Audit: QRS - ANKTIVA to Treat Cancer

Audit conducted on 25/06/2026 20:31 using AI4L / Opus 4.8

Iterations

Summary

Items Count
Total 91
Passed 85
Failed 0
N/A 6
Pass Rate 100.00%
  • Total = Passed + Failed + N/A
  • Pass Rate = Passed / (Passed + Failed) × 100
  • N/A items are excluded from the pass rate calculation

1. General Rules

# Description Result Comments
1.1 Every claim, magnitude, label, recommendation, and statement in the QRS is literally supported by content in the source ER. 🟢 All protocol values, magnitudes, contraindications, interactions, and monitoring markers trace to ER Protocol, Risks, Interactions, and Monitoring sections.
1.2 Where the ER uses cautious phrasing (“not formally studied”, “None documented in human trials to date”, “theoretical concern”, “data are limited”), the QRS uses the same phrasing. 🟢 Speculative tiers (“Activity in other tumor types”, “Long-term and rare systemic risks”) preserve the ER’s tentative framing.
1.3 The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”). 🟢 No strengthening or softening detected.
1.4 The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc. 🟢 Contraindications and Key Interactions both drawn from ER’s Key Interactions & Contraindications section under correct categories.
1.5 PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact. 🟢 No PMIDs, NCT IDs, or expert names introduced. Brand names (BCG, ANKTIVA) match the ER.
1.6 The QRS does not introduce new attributions. 🟢 No new attributions present.

2. Focus, Tone & Audience

# Description Result Comments
2.1 The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing. 🟢 Objective, data-aware tone consistent with the ER.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging. 🟢 Expert yet accessible throughout.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor. 🟢 Presents evidence, does not prescribe.
2.4 The QRS avoids language that implies medical or clinical advice. 🟢 No advisory language.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”. 🟢 Information-presenting voice maintained.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance. 🟢 No second-person address.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon. 🟢 Plain language used; at-a-glance avoids acronyms.
2.8 Information is presented in a concise and very compact manner. 🟢 Compact bullets and cells throughout.
2.9 It DOES NOT address the reader directly. 🟢 No direct reader address.
2.10 The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review. 🟢 Framing fits a risk-aware audience weighing bladder-sparing options.
2.11 The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort. 🟢 Cost and multi-year burden surfaced without dismissal.
2.12 The document is NOT written for the general population, who are unwilling to employ lifestyle and behavioral changes or follow protocols that may be inconvenient, costly, or require effort. 🟢 Content presumes an engaged audience.
2.13 Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience. 🟢 Weighting reflects the target audience.
2.14 The document’s own voice frames usage in longevity terms, not “anti-aging”. Proper names that contain “anti-aging” are quoted verbatim. 🟢 No “anti-aging” language present.
2.15 The document’s own voice uses formal clinical and scientific terminology, not colloquial or consumer-grade language. Direct quotes from sources are exempt. 🟢 Formal terminology used (e.g., “intravesical”, “adverse events”, “instillation”).

3. Template Integrity

# Description Result Comments
3.1 The following labels and headings on the QRS are fixed and not modified (card/section headings, gate headings, tier labels, Monitoring column headers). 🟢 All fixed headings/labels present unchanged.
3.2 All “” from the [qrs_template] are present in the QRS. 🟢 All template spans present, including hidden time_2/time_3 sets.
3.3 Spans that are not addressed in a checklist item are left unchanged. 🟢 No unaddressed spans modified.

4. Formatting

# Description Result Comments
4.1 When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. 🟢 No empty ER sections requiring empty-state phrasing; unused sets hidden.
4.2 Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label. 🟢 Tier and protocol labels match the ER.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Labels faithful to the ER.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). 🟢 No emoji indicators found in the QRS body.
4.5 The QRS is designed to render on one A4 page. Any section with more content in the ER than fits is condensed, not extended onto a second page. 🟢 Content condensed to a single sheet.

5. Metadata

# Description Result Comments
5.1 The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content. 🟢 Metadata comment is the first element after doctype (lines 2-14).
5.2 Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. 🟢 YAML delimited by — at lines 3 and 13.
5.3 The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet. 🟢 Enclosed in an HTML comment; not rendered.
5.4 All frontmatter values are trimmed: no leading/trailing whitespace, no surrounding quotes unless YAML requires. 🟢 Values clean; duration: "00:03" quoted because it contains a colon.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]”. 🟢 er_filename: anktiva_cancer_2026-0625-1925_Opus_ER.md (line 4).
5.6 Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]”. 🟢 qrs_prompt_version: 26.5.18 matches the prompt version.
5.7 Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]”. 🟢 qrs_creation_date: 2026-0625-1925 (line 6).
5.8 The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: […]”. 🟢 qrs_creator_ai_nickname: Opus (line 7).
5.9 The nickname of the AI is just a single word model name without version, etc. 🟢 “Opus” is a single word.
5.10 The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: […]”. 🟢 qrs_creator_ai_fullname: Opus 4.8 (line 8).
5.11 The full name of the AI consists of the nickname and the model version number and no additional qualifier. 🟢 “Opus 4.8” is nickname plus version only.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]”. 🟢 qrs_filename: anktiva_cancer_2026-0625-1925_Opus_QRS.html (line 9).
5.13 All frontmatter values are trimmed: no leading/trailing whitespace, no surrounding quotes unless YAML requires. 🟢 All values trimmed and consistent.

6. Page Title & Header

# Description Result Comments
6.1 [page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet”. The canonical_topic is HTML-entity-encoded as needed. 🟢 “ANKTIVA to Treat Cancer - Quick Reference Sheet” (line 22); no entities required.
6.2 [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed. 🟢 “ANKTIVA to Treat Cancer” (line 417).
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]. 🟢 “06/25/2026” matches creation date 2026-0625.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname]. 🟢 “Opus 4.8” (line 425).
6.5 No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. 🟢 Header contains only title, date, AI4L/model attribution; no extra content.

7. At-A-Glance Section

# Description Result Comments
7.1 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section. 🟢 Summarizes the ER Conclusion (ER lines 443-445).
7.2 [at_a_glance] is no longer than 60 words. 🟢 52 words.
7.3 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 Mechanism, indication, response, tolerability, cost, and unproven-in-other-cancers all trace to the Conclusion.
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead. 🟢 No acronyms (BCG, NMIBC, IL-15); plain language used.
7.5 It DOES NOT cite specific trials (names, years, sample sizes, p-values). 🟢 No trial references.
7.6 It DOES NOT cite effect sizes, relative risks, or statistical results. 🟢 No statistics cited.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section. 🟢 Derived from ER line 300 (“Populations who should avoid this intervention”).
8.2 [stop_items] represent the Contraindications from the ER. 🟢 All eight avoidance/deferral items from ER line 300 represented.
8.3 Individual [stop_items] are formatted as <li></li>. 🟢 Each item is a separate <li> (lines 542-549).
8.4 Items are as concise as possible. No trailing explanations, attributions, citations, or content after a dash. 🟢 All items are concise key facts; no trailing clauses.
8.5 Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved. 🟢 “Muscle-invasive disease (≥ stage T2)” and “Immunocompromised states (…)” preserved.
8.6 When the ER uses ranking notation inside parens, normalize to a plain comma-separated list rather than carrying the bare symbol. 🟢 No ranking symbols present; parentheticals are plain lists.
8.7 If no [stop_items] are present the section is left empty. N/A Contraindications are present, so the empty-state condition does not apply.

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section. 🟢 Derived from ER lines 288-298.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any already listed as Contraindications. 🟢 Four interactions listed; none duplicate the contraindications.
9.3 Individual [caution_items] are formatted as <li></li>. 🟢 Each item is a separate <li> (lines 557-560).
9.4 Items are as concise as possible. No trailing explanations, attributions, citations, or content after a dash. 🟢 Items are concise; severity/mitigation clauses dropped.
9.5 Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, etc. — ARE preserved. 🟢 Example drug lists preserved (prednisone/methotrexate/tacrolimus/TNF inhibitors; ciprofloxacin/antituberculous agents; pembrolizumab/nivolumab).
9.6 When the ER uses ranking notation inside parens, normalize to a plain comma-separated list. 🟢 No ranking symbols; lists are plain.
9.7 If no [caution_items] are present the section is left empty. N/A Key interactions are present, so the empty-state condition does not apply.

10. Protocol

# Description Result Comments
10.1 The section is derived from the ER Protocol section. 🟢 Derived from ER lines 324-328.
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section. 🟢 Induction, Maintenance, Route — the three core actionable aspects.
10.3 If less than three distinct actionable implementation aspects are mentioned, the unused sets are left empty and made invisible, not filled with placeholder text. N/A Three actionable aspects are present, so the condition does not apply.
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 All three sets filled with ER-derived content.

11. Time to Effect

# Description Result Comments
11.1 The three sets of [time] items cover the three most important time-to-effect aspects from the ER. 🟢 The ER provides a single time-to-effect anchor (~3-month cystoscopy); it is captured and the remaining sets are hidden.
11.2 The sets are picked and ordered by the magnitude of the related benefit. 🟢 Single set tied to the primary complete-response outcome.
11.3 If less than three distinct time-to-effect aspects are mentioned, the unused sets are left empty and made invisible. 🟢 time_2 and time_3 sets are empty and set to display:none (lines 492-513).
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 time_1 set filled from ER lines 375/399.
11.5 If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel. N/A The ER provides time-to-effect information, so removal does not apply.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section. 🟢 Derived from ER lines 153-196.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]. 🟢 All four tier variables populated.
12.3 Items are as concise as possible. No explanations, effect sizes, qualifiers, attributions, citations, or mechanistic explanations. 🟢 Concise tier facts; no effect sizes or mechanism.
12.4 Parenthetical content — effect sizes, sample notes, mechanistic hints, example studies — is stripped, NOT preserved. 🟢 No parentheticals carried into the benefits.
12.5 If no items of a specific sub-section are present the respective SPAN is set to display=none, not filled with empty-state phrasing. N/A All four benefit tiers have content, so the empty-state condition does not apply.

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section. 🟢 Derived from ER lines 221-264.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]. 🟢 All four tier variables populated.
13.3 Items are as concise as possible. No explanations, effect sizes, qualifiers, attributions, citations, or mechanistic explanations. 🟢 Concise tier facts only.
13.4 Parenthetical content — frequencies, severity grades, sample notes, mechanistic hints, example studies — is stripped, NOT preserved. 🟢 No parentheticals carried into the risks.
13.5 If no items of a specific sub-section are present the respective SPAN is set to display=none, not filled with empty-state phrasing. N/A All four risk tiers have content, so the empty-state condition does not apply.

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section. 🟢 Derived from ER Monitoring Protocol table (lines 401-407).
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed. 🟢 All five markers listed (cystoscopy+biopsy/cytology, urine cytology, serum creatinine, urinalysis, CBC).
14.3 [monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty. 🟢 Cadence populated (cystoscopy ~3 and 6 months, then periodic; labs through the up-to-37-month course).

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section. 🟢 Derived from the ER qualitative markers (lines 411-415).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed. 🟢 All three listed (urinary symptom burden, systemic symptoms, functional well-being).

Issues 25/06/2026 20:31

Pass rate 100.00%. No issues found.

Issues 25/06/2026 20:27

  1. 9.2 — Contraindication duplicated as interaction: The Key Interactions gate lists “Recent transurethral resection or traumatic catheterization” (QRS line 560), but “Recent traumatic catheterization” is already a Contraindication (QRS line 548); 9.2 requires Key Interactions to exclude items already listed as Contraindications.

Fixes 25/06/2026 20:27

  1. 9.2 — Contraindication duplicated as interaction: Narrowed the Key Interactions item from “Recent transurethral resection or traumatic catheterization” to “Recent transurethral resection”, removing the “traumatic catheterization” portion already listed as a Contraindication.

Issues 25/06/2026 20:23

  1. 7.4 — Unexpanded acronym BCG in At-A-Glance: [at_a_glance] (line 433) uses the specialist acronym “BCG” twice (“the older BCG treatment”, “returned after BCG”) without plain-language explanation; a non-specialist would not know its exact meaning.

Fixes 25/06/2026 20:23

  1. 7.4 — Removed unexpanded BCG acronym: Replaced both uses of “BCG” in [at_a_glance] with plain-language wording (“an older bacteria-based bladder treatment” / “after that treatment”), keeping the meaning faithful to the ER while removing the specialist acronym.