Clinical Validation of an Artificial Intelligence-Based G-FAST Score in Patients With Stroke
ConditionStroke
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorXuanwu Hospital, Beijing
About this trial
This study aims to validate the clinical performance of an artificial intelligence (AI)-based automatic assessment system for the G-FAST score. The core comparison is the consistency and accuracy between AI-generated G-FAST results and standardized manual G-FAST assessments performed by trained professionals. The goal is to provide a convenient, efficient, and objective tool for acute stroke screening and early identification, reduce the subjective variability of manual scoring, and optimize the pre-hospital and in-hospital stroke assessment workflow.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Aged ≥ 18 years, of either sex.
Clinically diagnosed with stroke, and confirmed by cranial CT/MRI to have ischemic or hemorrhagic stroke.
Onset within 7 days.
Alert and oriented, able to cooperate with standardized video and audio data collection.
Disqualifiers
Neurological deficits caused by non-stroke etiologies (e.g., brain tumor, traumatic brain injury, encephalitis).
Patients with impaired consciousness, severe cognitive dysfunction, or psychiatric disorders that prevent cooperation with video collection and scale assessment.
Patients with severe visual or hearing impairment, or global aphasia, who are unable to follow instructions.
Critically ill patients requiring immediate cardiopulmonary resuscitation or endotracheal intubation, making video and audio data collection impossible.
Trial population
Patients with acute ischemic stroke who undergo G-FAST scale assessments using both AI and manual methods.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Not listed
Trial groups
297 Participants
are grouped into 2 trial groupsGroup A: AI-first interview group
Group B: Human-first group
Trial outcomes
Primary outcomes
1
Agreement between AI-generated and physician-scored G-FAST scale assessments
The agreement between the scores generated by the artificial intelligence (AI) system and the scores assigned by neurologists on G-FAST scale will be evaluated using weighted Kappa coefficients.
Time frame
within 7 days of acute stroke onsetSecondary outcomes
1
Agreement of AI System vs. Neurologists in Binary G-FAST Classification (Score ≥3 vs. <3)
Kappa coefficient will be calculated to evaluate the agreement between the artificial intelligence (AI) system and neurologist experts in the binary classification of G-FAST scale scores, defined as high risk (total score ≥3) vs. low risk (total score \<3) for large vessel occlusion stroke.
Time frame
within 7 days of acute stroke onset2
Bland-Altman Agreement Limit Analysis
A Bland-Altman plot will be constructed, with the difference between manual scores and AI scores on the vertical axis and the mean of the two scores on the horizontal axis. The limits of agreement (mean difference ± 1.96 × standard deviation) will be calculated.
Time frame
within 7 days of acute stroke onset3
Diagnostic performance analysis
Taking the manual score as the gold standard, a 2×2 contingency table was constructed to calculate the sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and Youden index of the AI scoring system for stratifying the G-FAST score (LVO ≥3 vs. non-LVO \<3). The ROC curve was plotted and the AUC was calculated.
Time frame
within 7 days of acute stroke onsetLocations
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Xuanwu Hospital, Beijing
Lead sponsor
Capital Medical University
Collaborator
People's Hospital of Beijing Daxing District
Collaborator
Beijing Tiantan Hospital
Collaborator
The First Hospital of Fangshan District,Beijing
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: