An AI-Based CDSS for Integrated Management of Patients With Acute Ischemic Stroke(GOLDEN BRIDGE II)

Capital Medical University

Status: Unknown

Conditions: Stroke

Treatments: Device: AI-based CDSS

Study type: Interventional

Funder types: Other

Identifiers

NCT04524624

KY 2020-016-02

Details and patient eligibility

About

This study will conduct a cluster randomized controlled trial to evaluate the impact of an artificial intelligence-based clinical decision support system for the integrated management of patients with acute ischemic stroke on the adherence to guideline-based therapies and the incidence of new clinical vascular events.

Full description

Artificial intelligence (AI) and clinical decision support system (CDSS) have demonstrated great progress in the diagnosis and treatment of cerebrovascular diseases.CDSS can use computer technology to simulate and extend expert knowledge and empirical evidence in a timely and efficient manner. The combination of AI and CDSS is a potential solution to the shortage of medical resources and can improve the quality of and promote the standardization of medical services. At intervention sites, neurologists will receive support on use of the AI-based CDSS.

Aim: To evaluate the effectiveness of an AI-based CDSS for stroke management in patients with acute ischemic stroke within 7 days of symptom onset.

Intervention: An AI-based CDSS for an integrated management of patients with acute ischemic stroke. The strategy includes automatically identifying acute stroke lesions and lesion patterns, automated classification of stroke subtypes and mechanisms, evidence-based alerts, and guideline-recommended secondary stroke prevention strategies.

Eighty eligible hospitals in china, stratified by hospital capacity (secondary grade or tertiary) and economic-geographical regions (eastern, central, and western), will be randomized into either the CDSS group or the usual care group.

Enrollment: 21,689 estimated patients

Sex: All

Ages: 18 to 90 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Cluster Inclusion Criteria:

  • Secondary or tertiary hospitals with an emergency department and neurologic wards that receive patients with AIS.
  • Hospitals with available brain MRI scans (1.5T or 3.0T).

• Patient Inclusion Criteria:

  • Patients of 18 years or older.
  • Patients admitted with neurological deficit consistent with ischemic stroke within 7 days of of symptoms onset. (*Symptom onset is defined by the "last seen normal" principle)
  • Confirmation of new ischemic stroke by objective modality of CT scan and MRI (had relevant lesions on DWI).
  • Informed consent from patient or legally authorised representative (primarily spouse, parents, adult children, otherwise indicated).

Exclusion criteria

• Cluster Exclusion Criteria:

  • Grade-one hospitals and rural hospitals.
  • The specialized hospitals, such as women and children specialist hospital and tumor hospital.
  • Hospitals with less than 20 patients with suspected AIS per month.

• Patient Exclusion Criteria:

  • Diagnosed DWI negative stroke.
  • Diagnosed other types of cerebrovascular diseases, such as transient ischaemic attack, hemorrhagic stroke, cerebral venous sinus thrombosis, and so on.
  • Diagnosed non cerebral vascular disease, such as stroke mimic, seizures, central nervous system infections, metabolic encephalopathy, and so on.
  • Received carotid endarterectomy (CEA) and carotid angioplasty and stenting (CAS).
  • Involving in other investigational drug or device clinical trials.
  • Patients with malignant disease and life expectancy of less than 3 months or patients who are unable to complete the study for other reasons.
  • Women who are pregnant or postpartum (≤6 weeks).
  • Patients refuse to participate in this study.

Trial design

Primary purpose: Prevention

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: Single Blind

---

21,689 participants in 2 patient groups

AI-based CDSS

Experimental group

Description:

1. Automatically identifying acute ischemic stroke lesions on DWI. 2. Classification of stroke subtypes and mechanisms. 3. Evidence-based alerts and guidelines for early stroke management. 4. Guideline-recommended secondary stroke prevention strategies.

Treatment:

Device: AI-based CDSS

Usual Care

No Intervention group

Description:

Usual Care