# Decision support that cites the exact trial and guideline line it relies on

Source: https://onco.cc/ideas/idea-data-provenance-first-decision-support/  
OnCo record `idea-data-provenance-first-decision-support` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

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.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- 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.
- Proposed 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

## Sources

- Bottleneck evidence (Knowledge reaches practice too slowly): Morris, Wooding & Grant, The answer is 17 years, what is the question (JRSM 2011): https://doi.org/10.1258/jrsm.2011.110180

## Connected records

- ideas: [A randomised trial of AI-generated treatment recommendations versus tumour boards](https://onco.cc/ideas/idea-data-ai-vs-tumour-board-rct/), [A tumour board assistant that cites its evidence and tracks outcomes](https://onco.cc/ideas/idea-data-tumour-board-evidence-assistant/), [An open knowledge graph linking trials, results, biomarkers, drugs and recommendations](https://onco.cc/ideas/idea-data-open-evidence-knowledge-graph/), [Living guidelines published as versioned, computable rules](https://onco.cc/ideas/idea-data-computable-living-guidelines/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Knowledge reaches practice too slowly](https://onco.cc/bottlenecks/b-knowledge-diffusion/)
- key papers: [The answer is 17 years, what is the question: understanding time lags in translational research](https://onco.cc/key-papers/paper-morris-j-r-soc-med/)

---
JSON: https://onco.cc/api/v1/entities/idea-data-provenance-first-decision-support.json