How are you taking part in this consultation?

You will not be able to change how you comment later.

You must be signed in to answer questions

    The content on this page is not current guidance and is only for the purposes of the consultation process.

    Artificial intelligence (AI) software to help clinical decision making in stroke

    Closed for comments This consultation ended on at   Request commenting lead permission

    4 Recommendations for further research

    4.1 The committee recommended more research on the AI-software technologies in all 3 indications, specifically comparing diagnostic accuracy and outcomes of an AI technology plus a clinician looking at the scans, compared with clinician alone. Ideally, studies would be prospective, they should be done in comprehensive and acute stroke centres, describe the level of experience of the clinicians interpreting the CT brain scans and include both people who had and did not have a particular type of treatment. Studies should also consider reporting data separately in subgroups when using the technologies may be particularly useful or less effective (for example in older people, particularly those over the age of 80, with small vessel disease and calcification of the cerebrovasculature). The specific research recommendations for each indication are detailed in sections 4.2 to 4.4.

    4.2 For guiding thrombolysis treatment decisions for people with suspected acute stroke using a non-enhanced CT scan research is recommended on:

    • the accuracy of Accipio, Aidoc, Biomind, Brainscan CT, CINA head, e-Stroke, Neuro Solution, qER, RapidAI or Viz plus clinician compared with clinician alone, in identifying stroke and determining whether it is ischaemic or haemorrhagic

    • test failure rate with causes of failures

    • time to thrombolysis

    • short-term clinical outcomes with the National Institutes of Health Stroke Scale (NIHSS) at 24 hours after treatment and modified Rankin Scale (mRS) at 90 days.

    4.3 For CT angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with ischaemic stroke using CT angiography, research is recommended on:

    • the accuracy of Aidoc, CINA head, e-Stroke, RapidAI or Viz plus clinician compared with clinician alone, in determining whether or not thrombectomy is appropriate

    • test failure rate with causes of failures

    • time to thrombectomy

    • short-term clinical outcomes with the National Institutes of Health Stroke Scale (NIHSS) at 24 hours after treatment and modified Rankin Scale (mRS) at 90 days.

    4.4 For guiding mechanical thrombectomy treatment decisions for people with ischaemic stroke using CT perfusion after a CT angiography brain scan, research is recommended on:

    • the accuracy of Cercare (Perfusion), CT Perfusion 4D, e-Stroke, icobrain ct, RapidAI or Viz plus clinician compared with clinician alone, in determining whether or not thrombectomy is appropriate

    • test failure rate with causes of failures

    • time to thrombectomy

    • short-term clinical outcomes with the National Institutes of Health Stroke Scale (NIHSS) at 24 hours after treatment and modified Rankin Scale (mRS) at 90 days.