- \n
- New DECIDE-AI guidelines aim to improve reporting of early-stage clinical trials of AI-based clinical decision support systems.<\/li>\n
- The authors hope that addressing this unmet need will facilitate more robust research, and ultimately translate to increased uptake of these technologies.<\/li>\n<\/ul>\n
\n![\"\"](\"https:\/\/i0.wp.com\/thepublicationplan.com\/wp-content\/uploads\/2022\/12\/iStock-1365534802.jpg?resize=748%2C467&ssl=1\")
<\/p>\nWith the advent of artificial intelligence (AI), there has been much discussion, debate, and research on its applicability<\/a> to clinical decision support systems<\/a> (CDSS). Although some regulatory guidance<\/a> is available, and AI-based CDSS have been approved<\/a>, a recent article by Vasey et al in The BMJ<\/em><\/a> and Nature Medicine<\/em><\/a> argues that a need remains for a more robust approach in early clinical development. The authors present new guidelines aimed at improving reporting at this stage which, they argue, would create a stronger foundation for larger clinical trials and ultimately increase uptake.<\/p>\n
The Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI<\/a>) guidelines provide minimum reporting standards for studies of AI-CDSS, whether for detection, diagnosis, prognosis, or therapy. It complements other guidance, such as CONSORT-AI<\/a> (for randomised controlled trials) and SPIRIT-AI<\/a> (for protocol reporting).<\/p>\n
DECIDE-AI incorporates 27 recommended reporting items, 17 of which are AI specific. These include:<\/p>\n
- \n
- methods for integrating the system into the clinical care pathway<\/li>\n
- user familiarisation with the system<\/li>\n
- description of the algorithm, inputs, and outputs<\/li>\n
- human factors (ie interactions between humans and the system)<\/li>\n
- characteristics of both patients and users<\/li>\n
- usability<\/li>\n
- risks\/ harms and means for mitigating these.<\/li>\n<\/ul>\n
The authors note that the complexity of the field is reflected in the breadth and depth of reporting detail that is required by the guidance. They suggest that, to ensure adequate and complete reporting, \u201cthorough evaluation of AI systems should not be limited by word count\u2026publications reporting on such systems might benefit from special formatting requirements.\u201d<\/p>\n
\n
\u201cThorough evaluation of AI systems should not be limited by word count\u2026publications reporting on such systems might benefit from special formatting requirements.\u201d<\/p>\n<\/blockquote>\n
As highlighted by the authors, this field continues to evolve. Future iterations of the guidance may be expanded further as more research is carried out, to cover currently contentious topics such as interpretability and user trust levels.<\/p>\n
\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2013<\/p>\n
![\"\"](\"https:\/\/i0.wp.com\/thepublicationplan.com\/wp-content\/uploads\/2022\/11\/Byline_PubPlan.png?resize=618%2C75&ssl=1\")
<\/a><\/p>\n