BioGrade · expert reasoning data for biopharma agentsEnvironmentsBenchmarkCompare modelsData flywheelThesis
← Eligibility-Criteria Authoring comparison · model: GPT-4o mini
LLM-judge score: 4.0 / 5 · acceptable
safety_exclusions: 4 lab_thresholds: 4 enrollability: 4 precedent_completeness: 5 faithfulness_clarity: 3
The agent covers CRS (cardiac/pulmonary reserve), ICANS (CNS mets, leptomeningeal, seizure disorder, baseline neuro exam), and cytopenia thresholds well, with sensible organ-function cutoffs and explicit enrollability balance (allowing treated/stable brain mets). However, it misses two checklist liabilities: infection screening is generic ('active infection') without explicit TB/HBV/HCV baseline screening for hypogammaglobulinemia/infection risk, and tumor flare/pyrexia is not addressed. Faithfulness is weakened because criteria are not visibly tied to the specific pulled safety_profile/precedent values—numbers appear to reflect generic conventions rather than cited tool data.
Clinical / Medical · Medical monitor

Eligibility-Criteria Authoring — agent trajectory for expert review

gpt-4o-mini · 2026-06-06T10:25:55.144398+00:00 · 2 tool calls · 10.9s · 2278 tokens
run id: eligibility_authoring_20260606_031816_eligibility-authoring__gpt-4o-mini

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_precedent_criteria(indication=ES-SCLC)
⚙ calls get_safety_profile(drug_class=DLL3 T-cell engager)
↳ 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_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."
}
Agent · turn 2

Here's the proposed inclusion/exclusion criteria for a Phase 1 first-in-human trial of a DLL3 T-cell engager (BiTE) in patients with relapsed/refractory extensive-stage small cell lung cancer (ES-SCLC), designed to balance safety against enrollability while considering the risks of cytokine release syndrome (CRS) and immune effector cell-associated neurotoxicity syndrome (ICANS).

Inclusion Criteria:

  1. Histologically or cytologically confirmed diagnosis of extensive-stage SCLC.
  2. Documented relapsed or refractory disease after at least one prior platinum-based regimen (exact line of therapy will be defined per protocol).
  3. Presence of measurable disease as per RECIST v1.1 criteria.
  4. ECOG performance status of 0 or 1.
  5. Adequate organ function as determined by the following lab thresholds:
    - Hematologic: ANC ≥ 1,000 cells/mm³, Platelets ≥ 75,000 cells/mm³, Hemoglobin ≥ 9 g/dL.
    - Hepatic: Bilirubin ≤ 1.5 times the upper limit of normal (ULN), AST/ALT ≤ 2.5 times ULN (or ≤ 5 times ULN in presence of liver metastases), Albumin ≥ 3 g/dL.
    - Renal: Creatinine clearance (CrCl) ≥ 30 mL/min or serum creatinine ≤ 1.5 times ULN.
  6. Life expectancy of at least 12 weeks.

Exclusion Criteria:

  1. Presence of untreated, active, or symptomatic CNS metastases. Patients who have received treatment for CNS metastases and are stable may be considered for inclusion.
  2. Diagnosis of leptomeningeal disease or carcinomatous meningitis.
  3. Active autoimmune disease or any condition requiring systemic immunosuppression that would interfere with the study treatment.
  4. Insufficient washout time from prior anticancer therapy (i.e., approximately 3-4 weeks or 5 half-lives, depending on the agent).
  5. Uncontrolled intercurrent illness or active infection.
  6. Presence of a second malignancy that requires active treatment.
  7. Any active CNS disease or condition (seizure disorders, active CNS autoimmune conditions) that may heighten the risk of ICANS.
  8. Insufficient cardiac reserve, including recent myocardial infarction or NYHA III/IV congestive heart failure, as CRS may induce hemodynamic stress.
  9. Significant baseline hypoxia or poor pulmonary reserve.

Notes:

This criteria set aims to optimize participant safety while maintaining the feasibility of enrollment for advancing the research into DLL3 T-cell engagers in extensive-stage SCLC.

Final output

Here's the proposed inclusion/exclusion criteria for a Phase 1 first-in-human trial of a DLL3 T-cell engager (BiTE) in patients with relapsed/refractory extensive-stage small cell lung cancer (ES-SCLC), designed to balance safety against enrollability while considering the risks of cytokine release syndrome (CRS) and immune effector cell-associated neurotoxicity syndrome (ICANS).

Inclusion Criteria:

  1. Histologically or cytologically confirmed diagnosis of extensive-stage SCLC.
  2. Documented relapsed or refractory disease after at least one prior platinum-based regimen (exact line of therapy will be defined per protocol).
  3. Presence of measurable disease as per RECIST v1.1 criteria.
  4. ECOG performance status of 0 or 1.
  5. Adequate organ function as determined by the following lab thresholds:
    - Hematologic: ANC ≥ 1,000 cells/mm³, Platelets ≥ 75,000 cells/mm³, Hemoglobin ≥ 9 g/dL.
    - Hepatic: Bilirubin ≤ 1.5 times the upper limit of normal (ULN), AST/ALT ≤ 2.5 times ULN (or ≤ 5 times ULN in presence of liver metastases), Albumin ≥ 3 g/dL.
    - Renal: Creatinine clearance (CrCl) ≥ 30 mL/min or serum creatinine ≤ 1.5 times ULN.
  6. Life expectancy of at least 12 weeks.

Exclusion Criteria:

  1. Presence of untreated, active, or symptomatic CNS metastases. Patients who have received treatment for CNS metastases and are stable may be considered for inclusion.
  2. Diagnosis of leptomeningeal disease or carcinomatous meningitis.
  3. Active autoimmune disease or any condition requiring systemic immunosuppression that would interfere with the study treatment.
  4. Insufficient washout time from prior anticancer therapy (i.e., approximately 3-4 weeks or 5 half-lives, depending on the agent).
  5. Uncontrolled intercurrent illness or active infection.
  6. Presence of a second malignancy that requires active treatment.
  7. Any active CNS disease or condition (seizure disorders, active CNS autoimmune conditions) that may heighten the risk of ICANS.
  8. Insufficient cardiac reserve, including recent myocardial infarction or NYHA III/IV congestive heart failure, as CRS may induce hemodynamic stress.
  9. Significant baseline hypoxia or poor pulmonary reserve.

Notes:

This criteria set aims to optimize participant safety while maintaining the feasibility of enrollment for advancing the research into DLL3 T-cell engagers in extensive-stage SCLC.

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