Skip to content

Using Artificial Intelligence to Help Detect Early and Recent Strokes on Brain Scans Without Contrast: A Study in Patients with Suspected Stroke

AI-Powered Real-Time Detection and Quantitative Analysis of Bilateral acute and sub-acute Infarcts Using Non-Contrast Computed Tomography Imaging: A Deep Learning-Based Approach - NIL

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
CTRI
Registry ID
CTRI/2025/04/084499
Enrollment
100
Registered
2025-04-09
Start date
Unknown
Completion date
Unknown
Last updated
2025-04-28

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Health Condition 1: G988- Other disorders of nervous system

Interventions

None listed

Sponsors

Dr.Abdul Majith Seeni Mohammed
Lead Sponsor

Eligibility

Inclusion criteria

Inclusion criteria: 1)Patients aged 18 years and above. 2)Presenting with acute or subacute neurological symptoms suggestive of stroke (e.g., weakness, slurred speech, visual disturbances, altered sensorium). 3)Undergoing non-contrast CT (NCCT) of the brain as part of initial evaluation. 4)Undergoing MRI with diffusion-weighted imaging (DWI) within 72 hours of the NCCT for diagnostic correlation. 5)Symptom onset within 1 to 72 hours prior to imaging. 6)Informed consent obtained from the patient or legally authorized representative

Exclusion criteria

Exclusion criteria: 1)Poor-quality NCCT images due to motion artifacts or technical issues. 2)Presence of non-ischemic pathology on CT such as hemorrhage, tumors, trauma, or postoperative changes. 3)History of prior stroke in the same vascular territory. 4)Inability to undergo MRI, including contraindications such as pacemakers, metallic implants, severe claustrophobia, or clinical instability. 5)Patients who have received reperfusion therapy (e.g., thrombolysis or thrombectomy) before the baseline NCCT. 6)Incomplete clinical, laboratory, or follow-up imaging data that prevents accurate analysis.

Design outcomes

Primary

MeasureTime frame
Diagnostic accuracy of AI in detecting bilateral MCA infarcts on non-contrast CT, measured by sensitivity, specificity, PPV, NPV, and AUC-ROC.Timepoint: Real-time analysis immediately after CT scan

Secondary

MeasureTime frame
1)Diagnostic accuracy of AI in detecting infarcts across ASPECTS severity categories (0 4, 5 7, 8 10), measured by sensitivity. 2)Time-to-diagnosis comparison between AI & radiologists, measured in minutes from CT scan completion to diagnosis report generation. 3)Clinical impact of AI on decision-making, measured by the proportion of cases with expedited thrombolysis, avoided MRI, & discordant reads requiring MRI confirmation.Timepoint: 1)Within 1 hour of AI analysis. 2)mmediately after CT scan completion. 3)Within 24 48 hours post-imaging.

Countries

India

Contacts

Public ContactDrMuthiah Pitchandi

Saveetha medical college and hospital, Saveetha institute of medical and technical sciences

drmuthiahmd@gmail.com919843175404

Outcome results

None listed

Source: CTRI (via WHO ICTRP) · Data processed: Feb 4, 2026