Ignite Creation Date:
2025-12-25 @ 1:31 AM
Ignite Modification Date:
2025-12-27 @ 11:05 PM
Study NCT ID:
NCT04757194
Status:
COMPLETED
Last Update Posted:
2025-01-08
First Post:
2021-02-03
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Machine Learning Assisted Differentiation of Low Acuity Patients at Dispatch
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D004630', 'term': 'Emergencies'}], 'ancestors': [{'id': 'D020969', 'term': 'Disease Attributes'}, {'id': 'D010335', 'term': 'Pathologic Processes'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}]}}, 'documentSection': {'largeDocumentModule': {'largeDocs': [{'date': '2021-02-09', 'size': 290416, 'label': 'Study Protocol and Statistical Analysis Plan', 'hasIcf': False, 'hasSap': True, 'filename': 'Prot_SAP_000.pdf', 'typeAbbrev': 'Prot_SAP', 'uploadDate': '2021-02-09T04:27', 'hasProtocol': True}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'SINGLE', 'whoMasked': ['INVESTIGATOR'], 'maskingDescription': 'Analyst masked to treatment group allocation in final analysis. Outcomes extracted algorithmically from databases.'}, 'primaryPurpose': 'HEALTH_SERVICES_RESEARCH', 'interventionModel': 'PARALLEL', 'interventionModelDescription': 'Groups of patients experiencing a resource constrained situation randomized 1:1 at time of inclusion to control/intervention arms'}, 'enrollmentInfo': {'type': 'ACTUAL', 'count': 2499}}, 'statusModule': {'overallStatus': 'COMPLETED', 'startDateStruct': {'date': '2021-02-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-01', 'completionDateStruct': {'date': '2024-11-30', 'type': 'ACTUAL'}, 'lastUpdateSubmitDate': '2025-01-07', 'studyFirstSubmitDate': '2021-02-03', 'studyFirstSubmitQcDate': '2021-02-11', 'lastUpdatePostDateStruct': {'date': '2025-01-08', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2021-02-17', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2024-11-30', 'type': 'ACTUAL'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Proportion of RCS where the first available ambulance was dispatched to the patient with the highest National Early Warning Score (NEWS).', 'timeFrame': 'Upon ambulance response (Within 8 hours of dispatch)', 'description': 'NEWS is a widely used and well-validated scoring algorithm based on objective patient vital signs, which are not causally dependent on the outcomes used to train the machine learning models investigated in this study. NEWS values will be based on the first set of vital signs obtained by ambulance nurses upon making contact with the patient. NEWS is measured on a 0-21 scale, with higher values corresponding to patients at higher risk for deterioration.'}], 'secondaryOutcomes': [{'measure': 'Difference in composite outcome measure score between patients with immediate vs. delayed response.', 'timeFrame': 'Up to 30 days', 'description': 'This measure investigates a composite score consisting of the outcomes used to train the machine learning models. The composite score is generated by identifying the following patient outcomes and assigning the corresponding weights:\n\nAbnormal intitial Arway/Breathing/Circulation findings by ambulance crew (4) Emergent (lights and sirens) transport to the hospital (2) Provision of prehospital interventions (1) Admission to in-patient care or mortality within 30 days (1)\n\nThis results in a score from 0-8, with higher scores representing more'}, {'measure': 'Difference in National Early Warning Score (NEWS) between patients with immediate vs. delayed response.', 'timeFrame': 'Upon ambulance response (Within 8 hours of dispatch)', 'description': 'Per primary outcome'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'conditions': ['Emergencies']}, 'referencesModule': {'references': [{'pmid': '31834920', 'type': 'BACKGROUND', 'citation': 'Spangler D, Hermansson T, Smekal D, Blomberg H. A validation of machine learning-based risk scores in the prehospital setting. PLoS One. 2019 Dec 13;14(12):e0226518. doi: 10.1371/journal.pone.0226518. eCollection 2019.'}, {'pmid': '32198303', 'type': 'BACKGROUND', 'citation': 'Spangler D, Edmark L, Winblad U, Collden-Benneck J, Borg H, Blomberg H. Using trigger tools to identify triage errors by ambulance dispatch nurses in Sweden: an observational study. BMJ Open. 2020 Mar 19;10(3):e035004. doi: 10.1136/bmjopen-2019-035004.'}], 'seeAlsoLinks': [{'url': 'https://github.com/dnspangler/openTriage', 'label': 'Source code for risk assessment tool used in intervention'}]}, 'descriptionModule': {'briefSummary': 'BACKGROUND:\n\nAt Emergency Medical Dispatch (EMD) centers, Resource Constrained Situations (RCS) where there are more callers requiring an ambulance than there are available ambulances are common. At the EMD centers in Uppsala and Västmanland, patients experiencing these situations are typically assigned a low-priority response, are often elderly, and have non-specific symptoms. Machine learning techniques offer a promising but largely untested approach to assessing risks among these patients.\n\nOBJECTIVES:\n\nTo establish whether the provision of machine learning-based risk scores improves the ability of dispatchers to identify patients at high risk for deterioration in RCS.\n\nDESIGN:\n\nMulti-centre, parallel-grouped, randomized, analyst-blinded trial.\n\nPOPULATION:\n\nAdult patients contacting the national emergency line (112), assessed by a dispatch nurse in Uppsala or Västmanland as requiring a low-priority ambulance response, and experiencing an RCS.\n\nOUTCOMES:\n\nPrimary:\n\n1\\. Proportion of RCS where the first available ambulance was dispatched to the patient with the highest National Early Warning Score (NEWS) score\n\nSecondary:\n\n* Difference in composite risk score consisting of ambulance interventions, emergent transport, hospital admission, intensive care, and mortality between patients receiving immediate vs. delayed ambulance response during RCS.\n* Difference in NEWS between patients receiving immediate vs. delayed ambulance response during RCS.\n\nINTERVENTION:\n\nA machine learning model will estimate the risk associated with each patient involved in the RCS, and propose a patient to receive the available ambulance. In the intervention arm only, the assessment will be displayed in a user interface integrated into the dispatching system.\n\nTRIAL SIZE:\n\n1500 RCS each consisting of multiple patients randomized 1:1 to control and intervention arms'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'healthyVolunteers': False, 'eligibilityCriteria': "Inclusion Criteria:\n\n* Identification of a resource constrained situation by ambulance director (i.e., 2 or more patients awaiting an ambulance response)\n* Assigned priority 2A or 2B (Low-priority ambulance response) by dispatch nurse call-taker\n* Valid Swedish personal identification number collected at dispatch\n* Age \\>= 18 years\n\nExclusion Criteria:\n\n* Relevant calls received more than 30 minutes apart\n* Logistical factors (eg. the patients' geographical locations) affect the ambulance assignment decision\n* On scene risk factors (eg. a patient is outdoors and risks hypothermia) or risk mitigators (eg. healthcare staff already on-scene with a patient) affect the ambulance assignment decision"}, 'identificationModule': {'nctId': 'NCT04757194', 'acronym': 'MADLAD', 'briefTitle': 'Machine Learning Assisted Differentiation of Low Acuity Patients at Dispatch', 'organization': {'class': 'OTHER', 'fullName': 'Uppsala University Hospital'}, 'officialTitle': 'Machine Learning Assisted Differentiation of Low Acuity Patients at Dispatch: A Randomized Controlled Trial', 'orgStudyIdInfo': {'id': 'SVLC001'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'Intervention', 'description': 'Calculation of risk assessment score by machine learning algorithm and display of risk assessment information to dispatch nurses. Staff encouraged but not required to comply with suggested ranking.', 'interventionNames': ['Diagnostic Test: openTriage - Alitis algorithm']}, {'type': 'NO_INTERVENTION', 'label': 'Control', 'description': 'Ambulance dispatch per standard of care'}], 'interventions': [{'name': 'openTriage - Alitis algorithm', 'type': 'DIAGNOSTIC_TEST', 'description': 'A machine learning algorithm (Gradient boosting) applied to structured data collected in the Alitis Clinical Decision Support system, patient demographics, and free-text notes.', 'armGroupLabels': ['Intervention']}]}, 'contactsLocationsModule': {'locations': [{'city': 'Västerås', 'state': 'Västmanland County', 'country': 'Sweden', 'facility': 'Västmanland hospital Västerås', 'geoPoint': {'lat': 59.61617, 'lon': 16.55276}}, {'city': 'Uppsala', 'country': 'Sweden', 'facility': 'Uppsala University Hospital', 'geoPoint': {'lat': 59.85882, 'lon': 17.63889}}], 'overallOfficials': [{'name': 'Hans Blomberg, MD, PhD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'Uppsala University Hospital'}]}, 'ipdSharingStatementModule': {'infoTypes': ['STUDY_PROTOCOL', 'ANALYTIC_CODE'], 'timeFrame': 'Upon publication', 'ipdSharing': 'YES', 'description': 'Individual level data available upon reasonable request to authors after publication', 'accessCriteria': 'Researchers with ethics board approved research plan'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Uppsala University Hospital', 'class': 'OTHER'}, 'collaborators': [{'name': 'Region Västmanland', 'class': 'OTHER'}], 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Medical Director', 'investigatorFullName': 'Hans Blomberg', 'investigatorAffiliation': 'Uppsala University Hospital'}}}}