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    The content on this page is not current guidance and is only for the purposes of the consultation process.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

    1 Recommendations

    NICE is aware that companies are reviewing their CE marking in response to changing regulations and advances in digital health technologies.

    1.1 There is insufficient evidence to recommend the routine use of artificial intelligence (AI) software to help clinical decision making in stroke (see sections 1.2 to 1.4). Further research is needed on the technologies to understand their diagnostic accuracy and impact on clinical outcomes (see section 1.5) when used alongside clinician interpretation.

    1.2 There is insufficient evidence to recommend the routine use of the following technologies for guiding thrombolysis treatment decisions for people with suspected acute stroke using a non-enhanced CT scan:

    • Accipio (MaxQ AI)

    • Aidoc (Aidoc)

    • Biomind (Biomind.ai)

    • Brainscan CT (Brainscan.ai)

    • CINA Head (Avicenna)

    • e-Stroke (Brainomix)

    • Neuro Solution (Nanox.AI)

    • qER (Qure.ai)

    • RapidAI (Ischemaview)

    • Viz (Viz.ai)

    1.3 There is insufficient evidence to recommend the routine use of the following technologies for guiding mechanical thrombectomy decisions for people with an ischaemic stroke using CT angiography:

    • Aidoc (Aidoc)

    • CINA head (Avicenna)

    • e-Stroke (Brainomix)

    • RapidAI (Ischemaview)

    • Viz (Viz.ai)

    1.4 There is insufficient evidence to recommend the routine use of the following technologies for guiding mechanical thrombectomy treatment decisions for people with ischaemic stroke using CT perfusion after a CT angiography brain scan:

    • Cercare (Perfusion) (Cercare Medical)

    • CT Perfusion 4D (GE Healthcare)

    • e-Stroke (Brainomix)

    • icobrain ct (icometrix)

    • RapidAI (Ischemaview)

    • Viz (Viz.ai)

    1.5 Further research is recommended (see section 4) to:

    • assess how using AI‑software technologies alongside clinician interpretation of CT brain scans affects diagnostic accuracy in identifying and classifying stroke

    • understand how reliably the AI‑software technologies work in clinical practice when used alongside clinician interpretation

    • understand how using AI‑software technologies alongside clinician interpretation in the diagnostic pathway affects time to treatment in ischaemic stroke

    • assess how using AI‑software technologies alongside clinician interpretation in the diagnostic pathway affects clinical outcomes, including level of disability (both apparent and non-apparent) after stroke.

    Why the committee made these recommendations

    Stroke adversely affects quality of life for many people who survive it. Faster access to treatment could improve clinical outcomes and so quality of life after stroke. AI-software technologies used alongside clinician interpretation of CT brain scan images could guide and speed up decision making in stroke, for example decisions on thrombolysis and thrombectomy treatment.

    Clinical evidence on the AI-software technologies is limited in quantity and quality. There is no evidence on their diagnostic accuracy when used alongside clinician interpretation. Studies on their use in clinical practice give results only for people who had a positive test result and treatment. So, it is unclear how using the technologies affects clinical outcomes, particularly for people who may not have the correct treatment because their diagnosis has been missed (false negatives). These studies also suggest that people had faster access to treatment after using the software technologies, but it is unclear if this is an effect of using the software.

    The lack of data on diagnostic accuracy and clinical outcomes means that the cost effectiveness of using AI-software technologies in suspected acute stroke cannot be determined, so they cannot be recommended for routine use in the NHS. Further research is needed.