Hemorrhage Stroke Decision Making Model Based Deep Learning (BrainHemoAI System)

Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age8+
SponsorSecond Affiliated Hospital of Nanchang University

About this trial

Although hemorrhagic stroke also has the characteristics of high mortality and disability rates, and constitutes a major public health problem worldwide, there is a relative lack of in-depth research teams for hemorrhagic stroke in China. The current preoperative imaging evaluation of spontaneous cerebral hemorrhage is still limited to the traditional Tada formula, and there are subjective differences in diagnosis among different doctors, making it difficult to achieve homogenization in clinical decision-making. Hemorrhagic stroke is a common and frequently occurring disease in Jiangxi Province. Therefore, establishing a new diagnosis and treatment system focused on hemorrhagic stroke can not only fill the research gap in this field in China, improve the accuracy and homogeneity of hemorrhagic stroke diagnosis and treatment, but also promote related research progress to reduce the mortality and disability rates of this disease and improve the clinical prognosis of patients.

Eligibility criteria

This trial accepts healthy volunteers

Qualifiers

Age >= 8 years old;

Patients diagnosed with spontaneous hemorrhagic stroke based on medical history and auxiliary examinations;

Received non-contrast computed tomography (NCCT) in the outpatient or emergency department;

Treated in accordance with standard clinical guidelines during hospitalization;

Disqualifiers

Had undergone surgical treatment in another hospital before admission;

Was in a state of shock upon admission;

Had severe heart, liver, or kidney dysfunction or other life-threatening systemic diseases;

Died during hospitalization;

Trial population

Spontaneous hemorrhagic stroke, including parenchymal hemorrhage, subarachnoid hemorrhage, intraventricular hemorrhage, and subdural hemorrhage(including chronic subdural hemorrhage).

Trial design

Design model

Cohort

Time perspective

Retrospective

Treatments tested in this trial

  • Large language model

    Diagnostic test

    Automatical diagnosis, treatment decision-making, and risk prediction after spontaneous intracerebral hemorrhage via a trained deep learning larger language model.

Treatment groups

No treatment groups listed

Trial outcomes

Primary outcomes

1

Area Under Curve

90-day and 180-day mRS score, survival status, functional independence (Barthel index).

Time frame
90-day and 180-day

Secondary outcomes

1

Sensitivity ,Specificity,True Positive Rate,False Positive Rate

Including hospital stay, ICU stay, hospitalization costs, rebleeding, delayed cerebral ischemia, intracranial infection, and hydrocephalus flow surgery needs

Time frame
Baseline (admission), 24 hours postoperatively, 3 days postoperatively, 7 days postoperatively, discharge, 90-day follow-up, 180-day follow-up

Other outcomes

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

Second Affiliated Hospital of Nanchang University

Lead sponsor

First Affiliated Hospital of Gannan Medical University

Collaborator

Zhejiang University

Collaborator

Ganzhou City People's Hospital

Collaborator

The First People's Hospital of Xiushui

Collaborator

Jiujiang No.1 People's Hospital

Collaborator

Renmin Hospital of Wuhan University

Collaborator

First Affiliated Hospital of Zhejiang University

Collaborator