The innovative software automates aspects of detecting brain abnormalities and assists in prioritising the most urgent cases. Its role would be to support hospital radiologists to review CT scans.
The technology may be of most benefit where images cannot initially be reviewed by specialist neuroradiologists.
The NICE briefing used evidence from 11 studies. Seven studies, which included the analysis of 31,118 CT brain scans, showed the technology to be as effective at detecting intracranial haemorrhages as neuroradiologists, however, study conditions did not reflect current NHS clinical practice. Four real world observational studies, which included 59,655 CT brain scans, suggest the technology may perform well in clinical practice.
However, there are uncertainties in the evidence. Six of the studies included in the briefing are only summaries and with limited methodological detail. The NICE team said the evidence base would benefit from well controlled comparative studies with an appropriate follow-up time to capture patient outcome and time to treatment.
The cost of AI software for CT brain scans is between £8,250 and £80,000 per licence fee every year. The cost of the technology depends on the size of the NHS trust and number of analyses done. Pay per use is also available for one of the listed technologies and costs £45.
Although more expensive than the analysis of scans solely by radiologists, the NICE team believes the extra cost may be offset by faster diagnosis of time-sensitive cases, reducing complications related to delayed treatment.
NICE MIBs summarise the best available published evidence for a technology. They also include some expert opinion and an evaluation of the strengths and weaknesses of the available evidence. MIBs are not NICE guidance and do not contain any recommendations on the use of the device or technology within the NHS.
MIBs are designed to provide rapid, objective information on devices and diagnostic technologies to aid local decision-making by clinicians, managers and procurement professionals. This helps to avoid the need for different NHS organisations to produce similar information for local use. The production of a MIB on a technology does not necessarily mean that NICE won't produce guidance on it at a later date.