{"entity":{"id":"idea-data-provenance-first-decision-support","kind":"idea","name":"Decision support that cites the exact trial and guideline line it relies on","aka":[],"tldr":"When a computer suggests a treatment, it should show the doctor the specific trial result and guideline sentence behind the suggestion, so it can be checked and trusted.","summary":"Most oncology decision support presents recommendations as opaque rules. Provenance-first CDS attaches, to every suggestion, the guideline version and recommendation identifier, the trial identifiers and structured results it derives from, and the date of last evidence check, drawn from a computable guideline feed and evidence graph. This makes recommendations auditable, updatable and correctable, and lets clinicians see when evidence is thin.","asOf":"2026-09-08","links":[{"label":"Bottleneck evidence (Knowledge reaches practice too slowly): Morris, Wooding & Grant, The answer is 17 years, what is the question (JRSM 2011)","url":"https://doi.org/10.1258/jrsm.2011.110180"}],"tags":[],"related":["idea-data-computable-living-guidelines","idea-data-open-evidence-knowledge-graph"],"cancers":[],"sections":["ai-computation"],"technologies":[],"targets":[],"drugs":[],"companies":[],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":["b-knowledge-diffusion","b-ai-validation"],"keyPapers":["paper-morris-j-r-soc-med"],"journals":[],"dependsOn":[],"notes":[],"hypothesis":"Clinicians will accept provenance-first CDS suggestions at a higher rate and override them more appropriately than opaque CDS, and errors introduced by stale rules will be detected faster.","rationale":"Trust in decision support depends on verifiability; in other domains (legal research, code review) tools that cite sources outperform those that do not in adoption and accuracy.","test":"Randomise oncologists in a simulation study to opaque versus provenance-first CDS for 40 cases with planted stale recommendations; measure appropriate acceptance, override and error detection.","maturity":"early-clinical","actor":"engineering","cost":"small","horizonYears":2},"route":"/ideas/idea-data-provenance-first-decision-support/","neighbours":{"idea":[{"id":"idea-data-ai-vs-tumour-board-rct","kind":"idea","name":"A randomised trial of AI-generated treatment recommendations versus tumour boards","route":"/ideas/idea-data-ai-vs-tumour-board-rct/"},{"id":"idea-data-tumour-board-evidence-assistant","kind":"idea","name":"A tumour board assistant that cites its evidence and tracks outcomes","route":"/ideas/idea-data-tumour-board-evidence-assistant/"},{"id":"idea-data-open-evidence-knowledge-graph","kind":"idea","name":"An open knowledge graph linking trials, results, biomarkers, drugs and recommendations","route":"/ideas/idea-data-open-evidence-knowledge-graph/"},{"id":"idea-data-computable-living-guidelines","kind":"idea","name":"Living guidelines published as versioned, computable rules","route":"/ideas/idea-data-computable-living-guidelines/"}],"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"},{"id":"b-knowledge-diffusion","kind":"bottleneck","name":"Knowledge reaches practice too slowly","route":"/bottlenecks/b-knowledge-diffusion/"}],"paper":[{"id":"paper-morris-j-r-soc-med","kind":"paper","name":"The answer is 17 years, what is the question: understanding time lags in translational research","route":"/key-papers/paper-morris-j-r-soc-med/"}]}}