[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100659425":3},{"organization":4,"outcomesModule":7,"designInfo":38,"detailedDescription":44,"studyPopulation":37,"armGroups":45,"interventions":56,"overallOfficials":60,"centralContacts":65,"locations":37,"responsibleParty":74,"collaborators":76,"id":79,"slug":80,"hasResults":81,"nctId":82,"briefTitle":83,"officialTitle":84,"acronym":85,"eligibilityCriteria":86,"healthyVolunteers":81,"sex":87,"minAge":88,"maxAge":37,"enrollmentInfo":89,"targetDuration":37,"studyType":92,"phases":93,"briefSummary":95,"conditions":96,"keywords":99,"overallStatus":104,"whyStopped":37,"lastUpdateSubmitDate":105,"lastUpdatePostDateStruct":106,"startDateStruct":109,"completionDateStruct":111,"leadSponsor":113,"locationsCount":37},{"fullName":5,"class":6},"Region Skane","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":13,"otherOutcomes":37},[9],{"measure":10,"description":11,"timeFrame":12},"EDLOS","Emergency department (ED) length of stay (LOS) in minutes in patients discharged home from the ED","Up to 24 hours",[14,18,22,25,28,31,34],{"measure":15,"description":16,"timeFrame":17},"30-day AMI and MACE in discharged patients","30-day (including index visit) acute myocardial infarction (AMI) and major adverse cardiac events (MACE) incidence in discharged patients.","30 days from ED arrival",{"measure":19,"description":20,"timeFrame":21},"30-day ED revisits with admissions","ED revisits within 30 days with admissions to inpatient care","Up to 30 days",{"measure":23,"description":24,"timeFrame":21},"Accuracy of AIDE-CP AMI prediction in all patients","Accuracy of AIDE-CP's 30-day AMI predictions (sensitivity, specificity, etc) in all patients; i.e. including patients where AIDE-CP is unavailable at the ED.",{"measure":26,"description":27,"timeFrame":12},"Time to disposition in in all patients","Time from ED arrival to decision regarding hospital admission or discharge home from the ED, in all patients",{"measure":29,"description":30,"timeFrame":12},"Proportion of patients discharged from the ED","Number of patients discharged from the ED divided by all included patients",{"measure":32,"description":33,"timeFrame":12},"Difference in physician estimates before and after AIDE-CP access.","Difference in physician estimates of 30-day AMI risk before versus after AIDE-CP access.",{"measure":35,"description":36,"timeFrame":12},"Output of AIDE-CP versus physician risk group assignment","Difference in risk group assignment of AIDE-CP versus physician before and after AIDE-CP access",null,{"allocation":39,"interventionModel":40,"interventionModelDescription":37,"primaryPurpose":41,"observationalModel":37,"timePerspective":37,"maskingInfo":42},"RANDOMIZED","PARALLEL","DIAGNOSTIC",{"masking":43,"maskingDescription":37,"whoMasked":37},"NONE","The AIDE-CP1 trial is a multicenter, randomized controlled trial evaluating whether an artificial intelligence-based clinical decision support system can improve the management of adults presenting to emergency departments (EDs) with chest pain. AIDE-CP integrates age, sex, initial laboratory results, and ECG data to estimate the 30-day probability of acute myocardial infarction (AMI) and provides risk-based management recommendations.\n\nApproximately 4,500 unselected adult chest pain patients will be included across five Swedish EDs. Randomization occurs at the level of the study day, with AIDE-CP either available to clinicians or unavailable, in which case patients receive standard care. The primary outcome is ED length of stay among patients discharged from the ED. Secondary outcomes include 30-day AMI and major adverse cardiac events, admission and discharge rates, time to disposition, downstream healthcare utilization and costs, and effects on overall ED patient flow.\n\nA nested substudy of 400 patients will assess how AIDE-CP influences physicians' estimates of AMI probability and clinical decision-making. The trial is designed to determine whether integrating AI-based risk prediction into routine emergency care can accelerate patient management while maintaining safety, and to provide prospective evidence on the real-world clinical impact of AI-supported decision-making.",[46,52],{"label":47,"type":48,"description":49,"interventionNames":50},"Intervention","ACTIVE_COMPARATOR","AIDE-CP available",[51],"Other: AIDE-CP available",{"label":53,"type":54,"description":55,"interventionNames":37},"Control","NO_INTERVENTION","Standard care",[57],{"type":6,"name":49,"description":58,"armGroupLabels":59,"otherNames":37},"On randomized days, AIDE-CP is available to the ED physicians",[47],[61],{"name":62,"affiliation":63,"role":64},"Ulf Ekelund, MD, PhD","Region Skåne, Lund University","STUDY_CHAIR",[66,70],{"name":62,"role":67,"phone":68,"phoneExt":37,"email":69},"CONTACT","+4646176744","ulf.ekelund@gmail.com",{"name":71,"role":67,"phone":72,"phoneExt":37,"email":73},"Johanna Holme, MD","+46-176782","holme.johanna@gmail.com",{"type":75,"investigatorFullName":37,"investigatorTitle":37,"investigatorAffiliation":37,"oldNameTitle":37,"oldOrganization":37},"SPONSOR",[77],{"name":78,"class":6},"Lund University","100659425","ai-based-decision-support-in-acute-chest-pain-100659425",false,"NCT07864038","AI-based Decision Support in Acute Chest Pain","A Randomized Controlled Trial of an AI-based Decision Support in Emergency Department Chest Pain Patients (AIDE-CP1)","AIDE-CP1","Inclusion Criteria:\n\n* Non-traumatic chest pain, presentation to the ED.\n\nExclusion Criteria:\n\n* Patient declining participation.","ALL","18 Years",{"count":90,"type":91},4500,"ESTIMATED","INTERVENTIONAL",[94],"NA","The AIDE-CP1 trial will test whether a decision support tool based on artificial intelligence (AI) can improve care for patients who come to an emergency department with chest pain. The AI tool uses the patient's age, sex, first blood tests and ECG to estimate the risk of a heart attack within 30 days and suggests what to do next. About 4,500 patients at five Swedish emergency departments will be included. The study will examine whether the AI tool can shorten time spent in the emergency department while maintaining patient safety. It will also study healthcare use, costs, and how AI affects doctors' decisions.",[97,98],"Myocardial Infarction","Chest Pain",[100,101,102,103],"Emergency department","Artificial intelligence","Acute myocardial infarction","Chest pain","NOT_YET_RECRUITING","2026-10-06",{"date":107,"type":108},"2026-10-07","ACTUAL",{"date":110,"type":91},"2027-01-18",{"date":112,"type":91},"2027-12",{"name":5,"class":6}]