BioGrade · expert reasoning data for biopharma agentsEnvironmentsBenchmarkCompare modelsData flywheelThesis
← Eligibility-Criteria Authoring
Clinical / Medical · Medical monitor

Eligibility-Criteria Authoring — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T09:13:25.418743+00:00 · 3 tool calls · 40.4s · 7919 tokens
run id: eligibility_authoring_20260606_021119_03_author-the-inclusion-exclusion-criteria-for-a-ph

Query

Author the inclusion/exclusion criteria for a Phase 2 trial of a JAK inhibitor in moderate-to-severe rheumatoid arthritis. Address the class boxed-warning risks (serious infection, VTE/PE, MACE, malignancy) while keeping the eligible RA population realistic.

Trajectory

Agent · turn 1

I'll author these criteria grounded in the JAK inhibitor safety profile and RA trial precedent. Let me pull the relevant references first.

⚙ calls get_safety_profile(drug_class=JAK inhibitor)
⚙ calls get_precedent_criteria(indication=Rheumatoid arthritis)
⚙ calls get_lab_thresholds()
↳ get_safety_profile result
show data
{
  "drug_class": "JAK inhibitor",
  "class_effect_aes": [
    "Serious and opportunistic infections (TB reactivation, herpes zoster)",
    "Venous thromboembolism / pulmonary embolism (boxed warning)",
    "Major adverse cardiovascular events (MACE)",
    "Malignancy signal (lymphoma, NMSC)",
    "Cytopenias and lipid/transaminase elevations"
  ],
  "monitoring": [
    "Baseline TB (IGRA/PPD) and hepatitis B/C screening",
    "Baseline + periodic CBC, lipid panel, LFTs",
    "VTE risk assessment; vigilance for thrombosis symptoms",
    "Cardiovascular risk-factor assessment"
  ],
  "contraindicated_comorbidities": [
    "Active or latent untreated tuberculosis; active serious infection",
    "History of VTE/PE or high thrombotic risk",
    "Recent major cardiovascular event / high MACE risk (esp. older smokers)",
    "Active or recent malignancy",
    "Active hepatitis B/C"
  ],
  "ddi_flags": [
    "Strong CYP3A4 inhibitors raise exposure (dose-adjust)",
    "Avoid combination with other potent immunosuppressants / biologics",
    "Live vaccines contraindicated"
  ],
  "notes": "Boxed warnings (infection, VTE, MACE, malignancy) make infection screening and thrombo-cardiovascular risk exclusions central to eligibility."
}
↳ get_precedent_criteria result
show data
{
  "indication": "Rheumatoid arthritis",
  "precedent_trials": [
    "ORAL Surveillance (tofacitinib)",
    "SELECT program (upadacitinib)"
  ],
  "inclusion": [
    "Adults meeting ACR/EULAR classification criteria for RA",
    "Moderate-to-severe active disease despite csDMARD (e.g. methotrexate)",
    "Adequate organ function (hematologic, hepatic, renal)",
    "Up-to-date age-appropriate cancer screening"
  ],
  "exclusion": [
    "Active or latent untreated tuberculosis; active serious/chronic infection",
    "History of VTE/PE or high thrombotic risk (JAK boxed warning)",
    "Recent major cardiovascular event / high MACE risk",
    "Active or recent malignancy (excluding adequately treated NMSC)",
    "Active hepatitis B/C; significant cytopenia at baseline"
  ],
  "notes": "Non-onc autoimmune precedents pivot eligibility around infection screening and the VTE/MACE/malignancy boxed-warning risks rather than RECIST/measurable disease."
}
↳ get_lab_thresholds result
show data
{
  "hematologic": [
    {
      "parameter": "Absolute neutrophil count (ANC)",
      "typical_threshold": ">= 1.5 x 10^9/L",
      "rationale": "Adequate marrow reserve before a myelosuppressive agent; lower (>=1.0) sometimes allowed if marrow involvement."
    },
    {
      "parameter": "Platelets",
      "typical_threshold": ">= 100 x 10^9/L (>=75 if marrow involvement)",
      "rationale": "Bleeding risk and tolerance of thrombocytopenia."
    },
    {
      "parameter": "Hemoglobin",
      "typical_threshold": ">= 9.0 g/dL (transfusion-independent)",
      "rationale": "Baseline reserve; many protocols require independence from recent transfusion."
    }
  ],
  "hepatic": [
    {
      "parameter": "Total bilirubin",
      "typical_threshold": "<= 1.5 x ULN (<=3 x ULN if Gilbert's/liver mets)",
      "rationale": "Hepatic clearance reserve; relaxed for documented Gilbert's or hepatic metastases."
    },
    {
      "parameter": "AST / ALT",
      "typical_threshold": "<= 3 x ULN (<=5 x ULN if liver metastases)",
      "rationale": "Baseline hepatocellular integrity; key for hepatotoxic agents (PI3Ki, JAKi)."
    },
    {
      "parameter": "Albumin",
      "typical_threshold": ">= 2.8-3.0 g/dL (some protocols)",
      "rationale": "Synthetic liver function / nutritional status, esp. GI cancers."
    }
  ],
  "renal": [
    {
      "parameter": "Creatinine clearance (Cockcroft-Gault)",
      "typical_threshold": ">= 50-60 mL/min",
      "rationale": "Renal elimination reserve; threshold depends on renal clearance of the drug."
    },
    {
      "parameter": "Serum creatinine",
      "typical_threshold": "<= 1.5 x ULN",
      "rationale": "Simpler surrogate when CrCl not used."
    }
  ],
  "cardiac": [
    {
      "parameter": "Left-ventricular ejection fraction (LVEF)",
      "typical_threshold": ">= 50% (institutional LLN)",
      "rationale": "Required for cardiotoxic agents (anti-HER2, anthracycline exposure)."
    },
    {
      "parameter": "QTc (Fridericia)",
      "typical_threshold": "<= 470 ms (women) / <= 450 ms (men)",
      "rationale": "Exclude baseline prolongation for QT-liable agents; pair with congenital long-QT exclusion."
    }
  ],
  "coagulation_metabolic": [
    {
      "parameter": "INR / aPTT (if on anticoagulation off-study)",
      "typical_threshold": "within therapeutic range / <= 1.5 x ULN",
      "rationale": "Bleeding risk, esp. for agents with hemorrhage signal (BTKi)."
    },
    {
      "parameter": "Fasting glucose / HbA1c",
      "typical_threshold": "HbA1c <= 6.5-8.0% per protocol",
      "rationale": "Baseline glycemic control for hyperglycemia-liable agents (PI3K-alpha)."
    }
  ],
  "notes": "Teaching-snapshot typical oncology cutoffs. Exact thresholds and relaxations (marrow involvement, liver mets, Gilbert's) are drug- and protocol-specific and must be set against the investigator's brochure and standard of care."
}
Agent · turn 2

Phase 2 Trial Eligibility Criteria

JAK Inhibitor in Moderate-to-Severe Rheumatoid Arthritis

Design context: Eligibility pivots around the four JAK-class boxed warnings (serious infection, VTE/PE, MACE, malignancy), modeled on the precedent set by ORAL Surveillance (tofacitinib) and the SELECT program (upadacitinib). Lab thresholds below are adapted from standard organ-function cutoffs to a non-oncology autoimmune population — i.e., screening windows rather than the marrow-/tumor-relaxed thresholds used in oncology.

INCLUSION CRITERIA

Disease definition & activity
1. Adults ≥18 years (see exclusion #9 for age-stratified MACE/malignancy considerations).
2. Diagnosis of RA meeting 2010 ACR/EULAR classification criteria, with disease duration ≥6 months.
3. Moderate-to-severe active disease at screening and baseline, defined by:
- ≥6 swollen joints (66-joint count) and ≥6 tender joints (68-joint count), and
- hs-CRP ≥ upper limit of normal or ESR ≥28 mm/hr.
4. Inadequate response, intolerance, or contraindication to ≥1 conventional synthetic DMARD (e.g., methotrexate) at an adequate dose for ≥3 months.
5. If on background csDMARD, stable dose for ≥4 weeks prior to baseline (background regimen to remain stable through the primary endpoint).

Functional & organ-function status
6. Adequate hematologic, hepatic, and renal function at screening:
- ANC ≥ 1.5 × 10⁹/L
- Lymphocytes ≥ 0.5 × 10⁹/L (JAK-specific; lymphopenia predisposes to opportunistic infection)
- Platelets ≥ 100 × 10⁹/L
- Hemoglobin ≥ 9.0 g/dL
- AST and ALT ≤ 2 × ULN; total bilirubin ≤ 1.5 × ULN (≤3 × ULN if documented Gilbert's)
- eGFR / CrCl (Cockcroft-Gault) ≥ 40 mL/min (JAKi are renally cleared; threshold set permissively for a chronic non-onc population)

  1. Up-to-date, age- and sex-appropriate cancer screening per local standard of care (e.g., cervical, breast, colorectal, skin).

  2. Women of childbearing potential: negative pregnancy test and agreement to use highly effective contraception through the safety follow-up window; men with WOCBP partners similarly.

  3. Able to provide informed consent and comply with visit schedule.

EXCLUSION CRITERIA

A. Serious & opportunistic infection (boxed warning)

  1. Active serious infection, or any infection requiring parenteral antimicrobials within 4 weeks, or oral antimicrobials within 2 weeks of baseline.
  2. Latent or active tuberculosis: positive IGRA (preferred) or PPD without documented completion/initiation of adequate latent-TB therapy; or chest imaging/history consistent with active/prior untreated TB.
  3. Active or chronic hepatitis B (HBsAg+ or HBV DNA+) or hepatitis C (HCV RNA+); known HIV infection.
  4. History of recurrent or disseminated herpes zoster, or any disseminated/serious opportunistic infection. (Strongly encourage recombinant zoster vaccination prior to enrollment; live vaccines are prohibited within 4 weeks of baseline and during treatment.)
  5. Chronic/recurrent infection requiring ongoing suppressive therapy (e.g., chronic osteomyelitis, bronchiectasis with frequent exacerbations).

B. VTE / PE (boxed warning)

  1. Personal history of DVT or PE.
  2. Known inherited or acquired hypercoagulable state (e.g., Factor V Leiden, antiphospholipid syndrome) or high baseline thrombotic risk — e.g., major surgery within 12 weeks, prolonged immobilization, or combined oral contraceptive use in a patient with additional VTE risk factors.
  3. Ongoing requirement for full-dose therapeutic anticoagulation for active thrombosis (concurrent VTE under treatment).

C. MACE / cardiovascular (boxed warning — ORAL Surveillance signal)

  1. Enrichment for MACE risk: patients ≥65 years who are current/former long-term smokers with ≥1 additional cardiovascular risk factor should be excluded or, per a risk-stratified protocol, enrolled only after benefit-risk committee review. (Mirrors the post–ORAL Surveillance label restriction; keep the broader RA population eligible while excluding the highest-risk subgroup.)
  2. Major adverse cardiovascular event (MI, unstable angina, stroke/TIA, coronary revascularization) within 6 months.
  3. NYHA Class III–IV congestive heart failure.
  4. Uncontrolled hypertension (sustained SBP >160 or DBP >100 despite therapy).

D. Malignancy (boxed warning)

  1. Active malignancy, or history of malignancy within 5 years, except adequately treated non-melanoma skin cancer, in-situ cervical carcinoma, or other in-situ malignancy treated with curative intent.
  2. History of lymphoproliferative disorder or lymphoma.

E. Hematologic / hepatic / metabolic safety

  1. Baseline cytopenia below inclusion thresholds (ANC <1.5, lymphocytes <0.5, platelets <100 × 10⁹/L, Hgb <9.0 g/dL).
  2. Transaminases >2 × ULN or other clinically significant hepatic impairment (Child-Pugh B/C).
  3. Severe uncontrolled dyslipidemia at baseline (JAKi raise LDL/HDL; require lipid panel at screening and periodic monitoring rather than absolute exclusion unless clinically significant).

F. Concomitant therapy & general

  1. Use of biologic DMARDs or another targeted synthetic DMARD (including another JAKi) within the appropriate washout (typically ≥4 weeks or 5 half-lives, longer for B-cell–depleting agents).
  2. Concurrent use of strong CYP3A4 inhibitors or inducers that cannot be discontinued (alters JAKi exposure; dose-adjustment or exclusion per protocol).
  3. Live or live-attenuated vaccine within 4 weeks of baseline.
  4. Pregnancy or breastfeeding.
  5. Any condition that, in the investigator's judgment, would compromise safety or interpretability.

Required Baseline Monitoring (mandated at screening)

Design notes

Caveat: These are precedent-grounded teaching criteria. Final thresholds, washout durations, the exact MACE risk-stratification algorithm, and CYP3A4 handling must be reconciled against the specific agent's Investigator's Brochure and current regulatory guidance before use.

Final output

Phase 2 Trial Eligibility Criteria

JAK Inhibitor in Moderate-to-Severe Rheumatoid Arthritis

Design context: Eligibility pivots around the four JAK-class boxed warnings (serious infection, VTE/PE, MACE, malignancy), modeled on the precedent set by ORAL Surveillance (tofacitinib) and the SELECT program (upadacitinib). Lab thresholds below are adapted from standard organ-function cutoffs to a non-oncology autoimmune population — i.e., screening windows rather than the marrow-/tumor-relaxed thresholds used in oncology.

INCLUSION CRITERIA

Disease definition & activity
1. Adults ≥18 years (see exclusion #9 for age-stratified MACE/malignancy considerations).
2. Diagnosis of RA meeting 2010 ACR/EULAR classification criteria, with disease duration ≥6 months.
3. Moderate-to-severe active disease at screening and baseline, defined by:
- ≥6 swollen joints (66-joint count) and ≥6 tender joints (68-joint count), and
- hs-CRP ≥ upper limit of normal or ESR ≥28 mm/hr.
4. Inadequate response, intolerance, or contraindication to ≥1 conventional synthetic DMARD (e.g., methotrexate) at an adequate dose for ≥3 months.
5. If on background csDMARD, stable dose for ≥4 weeks prior to baseline (background regimen to remain stable through the primary endpoint).

Functional & organ-function status
6. Adequate hematologic, hepatic, and renal function at screening:
- ANC ≥ 1.5 × 10⁹/L
- Lymphocytes ≥ 0.5 × 10⁹/L (JAK-specific; lymphopenia predisposes to opportunistic infection)
- Platelets ≥ 100 × 10⁹/L
- Hemoglobin ≥ 9.0 g/dL
- AST and ALT ≤ 2 × ULN; total bilirubin ≤ 1.5 × ULN (≤3 × ULN if documented Gilbert's)
- eGFR / CrCl (Cockcroft-Gault) ≥ 40 mL/min (JAKi are renally cleared; threshold set permissively for a chronic non-onc population)

  1. Up-to-date, age- and sex-appropriate cancer screening per local standard of care (e.g., cervical, breast, colorectal, skin).

  2. Women of childbearing potential: negative pregnancy test and agreement to use highly effective contraception through the safety follow-up window; men with WOCBP partners similarly.

  3. Able to provide informed consent and comply with visit schedule.

EXCLUSION CRITERIA

A. Serious & opportunistic infection (boxed warning)

  1. Active serious infection, or any infection requiring parenteral antimicrobials within 4 weeks, or oral antimicrobials within 2 weeks of baseline.
  2. Latent or active tuberculosis: positive IGRA (preferred) or PPD without documented completion/initiation of adequate latent-TB therapy; or chest imaging/history consistent with active/prior untreated TB.
  3. Active or chronic hepatitis B (HBsAg+ or HBV DNA+) or hepatitis C (HCV RNA+); known HIV infection.
  4. History of recurrent or disseminated herpes zoster, or any disseminated/serious opportunistic infection. (Strongly encourage recombinant zoster vaccination prior to enrollment; live vaccines are prohibited within 4 weeks of baseline and during treatment.)
  5. Chronic/recurrent infection requiring ongoing suppressive therapy (e.g., chronic osteomyelitis, bronchiectasis with frequent exacerbations).

B. VTE / PE (boxed warning)

  1. Personal history of DVT or PE.
  2. Known inherited or acquired hypercoagulable state (e.g., Factor V Leiden, antiphospholipid syndrome) or high baseline thrombotic risk — e.g., major surgery within 12 weeks, prolonged immobilization, or combined oral contraceptive use in a patient with additional VTE risk factors.
  3. Ongoing requirement for full-dose therapeutic anticoagulation for active thrombosis (concurrent VTE under treatment).

C. MACE / cardiovascular (boxed warning — ORAL Surveillance signal)

  1. Enrichment for MACE risk: patients ≥65 years who are current/former long-term smokers with ≥1 additional cardiovascular risk factor should be excluded or, per a risk-stratified protocol, enrolled only after benefit-risk committee review. (Mirrors the post–ORAL Surveillance label restriction; keep the broader RA population eligible while excluding the highest-risk subgroup.)
  2. Major adverse cardiovascular event (MI, unstable angina, stroke/TIA, coronary revascularization) within 6 months.
  3. NYHA Class III–IV congestive heart failure.
  4. Uncontrolled hypertension (sustained SBP >160 or DBP >100 despite therapy).

D. Malignancy (boxed warning)

  1. Active malignancy, or history of malignancy within 5 years, except adequately treated non-melanoma skin cancer, in-situ cervical carcinoma, or other in-situ malignancy treated with curative intent.
  2. History of lymphoproliferative disorder or lymphoma.

E. Hematologic / hepatic / metabolic safety

  1. Baseline cytopenia below inclusion thresholds (ANC <1.5, lymphocytes <0.5, platelets <100 × 10⁹/L, Hgb <9.0 g/dL).
  2. Transaminases >2 × ULN or other clinically significant hepatic impairment (Child-Pugh B/C).
  3. Severe uncontrolled dyslipidemia at baseline (JAKi raise LDL/HDL; require lipid panel at screening and periodic monitoring rather than absolute exclusion unless clinically significant).

F. Concomitant therapy & general

  1. Use of biologic DMARDs or another targeted synthetic DMARD (including another JAKi) within the appropriate washout (typically ≥4 weeks or 5 half-lives, longer for B-cell–depleting agents).
  2. Concurrent use of strong CYP3A4 inhibitors or inducers that cannot be discontinued (alters JAKi exposure; dose-adjustment or exclusion per protocol).
  3. Live or live-attenuated vaccine within 4 weeks of baseline.
  4. Pregnancy or breastfeeding.
  5. Any condition that, in the investigator's judgment, would compromise safety or interpretability.

Required Baseline Monitoring (mandated at screening)

Design notes

Caveat: These are precedent-grounded teaching criteria. Final thresholds, washout durations, the exact MACE risk-stratification algorithm, and CYP3A4 handling must be reconciled against the specific agent's Investigator's Brochure and current regulatory guidance before use.

Reference answer key (deterministic) — open after grading

Expected-coverage checklist for drug class 'JAK inhibitor' — a grading aid, NOT ground truth. A strong I/E list visibly protects against each liability (exclusion / lab cutoff / monitoring) while keeping the target population enrollable.

Class-effect liability to addressWhy it constrains eligibility
Serious and opportunistic infections (TB reactivation, herpes zoster)Baseline TB/HBV/HCV screening; exclude active/latent untreated infection.
Venous thromboembolism / pulmonary embolism (boxed warning)Exclude prior VTE/PE and high thrombotic risk (boxed warning).
Major adverse cardiovascular events (MACE)Exclude recent MACE / high cardiovascular risk.
Malignancy signal (lymphoma, NMSC)Exclude active/recent second malignancy.
Cytopenias and lipid/transaminase elevationsSet ANC/platelet/hemoglobin thresholds; CBC monitoring.

Expert grading

Safety-driven exclusions 1 (poor) 5 (excellent)
5: Authors exclusions that specifically protect against THIS drug's liabilities, grounded in its pulled safety profile — e.g. for a DLL3 TCE, excludes active CNS mets and poor cardiac/pulmonary reserve for CRS/ICANS; for a HER2 ADC, hard-excludes ILD history; for a JAK inhibitor, excludes untreated TB/active infection and prior VTE.
1: Generic exclusions that ignore the drug's mechanism, or misses the headline class risk (e.g. no ILD exclusion for a deruxtecan-class ADC; no infection screen for a JAK inhibitor).
Organ-function / lab thresholds 1 (poor) 5 (excellent)
5: Specifies appropriate, justified organ-function cutoffs (ANC, platelets, hemoglobin, bilirubin, AST/ALT, creatinine clearance, LVEF, QTc, HbA1c) tied to the drug's toxicities and the precedent thresholds — e.g. tighter LFT/glucose cutoffs for a hepatotoxic/hyperglycemic PI3Ki, LVEF for a cardiotoxic ADC.
1: Arbitrary or missing thresholds, copies generic numbers without tying them to the drug's risks, or sets cutoffs that are clinically implausible.
Enrollability balance 1 (poor) 5 (excellent)
5: Keeps the target population realistically enrollable — relaxes thresholds where precedent allows (marrow involvement, liver mets, Gilbert's; treated/stable brain mets), and does not stack so many exclusions that the trial cannot accrue. Explicitly reasons about the safety-vs-enrollability trade-off.
1: Over-restrictive: excludes the realistic target population into infeasibility (e.g. bars all prior lines, all brain mets, demands pristine organ function) with no enrollability reasoning; or the opposite, ignores safety to maximize accrual.
Precedent alignment & completeness 1 (poor) 5 (excellent)
5: Covers the standard I/E domains for the indication (histologic confirmation, ECOG, measurable disease per RECIST, washout, prior-line definition, life expectancy) and is consistent with the analogous-trial precedent it pulled.
1: Omits whole standard domains (no performance status, no washout, no disease confirmation), or contradicts the precedent criteria for the indication.
Evidence faithfulness & clarity 1 (poor) 5 (excellent)
5: Grounds each criterion in the pulled safety/precedent/threshold data rather than memory; criteria are unambiguous and operational (measurable, with explicit values, timeframes, and units a site could screen against).
1: Fabricates risks or thresholds not in the data, contradicts the tool outputs, or writes vague, non-operational criteria a coordinator could not apply.
Overall verdict
Your name / ID