Harrison.ai AI for Stroke

by Harrison.ai  · Based in Australia →Global leaders in imaging AI. Raising the standard of patient care with AI.
Emergency Medicine Neurology Radiology

Contact for pricing
Regulatory Status Disclosed

Overview

Harrison.ai AI for Stroke (integrated within the Harrison.ai CT Brain solution) is a clinical decision-support and triage tool designed to assist in the rapid identification of acute ischemic stroke. Unlike traditional stroke AI tools that focus primarily on identifying large vessel occlusions (LVOs) via CT angiography (CTA), this software analyzes the initial non-contrast head CT (NCCT) scan to triage acute infarcts based on actual brain tissue injury.

The tool is designed for:

  • Specialties: Radiologists, neuroradiologists, emergency medicine physicians, and stroke neurologists.
  • Care Settings: Emergency departments, urgent care centers, and acute care hospital networks.

Workflow Integration and Capabilities:

  • Early-Stage Triage: Operates on the very first non-contrast CT scan, allowing clinicians to prioritize suspected ischemic stroke cases for immediate follow-up and advanced imaging before a CTA is performed.
  • Broad Anatomical Coverage: Evaluates tissue injury across six distinct vascular territories and infarct locations, including the anterior cerebral artery (ACA), middle cerebral artery (MCA), posterior cerebral artery (PCA), cerebellar, basilar, and watershed regions.
  • PACS/RIS Integration: Seamlessly overlays findings directly onto existing PACS viewers with customizable sensitivity and specificity thresholds.
  • Multi-Projection Analysis: Displays localized findings across sagittal, axial, and coronal projections with scrollable slice views to reduce cognitive load during high-urgency interpretations.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • FDA-cleared AI acute infarct triage tool on non-contrast CT Brain.
  • Detects subtle infarcts across six vascular territories (ACA, MCA, PCA, cerebellar, basilar, and watershed infarcts).
  • Analyzes the very first scan (non-contrast head CT) to prioritize suspected ischemic stroke patients for follow-up and advanced imaging sooner.
  • Achieved up to 89.2% sensitivity on thin slices and 85.7% on thick slices, with greater than 80% sensitivity and specificity over multiple operating points.
  • Supports faster time to diagnosis and treatment by quickly identifying patients in the worklist for prioritized diagnostic and treatment pathways.
  • Reduces stress from chaotic worklists by surfacing emergent and incidental findings.
  • Offers comprehensive critical exam coverage on non-contrast CT Brain, including both hemorrhagic and ischemic stroke in one integration.
  • Provides AI results within minutes, supporting accelerated care pathways with AI-assisted Worklist Prioritization.
  • Features explainable AI with localization and confidence bars to improve interpretability.

Use Cases

  • Emergency and Acute Care (for rapid stroke triage and diagnosis).
  • Teleradiology.
  • Public and Private Hospitals.
  • Outpatient care.
  • Worklist prioritization for critical cases.
  • Reducing missed diagnoses of acute infarcts.

What Physicians Need to Know

Stroke Detection Speed
AI results are available within 90 seconds, supporting faster diagnosis and treatment pathways. The system can analyze CT brain scans and highlight potential abnormalities to radiologists within 10 minutes.
Brain MRI/CT Analysis
Harrison.ai's solution is FDA-cleared for acute infarct triage on non-contrast CT Brain. It detects subtle infarcts across six vascular territories (ACA, MCA, PCA, cerebellar, basilar, and watershed infarcts), triaging actual brain tissue injury rather than just vessel occlusions. The AI achieved up to 89.2% sensitivity on thin slices and 85.7% on thick slices, with greater than 80% sensitivity and specificity over multiple operating points. It offers comprehensive critical exam coverage on non-contrast CT Brain, covering both hemorrhagic and ischemic stroke in one integration. The platform can detect up to 130 findings on non-contrast head CT studies.
Large Vessel Occlusion Detection
Unlike many existing stroke AI solutions that focus solely on large vessel occlusion (LVO) in one or two vascular territories, Harrison.ai's system triages actual ischemic tissue damage across six vascular territories and mechanisms of infarct, offering a more comprehensive approach.
Triage Prioritization Speed
The AI analyzes the very first scan (non-contrast head CT) to prioritize suspected ischemic stroke patients for follow-up and advanced imaging sooner. AI results are available within 90 seconds, supporting immediate attention and accelerating care pathways. It helps reduce stress from chaotic worklists by surfacing emergent and incidental findings, managing critical patients up to 41% faster.
Mobile Notification System
The platform includes a notification feature and supports worklist triage to surface urgent findings, implying a system for alerting clinicians to prioritized cases.
Physician Tip

Harrison.ai's AI for Stroke offers a significant advantage by triaging acute infarcts on non-contrast CT, a finding often difficult to identify, and doing so across a broad range of six vascular territories. This capability, combined with rapid analysis (within 90 seconds), can lead to earlier prioritization of suspected ischemic stroke patients for advanced imaging and treatment. The system's ability to cover both hemorrhagic and ischemic stroke in a single integration streamlines workflow. Physicians can leverage the explainable AI with localization and confidence bars to enhance their diagnostic confidence and decision-making, particularly in high-pressure emergency settings. The tool aims to reduce worklist burden by highlighting critical cases, allowing for more focused and timely intervention.

Harrison.ai's solutions are designed for seamless integration into existing clinical workflows, with the user interface integrating directly with PACS and RIS. It provides a resizable, no-click overlay window displaying findings. The platform offers comprehensive critical exam coverage on non-contrast CT Brain, including both hemorrhagic and ischemic stroke, within a single integration, eliminating the need to juggle multiple point solutions. Harrison.ai also provides an Open Platform to facilitate the integration of third-party AI algorithms.

Details

Category Neurology AI, Radiology & Imaging AI, Triage & ER/ICU AI
Pricing Contact for pricing
  • Not publicly disclosed; operates on a zero-markup Open Platform model for third-party AI algorithms, with transparent pricing for infrastructure services
DeploymentCloud-based
Compliance
BAA AvailableUnknown AI-estimated
HIPAA CompliantUnknown AI-estimated
FDA Status 1 AI-estimated

Harrison.ai AI for Stroke is an FDA 510(k) cleared AI acute infarct triage tool for non-contrast CT Brain scans. It detects subtle infarcts across six vascular territories (ACA, MCA, PCA, cerebellar, basilar, and watershed infarcts), aiding in earlier stroke diagnosis and facilitating faster time to treatment.

Integrations
EHR Not specified
Specialties Emergency Medicine, Neurology, Radiology

Ratings & Reviews

No reviews yet. Be the first to review this tool!

Rate Harrison.ai AI for Stroke

Clinical Value
Ease of Use
Integration
Support & Docs
Value for Money

Videos

Product demos, reviews, and walkthroughs for Harrison.ai AI for Stroke.

View all on YouTube

Frequently Asked Questions

Harrison.ai's AI for Stroke is an FDA 510(k) cleared solution designed for acute infarct triage on non-contrast CT brain scans. It helps prioritize suspected ischemic stroke patients for follow-up, including advanced imaging, by identifying actual brain tissue injury across six vascular territories, a more comprehensive approach than many existing AI systems. This AI acts as a decision-support tool, surfacing findings and flagging priorities to assist radiologists in their workflow.
Harrison.ai's AI for Stroke has received FDA 510(k) clearance for acute infarct triage on non-contrast CT brain, marking its ninth FDA clearance and second Breakthrough Device Designation to reach marketing authorization. Clinical validation demonstrated up to 89.2% sensitivity on thin slices and 85.7% on thick slices, with greater than 80% sensitivity and specificity across multiple operating points. The AI was validated against confirmed infarcts using advanced imaging as the reference standard.
Unlike many existing stroke AI systems that focus on large vessel occlusion (LVO) detection, often on CT angiography (CTA), Harrison.ai's solution triages acute infarcts directly on the initial non-contrast head CT. This allows for earlier prioritization of suspected ischemic stroke cases by evaluating actual brain tissue injury across six vascular territories, rather than solely vessel occlusions.
The Harrison.ai AI for Stroke is intended as a triage and prioritization aid, not a comprehensive diagnostic tool, with the radiologist remaining the responsible clinician. While demonstrating high accuracy, prospective studies with larger and more diverse populations are needed to confirm broader applicability. Additionally, some scans might be incompatible with the AI tool's acquisition protocol, though this represents a small proportion of cases.
Harrison.ai operates an 'Open Platform' with a 'zero-markup model' for third-party AI algorithms, aiming to eliminate traditional platform fees that can range from 30-60%. This approach allows hospitals to invest directly in the AI. Furthermore, Harrison.ai is one of only two radiology AI companies with a device eligible for Medicare New Technology Add-on Payment (NTAP), which provides separate, additional Medicare payments.

Related Tools

DETECT-ME/CFS project
ME/CFS Research Foundation (Sponsor: Federal Ministry of Health (BMG))
Clinical Decision Support & Reference
The DETECT-ME/CFS project is developing an AI-supported clinical decision support system to improve the rapid and reliable diagnosis of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome.
Neurotrack
Neurotrack
Clinical Decision Support & Reference
Neurotrack is a cognitive care enablement platform that provides clinically validated, FDA class II device assessments and care planning support to identify and manage cognitive decline and dementia earlier and with greater accuracy.
LesionQuant
CorTechs Labs
Neurology AI
LesionQuant, an FDA-approved AI product by CorTechs Labs, is particularly useful for patients with multiple sclerosis. It provides brain structure data and quantifies the number, size, and location of lesions, comparing them to prior studies.
ExcelsiusGPS
Globus Medical
Neurology AI
ExcelsiusGPS™ is the first and only robotic navigation platform on the market that offers a comprehensive approach to spine and cranial procedures, from start to finish. The system enables repeatable and accurate trajectory alignment and navigation for placing screws, interbody implants, and cranial instruments.
Onera SleepMap
Onera B.V.
Neurology AI
Onera SleepMap is an AI-powered sleep analysis software that processes polysomnography data, part of Onera Health's innovative patch-based system for at-home and in-lab sleep studies. The system aims to make clinical-grade sleep diagnostics more accessible and user-friendly, providing comprehensive data comparable to traditional in-lab PSG.
JLK-NCCT
JLK-NCCT
Clinical Decision Support & Reference
JLK-NCCT is an AI software designed to assist in the analysis of non-contrast CT brain scans for the detection of acute ischemic stroke.

See all Neurology AI tools →

Suggest an Edit → | Last Verified: 2026-05-06 | First Added: 2026-05-06

Investors who backed Harrison.ai AI for Stroke

Funded through the company that built this tool.

AI Tool Finder
AI-powered search. Results may not be comprehensive.