00Drug development
R&D spending has outpaced drug approvals.
In a 2012 analysis, drug approvals per inflation-adjusted R&D dollar were about 80 times lower than in 1950. This historical trend is known as Eroom's law.
RuleKit examines how teams review eligibility interpretations and amendment effects. This prototype has not measured cost savings.
The walkthrough uses invented documents and synthetic patients.
01Protocol changes
Protocol amendments carry implementation costs.
A 2016 study reported median direct costs of $141K in Phase II and $535K in Phase III for a substantial amendment.
These are amendment costs, not savings demonstrated by RuleKit. This illustration uses invented documents and synthetic patients.
“At least 30” includes 30. “Over 30” does not. Compare the source criterion with its checklist or query, then test the boundary.
Getz et al., Therapeutic Innovation & Regulatory Science, 2016
02Rule authoring
Keep source wording beside the rule.
Each YAML rule stores the protocol sentence alongside its executable interpretation.
A person writes and reviews the rule. Criteria that the language cannot express remain visible as unmodeled text.
Version control records changes to the wording and logic. It does not establish which version a site is authorized to use.
03A worked criterion
Make each comparison explicit.
The synthetic criterion becomes a comparison: fact egfr, operator gte, value 30.
The rule includes the measurement unit and preserves the source sentence in verbatim.
Timing needs its own representation. A threshold alone does not check when a measurement was taken.
04Missing evidence
Keep missing evidence unresolved.
Synthetic patient: age 63, LVEF 38%, eGFR missing.
Without eGFR, the renal criterion returns unknown.
Every criterion must pass for an eligible result. Any failure makes the result ineligible. Otherwise, an unknown leaves it undetermined.
05Combined criteria
Inspect inclusions and exclusions together.
An inclusion requires eGFR ≥30. An exclusion applies below 45.
Values from 30 up to, but excluding, 45 pass the inclusion and trigger the exclusion. The overall result is ineligible.
This is ordinary exclusion behavior. rules check does not report a contradiction or fail the build.
06Consistent evaluation
Compare the same results across tools.
The CLI report and workbench share the evaluator and attrition logic.
Pin the engine version, rules, facts and evaluation date to compare results. Each patient trace shows the criteria behind its result.
At eGFR 30, this example passes the inclusion and triggers the exclusion in both views.
07Evidence review
Review proposed facts against their source.
An LLM can propose facts from a note. Each proposal must include an exact source quote and receive human confirmation before evaluation.
The note and patient here are synthetic. A matching quote supports review; it does not prove the proposed value is clinically correct.
An unmatched quote causes rejection. Model confidence is not a clinical probability or an eligibility score.
08Cohort review
Trace each cohort result.
This example contains ten synthetic patients: seven ineligible, three undetermined and none eligible.
Open a result to inspect failed criteria and unresolved evidence. These counts describe the demo cases, not a trial population.
09Available now
Run the prototype locally.
The repository includes a rule engine, CLI reports, an amendment workbench and a fact review component.
Bundled demos use synthetic patients and need no account or live model call. There is no EHR connector.
Automated regression tests cover the engine and interfaces. Real screening workflows and language coverage still need evaluation with clinical teams.
10Collaboration
Help test this against a screening workflow.
Clinical operations and trial managers: review a public or invented criterion and help define a useful amendment review. Engineers: inspect the rule format, traces and tests.
This prototype is not validated, not cleared by any regulator, and not for clinical, feasibility, or research screening use.
Discuss a clinical workflow · Set up the project
Emmanuel Cuyugan · RuleKit · Apache-2.0