← Eligibility-Criteria Authoring comparison · model: GPT (frontier)
LLM-judge score: 4.8 / 5 · strong
safety_exclusions: 5 lab_thresholds: 5 enrollability: 5 precedent_completeness: 5 faithfulness_clarity: 4
The agent comprehensively addresses all class-effect liabilities: CRS (cardiopulmonary reserve, infection, inpatient monitoring), ICANS (CNS mets, seizure, baseline neuro exam, ICE scoring), cytopenias (ANC/platelet/Hgb thresholds with marrow-involvement relaxations), and infection/hypogammaglobulinemia (HBV/HCV/HIV screening). Lab cutoffs are clinically plausible, operational, and tied to the drug's risks, and enrollability is explicitly balanced with marrow/liver-mets/Gilbert's relaxations and staged escalation-to-expansion loosening. Minor deduction on faithfulness: tumor flare/pyrexia is not explicitly captured as a discrete criterion, and the criteria are grounded more in standard practice than visibly traced to specific pulled tool values.
Clinical / Medical · Medical monitor

Eligibility-Criteria Authoring — agent trajectory for expert review

gpt-5.2-chat-latest · 2026-06-06T10:25:37.717295+00:00 · 3 tool calls · 20.4s · 4125 tokens
run id: eligibility_authoring_20260606_031816_eligibility-authoring__gpt-frontier

Query

Author the inclusion/exclusion criteria for a Phase 1 first-in-human trial of a DLL3 T-cell engager (BiTE) in relapsed/refractory extensive-stage small cell lung cancer (ES-SCLC), accounting for cytokine release syndrome and neurotoxicity (ICANS) risk. Balance safety against enrollability.

Trajectory

Agent · turn 1
⚙ calls get_safety_profile(drug_class=DLL3 T-cell engager)
⚙ calls get_precedent_criteria(indication=ES-SCLC)
⚙ calls get_lab_thresholds()
↳ get_safety_profile result
show data
{
  "drug_class": "DLL3 T-cell engager",
  "class_effect_aes": [
    "Cytokine release syndrome (CRS) \u2014 common, mostly cycle-1, can be high-grade",
    "Immune effector cell-associated neurotoxicity syndrome (ICANS) / neurotoxicity",
    "Cytopenias (neutropenia, anemia, thrombocytopenia)",
    "Hypogammaglobulinemia / infection risk from on-target B/neuroendocrine effects",
    "Tumor flare / pyrexia"
  ],
  "monitoring": [
    "Inpatient monitoring for CRS during step-up/priming doses (cycle 1)",
    "Frequent vitals, ferritin/CRP trend during CRS window",
    "Baseline + on-treatment neuro exam (ICE score) for ICANS",
    "Baseline ECG/echo if cardiac reserve is a concern during CRS",
    "CBC with differential before each dose"
  ],
  "contraindicated_comorbidities": [
    "Active CNS metastases / leptomeningeal disease (raises ICANS danger)",
    "Active autoimmune CNS disease or seizure disorder",
    "Inadequate cardiac reserve (CRS hemodynamic stress) \u2014 recent MI, NYHA III/IV CHF",
    "Active uncontrolled infection (CRS masks/worsens sepsis)",
    "Significant baseline hypoxia / poor pulmonary reserve"
  ],
  "ddi_flags": [
    "Live vaccines contraindicated (immune activation)",
    "Chronic systemic immunosuppression / high-dose steroids blunt efficacy and confound CRS grading",
    "Tocilizumab/steroids must be available on-site as CRS rescue"
  ],
  "notes": "First-in-human TCEs need a step-up/priming dose schedule and mandated CRS/ICANS rescue medication on hand; cycle-1 inpatient observation is standard."
}
↳ get_precedent_criteria result
show data
{
  "indication": "ES-SCLC",
  "precedent_trials": [
    "Tarlatamab DeLLphi-301/304 (DLL3 TCE)",
    "IMpower133 (1L chemo-IO)"
  ],
  "inclusion": [
    "Histologically/cytologically confirmed extensive-stage SCLC",
    "Relapsed/refractory after >=1 prior platinum-based regimen (line per protocol)",
    "Measurable disease per RECIST v1.1",
    "ECOG performance status 0-1",
    "Adequate hematologic, hepatic, renal organ function (see lab thresholds)",
    "Life expectancy >=12 weeks"
  ],
  "exclusion": [
    "Untreated/active/symptomatic CNS metastases (treated, stable may be allowed)",
    "Leptomeningeal disease / carcinomatous meningitis",
    "Active autoimmune disease or condition needing systemic immunosuppression (for IO/TCE)",
    "Insufficient washout from prior anticancer therapy (e.g. ~3-4 wks or 5 half-lives)",
    "Uncontrolled intercurrent illness / active infection",
    "Second malignancy requiring active treatment"
  ],
  "notes": "DLL3 TCE precedents often allow treated/stable brain mets but exclude active CNS disease specifically because of ICANS/neurotoxicity risk."
}
↳ 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

Below is a Phase 1, first-in-human, dose-escalation/expansion trial eligibility framework for a DLL3 T‑cell engager (BiTE) in relapsed/refractory extensive-stage SCLC (ES‑SCLC). It is written to balance:


Key Design Assumptions (Operational Context)


Inclusion Criteria

1. Disease Characteristics

  1. Histologically or cytologically confirmed small cell lung cancer.
  2. Extensive-stage disease at study entry.
  3. Relapsed or refractory after:
    - ≥1 prior platinum-based regimen (must have received platinum/etoposide)
    - Prior PD-1/PD-L1 therapy unless contraindicated or not available.
  4. Measurable disease per RECIST v1.1.
  5. Radiographic progression on or after most recent therapy.

2. Performance Status and Prognosis

  1. ECOG performance status 0–1
    (Consider allowing ECOG 2 in dose-expansion once safety is characterized.)
  2. Estimated life expectancy ≥ 12 weeks.

3. Organ Function (within 7–14 days of first dose)

Hematologic

Hepatic

Renal


4. CNS Disease (Balanced for Enrollability)

  1. Treated brain metastases are allowed if:
    - Definitively treated (radiation or surgery)
    - Clinically stable ≥2 weeks
    - Off steroids or on physiologic replacement only (≤10 mg prednisone equivalent)

  2. Asymptomatic untreated brain metastases ≤2 cm may be allowed in dose-expansion only, provided:
    - No mass effect
    - No edema requiring steroids

(Important for enrollability in ES-SCLC while mitigating ICANS risk.)


5. CRS/ICANS Safety-Specific Inclusion

  1. Baseline neurologic exam without clinically significant deficits.
  2. No history of grade ≥3 immune-related neurologic toxicity from prior IO.
  3. Oxygen saturation ≥ 92% on room air.
  4. Adequate cardiac reserve:
    - No symptomatic heart failure
    - No MI within 6 months
    - No unstable arrhythmias

6. Washout Periods

  1. ≥2 weeks from prior chemotherapy or radiation (≥4 weeks for nitrosoureas/mitomycin C).
  2. ≥4 weeks from prior investigational biologic agents.
  3. Toxicities from prior therapy recovered to Grade ≤1 (except alopecia, stable neuropathy ≤Grade 2).

Exclusion Criteria

1. CNS / Neurologic Risk (ICANS Mitigation)

  1. Active, untreated, or symptomatic brain metastases.
  2. Leptomeningeal disease.
  3. History of:
    - Seizure disorder requiring anti-epileptics
    - Stroke within 6 months
    - Clinically significant CNS hemorrhage
  4. Active autoimmune neurologic disease (e.g., MS, myasthenia gravis).
  5. Baseline ≥ Grade 2 cognitive impairment.

2. CRS Risk Amplifiers

  1. Active uncontrolled infection (including sepsis).
  2. Known active hepatitis B, C with viremia.
  3. HIV with detectable viral load.
  4. Ongoing systemic immunosuppression:
    - >10 mg prednisone equivalent daily within 7 days of first dose.
  5. Active autoimmune disease requiring systemic therapy within past 2 years (replacement therapy allowed).

3. Cardiopulmonary Risk (CRS Hemodynamic Stress)

  1. NYHA Class III or IV heart failure.
  2. LVEF < 45–50% (if clinically indicated to assess).
  3. Clinically significant pericardial effusion.
  4. Baseline QTcF > 470 ms.
  5. Significant baseline hypoxia requiring >2L supplemental O₂.
  6. Uncontrolled COPD exacerbation or active pneumonitis.

4. Hematologic / Organ Exclusions

  1. Platelets < 75 × 10⁹/L.
  2. ANC < 1.0 × 10⁹/L.
  3. AST/ALT > 5 × ULN without liver metastases.
  4. Creatinine clearance < 40 mL/min.

5. Other Standard Exclusions

  1. Second active malignancy requiring treatment.
  2. Major surgery within 2 weeks.
  3. Pregnancy or breastfeeding.
  4. Live vaccines within 4 weeks.

Optional Risk Mitigation Measures (Protocol-Specified, Not Eligibility)

To further balance safety and enrollability without over-restricting:


Rationale for Key Decisions

Risk Design Approach Enrollability Impact
CRS Exclude unstable cardiac/pulmonary disease; allow stable comorbidities Preserves real-world population
ICANS Allow treated/stable brain mets Critical for ES-SCLC feasibility
Cytopenias Allow marrow involvement with lower thresholds Prevents over-exclusion
Steroids Allow physiologic replacement Avoids unnecessary exclusions
ECOG 0–1 initially Expand to 2 once safety established

Optional Expansion Cohort Relaxations (After Dose Escalation)

Once RP2D safety is defined:
- Allow ECOG 2
- Allow asymptomatic untreated brain mets
- Lower ANC threshold to 1.0 × 10⁹/L universally
- Broaden CrCl to ≥40 mL/min


If helpful, I can next provide:

Final output

Below is a Phase 1, first-in-human, dose-escalation/expansion trial eligibility framework for a DLL3 T‑cell engager (BiTE) in relapsed/refractory extensive-stage SCLC (ES‑SCLC). It is written to balance:


Key Design Assumptions (Operational Context)


Inclusion Criteria

1. Disease Characteristics

  1. Histologically or cytologically confirmed small cell lung cancer.
  2. Extensive-stage disease at study entry.
  3. Relapsed or refractory after:
    - ≥1 prior platinum-based regimen (must have received platinum/etoposide)
    - Prior PD-1/PD-L1 therapy unless contraindicated or not available.
  4. Measurable disease per RECIST v1.1.
  5. Radiographic progression on or after most recent therapy.

2. Performance Status and Prognosis

  1. ECOG performance status 0–1
    (Consider allowing ECOG 2 in dose-expansion once safety is characterized.)
  2. Estimated life expectancy ≥ 12 weeks.

3. Organ Function (within 7–14 days of first dose)

Hematologic

Hepatic

Renal


4. CNS Disease (Balanced for Enrollability)

  1. Treated brain metastases are allowed if:
    - Definitively treated (radiation or surgery)
    - Clinically stable ≥2 weeks
    - Off steroids or on physiologic replacement only (≤10 mg prednisone equivalent)

  2. Asymptomatic untreated brain metastases ≤2 cm may be allowed in dose-expansion only, provided:
    - No mass effect
    - No edema requiring steroids

(Important for enrollability in ES-SCLC while mitigating ICANS risk.)


5. CRS/ICANS Safety-Specific Inclusion

  1. Baseline neurologic exam without clinically significant deficits.
  2. No history of grade ≥3 immune-related neurologic toxicity from prior IO.
  3. Oxygen saturation ≥ 92% on room air.
  4. Adequate cardiac reserve:
    - No symptomatic heart failure
    - No MI within 6 months
    - No unstable arrhythmias

6. Washout Periods

  1. ≥2 weeks from prior chemotherapy or radiation (≥4 weeks for nitrosoureas/mitomycin C).
  2. ≥4 weeks from prior investigational biologic agents.
  3. Toxicities from prior therapy recovered to Grade ≤1 (except alopecia, stable neuropathy ≤Grade 2).

Exclusion Criteria

1. CNS / Neurologic Risk (ICANS Mitigation)

  1. Active, untreated, or symptomatic brain metastases.
  2. Leptomeningeal disease.
  3. History of:
    - Seizure disorder requiring anti-epileptics
    - Stroke within 6 months
    - Clinically significant CNS hemorrhage
  4. Active autoimmune neurologic disease (e.g., MS, myasthenia gravis).
  5. Baseline ≥ Grade 2 cognitive impairment.

2. CRS Risk Amplifiers

  1. Active uncontrolled infection (including sepsis).
  2. Known active hepatitis B, C with viremia.
  3. HIV with detectable viral load.
  4. Ongoing systemic immunosuppression:
    - >10 mg prednisone equivalent daily within 7 days of first dose.
  5. Active autoimmune disease requiring systemic therapy within past 2 years (replacement therapy allowed).

3. Cardiopulmonary Risk (CRS Hemodynamic Stress)

  1. NYHA Class III or IV heart failure.
  2. LVEF < 45–50% (if clinically indicated to assess).
  3. Clinically significant pericardial effusion.
  4. Baseline QTcF > 470 ms.
  5. Significant baseline hypoxia requiring >2L supplemental O₂.
  6. Uncontrolled COPD exacerbation or active pneumonitis.

4. Hematologic / Organ Exclusions

  1. Platelets < 75 × 10⁹/L.
  2. ANC < 1.0 × 10⁹/L.
  3. AST/ALT > 5 × ULN without liver metastases.
  4. Creatinine clearance < 40 mL/min.

5. Other Standard Exclusions

  1. Second active malignancy requiring treatment.
  2. Major surgery within 2 weeks.
  3. Pregnancy or breastfeeding.
  4. Live vaccines within 4 weeks.

Optional Risk Mitigation Measures (Protocol-Specified, Not Eligibility)

To further balance safety and enrollability without over-restricting:


Rationale for Key Decisions

Risk Design Approach Enrollability Impact
CRS Exclude unstable cardiac/pulmonary disease; allow stable comorbidities Preserves real-world population
ICANS Allow treated/stable brain mets Critical for ES-SCLC feasibility
Cytopenias Allow marrow involvement with lower thresholds Prevents over-exclusion
Steroids Allow physiologic replacement Avoids unnecessary exclusions
ECOG 0–1 initially Expand to 2 once safety established

Optional Expansion Cohort Relaxations (After Dose Escalation)

Once RP2D safety is defined:
- Allow ECOG 2
- Allow asymptomatic untreated brain mets
- Lower ANC threshold to 1.0 × 10⁹/L universally
- Broaden CrCl to ≥40 mL/min


If helpful, I can next provide:

Reference answer key (deterministic) — open after grading

Expected-coverage checklist for drug class 'DLL3 T-cell engager' — 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
Cytokine release syndrome (CRS) — common, mostly cycle-1, can be high-gradeDrives cycle-1 inpatient monitoring + exclude poor cardiac/pulmonary reserve and active infection.
Immune effector cell-associated neurotoxicity syndrome (ICANS) / neurotoxicityExclude active CNS mets / leptomeningeal / seizure disorder; baseline neuro exam.
Cytopenias (neutropenia, anemia, thrombocytopenia)Set ANC/platelet/hemoglobin thresholds; CBC monitoring.
Hypogammaglobulinemia / infection risk from on-target B/neuroendocrine effectsBaseline TB/HBV/HCV screening; exclude active/latent untreated infection.
Tumor flare / pyrexiaShould be reflected in an exclusion, lab threshold, or monitoring requirement.

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