiac chest pain in patients attending an emergency department.

Project description:Many patients who attend an emergency department (ED) with chest pain receive a diagnosis of non-cardiac chest pain (NCCP), and often suffer poor psychological outcomes and continued pain. This study assessed the role of illness representations in explaining psychological distress and continued chest pain in patients attending an ED.ED NCCP patients (N = 138) completed measures assessing illness representations, anxiety, depression and quality of life (QoL) at baseline, and chest pain at one month.Illness representations explained significant amounts of the variance in anxiety (Adj. R² = .38), depression (Adj. R² = .18) and mental QoL (Adj. R² = .36). A belief in psychological causes had the strongest associations with outcomes. At one month, 28.7% of participants reported experiencing frequent pain, 13.2% infrequent pain and 58.1% no pain. Anxiety, depression and poor QoL, but not illness representations, were associated with continued chest pain.The findings suggest that (i) continued chest pain is related to psychological distress and poor QoL, (ii) interventions should be aimed at reducing psychological distress and improving QoL and (iii) given the associations between perceived psychological causes and psychological distress/QoL, NCCP patients in the ED might benefit from psychological therapies to manage their chest pain.

| S-EPMC4192860 | biostudies-other

Introducing a chest pain pathway in the emergency department to improve quality of care for patients with possible cardiac chest pain.

Project description:Chest pain is a common reason for patients to present to an emergency department (ED). It is crucial not to miss presentations of the potentially life-threatening acute coronary syndrome (ACS), although often these people present with a non-diagnostic ECG. This makes recognition of a history consistent with ACS very important. We noted inconsistencies in assessment, with many admissions to cardiology beds who did not prove to have ACS and some erroneous discharges who subsequently did have an ACS. We introduced a history based risk tool as part of a chest pain pathway into the ED for use by medical staff assessing patients presenting with chest pain. The intervention involved a nurse from cardiology engaging with clerical, nursing, and medical staff in the ED to ensure success of this quality improvement project. The project showed a reduction in admissions to cardiology with suspected ACS from 29% to 15%, with a projected saving of £889 per patient who was prevented from being admitted. In addition, admissions became more appropriate, with an increase in the proportion of patients with a final diagnosis of ACS from 25% to 46% and a reduction in admissions with atypical chest pain from 75% to 54%.

| S-EPMC4645935 | biostudies-literature

How do patients with chest pain access Emergency Department care?

Project description:It is important that patients with symptoms of acute coronary syndrome receive appropriate medical care as soon as possible. Little is known about the preadmission actions that patients with chest pain take before arrival at the Emergency Department (ED).This study aimed to describe the actions of patients with chest pain or pressure after onset of symptoms. What is the first action following onset of symptoms? Who is the first lay or professional person to be contacted? Which steps are taken first? How is the patient transported to the hospital?Consecutive patients, arriving at the ED of two large hospitals in Belgium, were asked additional questions during the initial assessment.Overall, 35% of 412 consecutive patients with chest pain admitted to the ED were diagnosed with acute coronary syndrome. A total of 57% contacted a GP between symptom onset and arrival at the ED. Only 32% of the patients were transported to the ED by ambulance, 16% drove themselves and 52% arrived by other means of transport (by family, neighbour, GP, public transport).In Belgium, the GP is still the first professional to be contacted for most patients. Other patients initially rely on their partner, family or friends when symptoms emerge. Too often, patients with chest pain rely on other transport to get to the ED instead of calling the Emergency Medical Services. This study included only patients who ultimately attended the ED.

| S-EPMC5671801 | biostudies-other

Multicenter analysis to assess risk of major adverse cardiac events in patients undergoing high-sensitivity troponin testing in the emergency department.

Project description:Study hypothesisOur objective was to evaluate 30-day major adverse cardiac events (MACE) in emergency department (ED) patients with normal high-sensitivity troponins (hs-trop). We hypothesized that MACE rates would be <1% in patients with (1) two normal troponins regardless of change in troponin (delta) and (2) index hs-trop below the limit of quantitation (LOQ) regardless of the institution modified HEART score.MethodsThis was a multicenter, retrospective, cohort study of adult patients who presented to 1 of 18 EDs between July 2020 and April 2021 with acute coronary syndrome as defined by an institutional-modified HEART score completed by their treating physician or midlevel, no evidence of ST-elevation myocardial infarction, and an index or serial gender-adjusted hs-trop within normal limits. The primary outcome was MACE within 30 days of index ED encounter. A detailed case review was then performed for those patients experiencing a MACE.ResultsOf the 9084 patients who had single or serial normal troponins, 31 (0.34%; confidence interval [CI] 0.23%-0.48%) experienced MACE. Of the 6140 patients with 2 normal hs-trop and a delta (change in troponin) <4, 27 patients (0.44%; CI 0.29%-0.64%) experienced MACE. Only 1 of the 69 patients with 2 normal hs-trop results but delta (change in troponin) ≥ 4 (1.45%; CI 0.04%-7.81%) suffered MACE. This patient was classified as non-low risk by our institutional HEART score. Of 7498 patients with an index hs-trop <LOQ, 14 (0.19%; CI 0.10%-0.31%) experienced MACE, with 57% (N = 8) deemed non-low risk by HEART score.ConclusionPatients with 2 normal hs-trop values in the ED are unlikely to suffer 30-day MACE. Although it remains unclear whether patients with delta (change in troponin) ≥4 despite normal troponins will have a 30-day MACE, this situation is rare. Additionally, a single index hs-trop <6 ng/L demonstrated a low risk for 30-day MACE independent of the institutional HEART score.

| S-EPMC10560008 | biostudies-literature

Adverse events in patients with return emergency department visits.

Project description:ObjectivesThis study describes the proportion of emergency department (ED) returns within 7 days due to adverse events, defined as adverse outcomes related to healthcare received.DesignProspective cohort study.SettingWe used an electronically triggered adverse event surveillance system at a tertiary care ED from May to June 2010 to examine ED returns within 7 days of index visit.ParticipantsOne of three trained nurses determined whether the visit was related to index emergency care. For such records, one of three trained emergency physicians conducted adverse event determinations.Main outcome measureWe determined adverse event type and severity and analysed the data with descriptive statistics, χ(2) tests and logistic regression.ResultsOf 13,495 index ED visits, 923 (6.8%) were followed by ED returns within 7 days. The median age of all patients was 47 years and 52.8% were women. After nursing review, 211 cases required physician review. Of these, 53 visits were adverse events (positive predictive value (PPV)=5.7%, 95% CI 4.4% to 7.4%) and 30 (56.6%) were preventable. Common adverse event types involved management, diagnostic or medication issues. We observed one potentially preventable death and 58.5% of adverse events resulting in transient disability. The PPV of a modified trigger with a cut-off of return within 72 h, resulting in admission was 11.9% (95% CI 6.8% to 18.9%).ConclusionsOur electronic trigger efficiently identified adverse events among 12% of patients with ED returns within 72 h, requiring hospital admission. Given the high degree of preventability of the identified adverse events, this trigger also holds promise as a performance measurement tool.

| S-EPMC4316869 | biostudies-literature

Clinical Effectiveness of Cardiac Noninvasive Diagnostic Testing in Patients Discharged From the Emergency Department for Chest Pain.

Project description:Background More than 4 million cardiac noninvasive diagnostic tests are performed annually in the United States. However, questions remain regarding their effectiveness in improving clinical outcomes. We sought to evaluate whether noninvasive diagnostic tests were associated with lower rates of myocardial infarction or cardiovascular death when compared with no testing. Methods and Results We performed a retrospective, population-based cohort study of adults evaluated for chest pain and discharged home from an emergency department in Ontario, Canada. Propensity score matching was employed to reduce confounding between the testing and nontesting groups. There were 370 863 patients evaluated in our cohort. Rates of the composite outcome were low for both groups after propensity-score matching (0.29% and 0.78% for the nontesting group at 90 days and 1 year, respectively, and 0.34% and 0.68% for the noninvasive diagnostic test group at 90 days and 1 year respectively). Over 1 year, patients undergoing noninvasive diagnostic testing had a small but statistically significant lower hazard of developing the composite outcome of myocardial infarction or cardiovascular mortality (hazard ratio, 0.87; 95% CI, 0.78-0.96 [P<0.01]), which appears to be driven by the high-risk subgroup (hazard ratio, 0.75; 95% CI, 0.61-0.92 [P<0.01]). Conclusions We report a lower observed rate of the composite outcome of cardiovascular death or myocardial infarction associated with noninvasive diagnostic testing following evaluation for chest pain in the emergency department. This lower rate was driven by the high-risk subgroup. These results suggest that risk-based testing should be considered for patients discharged from the emergency department for chest pain.

| S-EPMC6898808 | biostudies-literature

The prevalence of non-cardiac chest pain (NCCP) using emergency department (ED) data: a Northern Ireland based study.

Project description:The aim of this study was to assess the frequency of chest pain presentations and the subsequent non-cardiac chest pain diagnoses in an emergency department (ED) over a 3 year period.Administrative data on ED attendances to an urban general hospital in Northern Ireland between March 2013 and March 2016 were used. Data were coded and analysed to estimate frequencies of 'chest pain' presentation and the subsequent diagnoses for each year.Both chest pain presentations and chest pain presentations with a subsequent diagnosis of unknown cause increased each year. In total, 58.7% of all chest presentations across 3 years resulted in a non-cardiac diagnosis of either 'anxiety', 'panic' or 'chest pain of unknown cause'.There is a significant amount of patients in the ED leaving with a non-cardiac diagnosis, following an initial presentation with chest pain.Given the link between non-cardiac chest pain and frequent use of services, the degree of repeat attendance should be investigated.

| S-EPMC5550987 | biostudies-other

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data