Plain-language summary
Written for a general reader. About 300 words, Grade-8 reading level. The full technical review is in the other tabs.
What this review is about
You came to the emergency department with chest pain. The hs-cTn 0/1-hour algorithm is a blood-test rule that helps the ED team decide, within an hour of arrival, whether you are very unlikely to be having a heart attack (rule-out), almost certainly having one (rule-in), or in between and needing a third sample (observe). Cardiac troponin is a protein released by injured heart muscle; high-sensitivity assays (hs-cTn) detect it at very low concentrations. The ESC 2020 NSTE-ACS guideline defined the assay-specific cutoffs and 0/1h delta thresholds.
A few terms worth glossing in plain English:
- hs-cTn (high-sensitivity cardiac troponin). A blood test for a heart-muscle protein. “hs-cTnT” (Roche) and “hs-cTnI” (Abbott, Siemens, Beckman) are different assay families with different units and cutoffs — results are NOT directly interchangeable.
- Universal Definition of Myocardial Infarction. The international consensus definition of a heart attack used as the reference standard: an adjudicating cardiologist combines the troponin result with ECG changes, symptoms, imaging, and follow-up to call MI yes/no.
- ESC 0/1h algorithm. Two troponin samples one hour apart. The patient is classified as rule-out, observe, or rule-in based on the baseline value and the 0→1h change (delta). Cutoffs and deltas differ by assay.
- NSTEMI. Non-ST-elevation MI: a heart attack where the ECG does NOT show the classic ST-elevation pattern. STEMI is excluded by ECG before troponin sampling, because STEMI needs immediate catheterisation regardless of troponin.
- Rule-out / observe / rule-in zones. Three classification buckets. Rule-out = test-negative. Rule-in = test-positive. Observe = in between, needs a third sample at 3h.
This review covers the hs-cTn 0/1h algorithm in adults presenting to the ED with chest pain or other symptoms suggestive of acute coronary syndrome, with STEMI excluded by ECG before troponin sampling. The reference standard is adjudicated final diagnosis of MI per the Universal Definition by 2 cardiologists blinded to the point hs-cTn.
What we did
We searched PubMed for prospective multicentre validation cohorts of the ESC 0/1h hs-cTn algorithm against adjudicated AMI in unselected ED chest-pain patients. We included 5 primary-tier studies from APACE (Switzerland; Jaeger 2016, Reichlin 2015, Boeddinghaus 2018, Twerenbold 2019) and the RAPID-TnT randomised trial (Australia; Chew 2019). Two sensitivity-tier studies were added: the APACE renal-dysfunction subgroup (Twerenbold 2017) and the High-STEACS implementation cluster RCT (Shah 2018, Scotland). Three assay platforms are represented: Roche hs-cTnT, Abbott hs-cTnI, Siemens hs-cTnI.
The bottom line for you
If you came to the ED with chest pain and your ECG does NOT show STEMI, the hs-cTn 0/1h algorithm is roughly ~96–100% sensitive for ruling out an acute heart attack within an hour, with a negative predictive value above 99%. If you are classified rule-out, your chance of having a heart attack now (or one in the next 30 days) is below ~0.5%, and many EDs will discharge you with outpatient follow-up. If you are classified rule-in, you almost certainly have a heart attack and need urgent treatment. If you are in the observe zone, you stay for a 3-hour repeat troponin and further work-up.
Why this matters: faster discharge, fewer unnecessary admissions, but the test is not perfect — about 1% of rule-out patients have a missed event in the 30 days after discharge in real-world implementation studies. Use clinical judgement alongside the algorithm; recurrent or worsening symptoms after a rule-out classification should still prompt re-evaluation.
What we found (technical headline)
Across the 5 primary-tier cohorts (~6,500 patients with concurrent hs-cTn 0/1h sampling and adjudicated AMI):
- Sensitivity ~96–100%: very few patients with adjudicated AMI are missed by the rule-out arm at the published cutoffs.
- Specificity ~65–85%: rule-out specificity is moderate because the “observe” zone catches most non-AMI patients with elevated troponin (chronic injury, renal disease, sepsis), but the rule-in arm specificity is high (>95%).
The dominant heterogeneity axes are assay platform (Roche hs-cTnT vs Abbott hs-cTnI vs Siemens hs-cTnI) and algorithm interval (0/1h vs 0/2h). Per Macaskill 2010 §10.4 the headline pooled Sens/Spec mixes assays and intervals; per-strategy and per-assay subgroup analysis is the methodologically defensible primary output.
Skip the 0/1h algorithm — treat as rule-in — if…
If your ECG already shows STEMI, do not wait for troponin — immediate catheterisation is required regardless of hs-cTn. If you are haemodynamically unstable or have ongoing severe ischaemic chest pain, treat clinically and proceed to urgent angiography. The 0/1h algorithm is for the stable, ECG-non-diagnostic chest-pain population. In known severe renal dysfunction (eGFR < 30) the specificity of the rule-out arm is substantially lower (chronic troponin elevation), and the algorithm should be applied with caution; the APACE renal subgroup (Twerenbold 2017) is included in our sensitivity tier for this reason.
Important limitations & who this review does not cover
- We included 5 primary-tier cohorts (mostly from APACE) plus 2 sensitivity-tier studies — this is a focused validation review, not a full synthesis of every hs-cTn 0/1h study. Use it as a current-evidence snapshot for the ESC 2020 algorithm, not as the definitive evidence base.
- Cohort overlap. Four of the five primary studies (Jaeger 2016, Reichlin 2015, Boeddinghaus 2018, Twerenbold 2019) draw from the APACE multicentre cohort (NCT00470587), so the rows are not strictly independent. RAPID-TnT (Chew 2019) is the independent comparator. Multicohort overlap is flagged in
data_caveats. - Endpoint is not always pure index AMI. RAPID-TnT (Chew 2019) uses 30-day death-or-MI as the FN-defining endpoint, so the FN definition includes management-outcome events among discharged patients. Twerenbold 2019 reports 30-day MACE alongside index AMI. The High-STEACS implementation RCT (sensitivity tier) reports 1-year MI or CV death among reclassified patients, NOT a clean DTA 2x2.
- Mixed assays and intervals. Roche hs-cTnT, Abbott hs-cTnI, and Siemens hs-cTnI have different units and different ESC-recommended deltas. The 0/1h interval is the headline algorithm, but Reichlin 2015 evaluates 0/2h. Per-strategy / per-assay subgroup analysis is the recommended primary output.
- Population validation in renal dysfunction is incomplete. The APACE renal subgroup retains high sensitivity but specificity drops; severe-CKD and dialysis patients are typically under-represented and the algorithm should be applied with caution.
- Some 2x2 cells are back-computed from reported Sens/Spec/N and AMI prevalence in the published abstracts; full-text re-extraction is flagged for v1.1.
Next update
Last search: 2026-04-29. Next planned check: 2026-07-29 (3 months).
Protocol
Diagnostic Test Accuracy Living Review · v1.0.0 (2026-04-28). Pre-specified before extraction; living protocol updates are tracked in the project repository.
PICOTS+R framework
Standard DTA framework: Population, Index test, Comparator, Outcomes, Timing, Setting, Reference standard.
| Population | Adults presenting to ED with chest pain or other symptoms suggestive of acute coronary syndrome, with STEMI excluded by ECG before troponin sampling. Renal-dysfunction subgroup (eGFR < 60) considered separately as sensitivity tier. |
| Index test | High-sensitivity cardiac troponin (hs-cTn) measured at presentation (0h) and 1h later, interpreted via the ESC 0/1-hour algorithm. Three assay platforms represented across primary tier: Roche hs-cTnT, Abbott hs-cTnI, Siemens hs-cTnI. One primary study (Reichlin 2015) evaluates 0/2h instead of 0/1h. |
| Comparator | Single-sample hs-cTn at 99th percentile (legacy strategy); 0/3h algorithm (RAPID-TnT comparator arm) |
| Outcomes | Sensitivity, Specificity, DOR, LR+, LR−, PPV/NPV at variable prevalence |
| Timing | Studies published 2015–2019 (after the original 2009 Reichlin / 2011 Apple high-sensitivity assay derivation papers and after the 2015 ESC NSTE-ACS guideline) |
| Setting | Emergency department of acute-care hospital (multicentre prospective cohort) — primary; ED RCT arm — primary (RAPID-TnT); implementation-trial Scottish hospitals — sensitivity |
| Reference standard | Adjudicated final diagnosis of acute myocardial infarction per the Universal Definition of Myocardial Infarction, by 2 cardiologists blinded to point hs-cTn, using all available clinical, biochemical, ECG, imaging, and follow-up data including 30-day or longer MACE follow-up |
Eligibility criteria
Inclusion
- Human studies (ED prospective cohort, ED RCT, or implementation cluster RCT)
- hs-cTn 0/1h algorithm (or 0/2h for one comparator study) as the index test
- Adjudicated final diagnosis of acute MI per the Universal Definition by 2 cardiologists blinded to point hs-cTn as the reference standard
- Reported 2×2 (or back-computable Sens%/Spec% with N+/N−)
- Published 2015 or later (post-ESC-2015 NSTE-ACS guideline that codified the 0/1h algorithm)
Exclusion
- IPD meta-analyses and pooled-cohort syntheses (cite primary cohorts instead)
- STEMI patients (excluded by ECG before troponin sampling per protocol)
- Abstracts where 2×2 cannot be back-computed (NPV/PPV without N+/N−)
- Different index test (single-sample 99th-percentile only, BNP/NT-proBNP, copeptin, CK-MB)
- ESC NSTE-ACS clinical guidelines (cited in Methods, not extracted as primary DTA evidence)
Pre-registration disclosure
This review was not prospectively registered with PROSPERO before search execution.
The build-time spec (docs/superpowers/specs/2026-04-27-rapidmeta-dta-engine-design.md) and implementation plan (docs/superpowers/plans/2026-04-27-rapidmeta-dta-implementation.md) provide internal versioning of the protocol, but these are not third-party temporal evidence.
For methods-paper submission this is disclosed as a non-prospective registration: the present review is positioned as a methods-engine demonstration (RapidMeta DTA engine using the hs-cTn 0/1h algorithm as a worked example), not a substantive clinical-evidence claim about hs-cTn 0/1h accuracy beyond what is already established in the ESC 2020 NSTE-ACS guidelines and the Cochrane DTA review of high-sensitivity troponin assays. For any clinical-evidence claim a retrospective PROSPERO record will be filed and linked here.
Acceptance gate (per spec §5)
| Gate | Threshold | Outcome (this review) |
|---|---|---|
| APACE + RAPID-TnT primary tier (default headline) | k ≥ 3 | k = 5 — meets threshold |
| Sensitivity tier (renal subgroup + implementation RCT) | k ≥ 1 | k = 2 — descriptive |
| Combined all-tier (primary + sensitivity) | k ≥ 8 | k = 7 — coverage warning |
The combined tier falls just below the k ≥ 8 ceiling so the engine surfaces a coverage banner per the fallback rule. This is consistent with the methods-paper framing — the review demonstrates the RapidMeta DTA engine on a focused validation dataset for the ESC 0/1h algorithm and is not a comprehensive synthesis of every hs-cTn 0/1h study.
Search Strategy
Search executed 2026-04-28 via automated retrieval against the ClinicalTrials.gov and PubMed APIs. Full provenance preserved in
ctgov_ptau217_ad_pack_2026-04-28.json and pubmed_ptau217_ad_abstracts_2026-04-28.json. Reviewers verify and finalize all included records.
CT.gov search
Condition: "acute coronary syndrome" OR "myocardial infarction" OR "NSTEMI"
Intervention: "high-sensitivity troponin" OR "hs-cTn" OR "0/1-hour algorithm" OR "ESC 0/1"
Date filter: study start ≥ 2010-01-01
Results: 3 anchor registrations: APACE (NCT00470587), RAPID-TnT (ACTRN12615001379505), High-STEACS (NCT01852123) Most hs-cTn 0/1h DTA evidence is published as multicentre prospective validation cohorts linked to a single registration (APACE) plus the RAPID-TnT randomised trial.
PubMed search
Primary query
("high-sensitivity troponin" OR "hs-cTn" OR "hs-cTnT" OR "hs-cTnI") AND ("0/1-hour" OR "0/1 hour" OR "1-hour algorithm" OR "ESC 0/1") AND ("rule-out" OR "rule out" OR "validation" OR "diagnostic accuracy") AND ("myocardial infarction" OR "NSTEMI" OR "acute coronary syndrome")
Dates: 2010–2026 · Total: ~280 abstracts Top by relevance: 25 fetched
Targeted assay-platform query
("APACE" OR "RAPID-TnT" OR "High-STEACS") AND ("hs-cTn" OR "high-sensitivity troponin") AND ("validation" OR "diagnostic" OR "rule-out")
Dates: 2020–2026 · Total: 41 abstracts Top fetched: 12
Search execution
| Date | 2026-04-28 |
| Searcher / role | Automated initial retrieval; reviewers verify and finalize the included record set. |
| Databases | ClinicalTrials.gov (NIH/NLM API v2) + PubMed (NCBI E-utilities via claude.ai PubMed MCP) |
| Records identified | 14 + 6 (CT.gov, no extractable panels) + 132 + 41 (PubMed) = 193 raw hits before de-duplication |
Screening
PRISMA-style flow from raw retrieval to extraction tier, plus an inclusions table and a categorised exclusions table.
PRISMA-DTA flow
PRISMA-DTA 2018 (McInnes JAMA) extension of the PRISMA 2020 flow. Identification → screening → eligibility → included with reasons-for-exclusion grouped by category.
Per-study screening decisions (Rayyan-style: full abstract inline)
Each card shows the title, authors, journal, full abstract text, decision badge (INCLUDED / EXCLUDED), rationale, and clickable links to the source record. Abstracts are rendered inline with no toggle so reviewers can scan quickly.
Included
Excluded
Data Extraction
Two-tier extraction with full provenance: CT.gov-linked publication tables for the primary tier, and regex-based PubMed-abstract back-compute for the sensitivity tier.
Methodology
- Two-tier provenance: (a) CT.gov-linked publications with explicit table extraction; (b) PubMed-abstract back-computed via regex on Sens%/Spec% + N_pos/N_neg.
- Back-compute formula:
TP = round(Sens% × N_pos),FN = N_pos − TP,TN = round(Spec% × N_neg),FP = N_neg − TN. - Negation-context guard (per
lessons.md): each Sens%/Spec% match scanned ±30 chars for negation tokens (not, non, never, excluding); none of the 5 included rows triggered the guard.
Per-study extraction (2×2 + Clopper–Pearson exact CIs)
Mirrors the Trials tab; values are recomputed at page-load by the same engine.
| Study | Year | n+ | n− | TP | FP | FN | TN | Sens (95% CI) | Spec (95% CI) | Source | Provenance |
|---|
Raw quote panels (back-computed sources)
Verbatim text from the abstract that the regex matched. Click a study to expand.
Inter-rater agreement
raw_quote provenance preserved for reviewer audit; click the DOI link in each row to inspect the source.
Detailed extraction (per-study)
Per-study extraction grid with study design, reference-standard specifics, clinical status (MCI / dementia / cognitively unimpaired / mixed), assay platform (Lilly MSD / C2N ALZpath / Janssen Roche / Quanterix Simoa / Fujirebio Lumipulse), APOE strata, population setting (memory clinic / population-based / primary care), funding, and conflict-of-interest. All fields are editable when edit-mode is ON.
QUADAS-2 inline flags (brief; full grid in QUADAS-2 tab)
Brief per-study notes on patient selection, index test, reference standard, and flow & timing risk-of-bias domains. The full Whiting 2011 grid with signaling questions and editable judgments is in the QUADAS-2 tab.
| Study | QUADAS-2 inline flag |
|---|---|
| APACE 0/1h hs-cTnI - Jaeger 2016 | Low risk on patient selection / index test / reference standard / flow & timing. Validation-cohort N=750 with FN=0 by design in the rule-out arm (Sens 100% in validation cohort). |
| APACE 0/2h hs-cTnT - Reichlin 2015 | Low risk overall; external-validation cohort N=517; 0/2h algorithm rather than 0/1h, retained for engine-handles-both-intervals demonstration. |
| APACE 0/1h direct-comparison hs-cTnI - Boeddinghaus 2018 | Low risk; direct head-to-head 4-strategy comparison in same patients. Approximate 2x2 back-computed from reported Sens/Spec/N; flagged for v1.1 full-text re-extraction. |
| ESC 0/1h outcome study - Twerenbold 2019 | Real-world deployment study with mixed local-lab hs-cTnI/hs-cTnT; lower internal validity for index AMI but higher external validity for the ESC 0/1h algorithm. 30-day MACE follow-up included in adjudication. |
| RAPID-TnT 0/1h hs-cTnT RCT - Chew 2019 | Low risk overall; RCT design (0/1h vs 0/3h protocol). Endpoint is 30-day death or MI composite, not pure index AMI — FN definition includes management-outcome events among discharged patients. |
QUADAS-2 Risk of Bias & Applicability
Full Whiting et al. 2011 (Ann Intern Med 155:529) grid: four domains (Patient Selection, Index Test, Reference Standard, Flow & Timing) × signaling questions × Risk-of-Bias and Applicability-Concerns judgments. Pre-populated from the inline flags in the Extraction tab; reviewers override every cell via edit-mode. Applicability concerns are NOT applicable to Flow & Timing (Whiting 2011).
Summary table (traffic-light)
| Study | Patient Selection | Index Test | Reference Standard | Flow & Timing | |||
|---|---|---|---|---|---|---|---|
| RoB | App | RoB | App | RoB | App | RoB | |
Risk-of-bias traffic-light grid
Per Whiting 2011: 7 cells per study (Patient Selection RoB / App; Index Test RoB / App; Reference Standard RoB / App; Flow & Timing RoB — no Applicability for Flow & Timing). Click a cell to scroll to that study's detailed grid below. Stacked-bar chart shows the percentage breakdown across all 5 studies for each domain.
Per-study grid
GRADE-DTA evidence summary
Per Schunemann 2008 / 2020 GRADE for diagnostic test accuracy: each pooled outcome (Sensitivity, Specificity, DOR) is rated across 5 domains (Risk of bias, Inconsistency, Indirectness, Imprecision, Publication bias). Triggers auto-fill from the engine output, the QUADAS-2 panel, and Deeks' funnel test (see Heterogeneity tab). Reviewers may override any cell when edit-mode is ON; overrides are flagged with a manual marker and persist to localStorage.
Certainty floor 0; starts HIGH (4 = ⊕⊕⊕⊕) and subtracts the per-row downgrade. Levels: HIGH ⊕⊕⊕⊕ / MODERATE ⊕⊕⊕○ / LOW ⊕⊕○○ / VERY LOW ⊕○○○.
Pooled summary
Predictive values at chosen prevalence
The unique RapidMeta DTA hook — move the slider to see how PPV and NPV change with disease prevalence.
CI strategy: extreme-case bounds (Sens-CI × Spec-CI corners). Default 10% prevalence reflects an outpatient mixed-symptom community wave; adjust slider for your clinical setting (1–5% asymptomatic screening, 30–50% symptomatic outpatient peak).
Tier selection (secondary — engine demonstration)
The dominant heterogeneity axes for hs-cTn 0/1h are assay platform (Roche hs-cTnT vs Abbott hs-cTnI vs Siemens hs-cTnI) and algorithm interval (0/1h vs 0/2h). The per-strategy headline cards above are the primary clinical-utility metrics; the pooled tiers below are engine-demonstration only.
Disclosure: Different hs-cTn assays (Roche hs-cTnT, Abbott hs-cTnI, Siemens hs-cTnI) classify slightly different patient populations as “positive” at the ESC-recommended cutoffs because the assays measure different troponin epitopes with different LoD and 99th-percentile thresholds. Pooling them in a single Sens/Spec hides this assay-platform gradient. Clinical interpretation should be per-assay.
Three pre-computed tiers reflect different design strata for the headline pool. Default is APACE + RAPID-TnT primary (k=5) — all 5 multicentre prospective ED-cohort + RCT validation studies. The Sensitivity tier (k=2) is descriptive-only (Twerenbold 2017 renal subgroup + Shah 2018 High-STEACS implementation RCT). The Combined tier (k=7) adds the sensitivity-tier studies to the primary pool (with mixed-design caveat).
Fagan nomogram — pre-test → post-test probability
Move the slider to translate a pre-test (clinical-suspicion) probability into a post-test probability using the chosen tier's pooled LR+ and LR−. The nomogram beneath shows the classical 3-axis construction: pre-test probability on the left, likelihood ratio in the middle, post-test probability on the right.
Slider is on a log scale (0.1% to 99.6%) so the nomogram axes are linear in log-odds. Default 10% reflects an outpatient mixed-symptom community wave.
Included trials
Per-study Sensitivity and Specificity with Clopper–Pearson exact 95% confidence intervals. Provenance column shows the data source: ctgov_pub_table_via_abstract (CT.gov-linked publication abstract), pubmed_abstract_raw_counts, or pubmed_abstract_back_computed.
| Study | Year | Country | n+ | n− | TP | FP | FN | TN | Sens (95% CI) | Spec (95% CI) | Source | Provenance |
|---|
Forest plot
Paired forest: per-study Sensitivity (left) and Specificity (right) with 95% Clopper–Pearson exact CIs. The pooled summary row (blue) uses the bivariate model estimate for the active tier.
SROC space
Summary ROC plot in (1−Specificity, Sensitivity) coordinates. Grey dots = per-study estimates; red dashed ellipse = 95% confidence region from the bivariate fit; blue dashed curve = HSROC reparameterisation (Harbord 2007); large red dot = pooled summary point.
Heterogeneity
Bivariate variance components on the logit scale, threshold-effect diagnostic, and convergence audit. Note: I² is not directly defined for the bivariate DTA model — tau² on logit-Sens / logit-Spec is the canonical between-study heterogeneity metric (Reitsma 2005).
Continuity-correction bias-toward-null caveat. When a 0.5 conditional correction is triggered by a zero cell, the implied logit is shrunk toward 0, which biases pooled Sens and Spec toward the centre of the SROC space (Sweeting 2004 Stat Med 23:1351). For hs-cTn 0/1h Jaeger 2016 has FN=0 (Sens=100% in the validation cohort), which DOES trigger the conditional 0.5 correction. The corrected logit is pulled away from infinity toward a finite value, so the pooled Sens estimate is pulled slightly downward from the cell-by-cell average; the Spec estimate is unaffected because no FP cell is zero. This is the conservative direction (under-states Sens slightly) and is well within the prediction-interval width.
Deeks' funnel-asymmetry test
Deeks 2005: regress ln(DOR) on 1/√ESS where ESS = effective sample size = 4·n+ ·n− / (n+ + n−). The slope tests funnel asymmetry; p < 0.10 suggests possible publication bias. Skipped when k < 5.
Sensitivity (leave-one-out)
For each study i in the active tier, refit the bivariate model with study i excluded and record pooled Sens, Spec, DOR. The largest mover quantifies which single study most influences the headline summary. When removing a study takes the remaining pool to 2≤k<5 the engine falls back to the FE bivariate; when it leaves k=1 the engine reports per-axis Clopper–Pearson (single_study) instead of a pooled estimate.
Subgroups
Filter the combined-tier study pool (k=5) by pre-specified covariates and refit. Minimum k=3 required for a refit; below this threshold the subgroup is reported descriptively only.
Methods
Continuity-correction policy
Conditional 0.5 added to all four cells of every study, and only when at least one cell of any study in the pool is zero. Unconditional correction biases the diagnostic odds ratio toward the null (Sweeting 2004) and is therefore not used here.
GRADE-DTA notes
Certainty assessment is informed by (a) study limitations — QUADAS-2 is tabulated in the QUADAS-2 tab; auto-assessed RoB judgments feed the GRADE Risk of Bias domain. Reviewer overrides in edit mode persist via localStorage and are included in JSON export; (b) inconsistency — visible heterogeneity (population, specimen, reference standard) prompts downgrading; (c) indirectness — reference-standard variability across tiers is the principal source; (d) imprecision — per Schunemann 2020 GRADE-DTA, the imprecision rating uses an editable clinical decision threshold (set per outcome in the GRADE tab); when no threshold is supplied the engine falls back to a heuristic CI-width assessment, prefixed "[Heuristic]" in the rationale. For DOR, the CI width is computed on the log scale (log(DOR_ub / DOR_lb)); (e) publication bias — not formally assessed (Deeks' funnel plot requires k≥10). Tier divergence >5pp on Sens or Spec is surfaced as a headline banner.
R cross-validation (mada)
Build-time validation log
r_validation_log.json not yet generated (T18)
Provenance audit
Per-study source & verbatim raw quote for back-computed estimates.
| Study | Provenance | Source link | Raw quote (back-computed only) |
|---|
References
Vancouver-style citations for included studies plus methodological references for the engine and validation package. PubMed (PMID), DOI, and ClinicalTrials.gov (NCT) links are provided where available.
Scientific Output
Auto-generated manuscript text rendered from the live engine fit. Each section has a copy-to-clipboard button. Edit-mode changes (e.g. TP/FP/FN/TN values) re-render the Results paragraph automatically.