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) < 1 month and all-cause mortality < 1 month. Comparisons of the predictive accuracies among random forest, logistic regression, support-vector clustering (SVC), and K-nearest neighbor (KNN) models were also performed.Results: Predicting MACE using the random forest model produced areas under the curves (AUC) of 0.915 for AMI < 1 month and 0.999 for all-cause mortality < 1 month. The random forest model had better predictive accuracy than logistic regression, SVC, and KNN. We further integrated the AI prediction model with the HIS to assist physicians with decision-making in real time. Validation of the AI prediction model by new patients showed AUCs of 0.907 for AMI < 1 month and 0.888 for all-cause mortality < 1 month.Conclusions: An AI real-time prediction model is a promising method for assisting physicians in predicting MACE in ED patients with chest pain. Further studies to evaluate the impact on clinical practice are warranted.

Hospice and palliative care has been recognized as an essential part of emergency medicine; however, there is no consensus on the optimal model for the delivery of hospice and palliative care in the emergency department (ED). Therefore, we conducted a novel implementation in a tertiary medical center in Taiwan. In the preintervention period, we recruited a specialist for hospice and palliative medicine in the ED to lead our intervention. In the early stage of the intervention, starting on July 1, 2014, we encouraged and funded ED physicians and nurses to receive training for hospice and palliative medicine and residents of emergency medicine to rotate to the hospice ward. In the late stage of the intervention, we initiated educational programs in the ED, an interdisciplinary meeting with the hospice team every month, sharing information and experience via a cell phone communication app, and setting aside an emergency hospice room for end-of-life patients. We compared the outcomes among pre-, during, and postintervention periods. Compared with 4 in the preintervention period, the cases of do not resuscitate (DNR) per month increased significantly to 30.1 in the early stage of intervention, 23.9 in late stage of intervention, and 34.6 in the postintervention period (all P < .001 compared with the preintervention period). Compared with 10.8% in the preintervention period, the ratio of DNR orders signed in the ED/total DNR orders signed in the study hospital was increased to 17.1% in early stage of intervention, 12.5% in late stage of intervention, and 22.8% in postintervention. Compared with zero in preintervention and early intervention, the cases of consultation with the hospice team increased significantly to 19 cases per month in the late stage of intervention and postintervention. The ability of nurses in hospice and palliative care, including knowledge and the timing and method of consultation with the hospice team, was also significantly improved. We successfully implemented a novel model of hospice and palliative care in the ED via a champion, education, and close collaboration with the hospice team, which could be an important reference for other EDs and intensive care unit in the future.

Objective: Chronic pain (CP) may increase the risk for major adverse cardiac and cerebrovascular events (MACCEs); however, this issue is still unclear in the Asian population. We conducted this study to delineate it.Design: From the Taiwan National Health Insurance Research Database, we identified 17,614 participants (<65 years) with CP and matched them by age and sex at a 1:2 ratio to participants without CP, who made up the comparison cohort. Several causes of CP and its underlying comorbidities were also analyzed.Outcome Measure: A comparison of MACCE occurring in the two cohorts was performed via follow-up until 2015.Results: The mean age (SD) was 50.2 (11.5) years and 50.4 (11.7) years in participants with and without CP, respectively. In both cohorts, the percentage of female participants was 55.5%. Common causes of CP were spinal disorders (23.9%), osteoarthritis (12.4%), headaches (11.0%), gout (10.2%), malignancy (6.2%), and osteoporosis (4.5%). After adjusting for hypertension, diabetes, chronic obstructive pulmonary disease, renal diseases, hyperlipidemia, liver diseases, dementia, and depression, participants with CP had a higher risk for MACCE than those without CP (adjusted hazard ratio [AHR] = 1.3, 95% confidence interval [CI] = 1.3 − 1.4). After conducting subgroup analyses, an increased risk was also found for all-cause mortality (AHR = 1.4, 95% CI = 1.1 − 1.8), acute myocardial infarction (AHR = 1.2, 95% CI = 1.0 − 1.4), and stroke (AHR = 1.3, 95% CI = 1.3 − 1.4).Conclusions: CP is associated with increased occurrence of MACCE. Early detection and interventions for CP are suggested.