← Eligibility-Criteria Authoring comparison · model: Claude Haiku 4.5
LLM-judge score: 4.4 / 5 · strong
safety_exclusions: 5 lab_thresholds: 5 enrollability: 4 precedent_completeness: 5 faithfulness_clarity: 3
The I/E list comprehensively protects against every DLL3 BiTE class liability — CRS (cardiac/pulmonary reserve, active infection, inpatient monitoring), ICANS (CNS mets/seizure/leptomeningeal exclusions, ICE scoring), cytopenias (specific ANC/platelet/Hgb cutoffs), and infection/hypogammaglobulinemia (HIV/HBV/HCV screening) — with clinically plausible, operational thresholds. Enrollability is reasonably balanced via relaxed cutoffs for marrow/liver mets and a treated-stable-brain-mets exception, though tumor flare/pyrexia is only indirectly addressed. The agent claims to 'gather reference information' but no tool outputs are evident, so criteria appear drawn from memory rather than visibly grounded in pulled precedent data, slightly weakening faithfulness despite clinically accurate content.
Clinical / Medical · Medical monitor

Eligibility-Criteria Authoring — agent trajectory for expert review

claude-haiku-4-5-20251001 · 2026-06-06T10:25:11.051542+00:00 · 3 tool calls · 27.2s · 7165 tokens
run id: eligibility_authoring_20260606_031816_eligibility-authoring__claude-haiku-4-5

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

I'll gather the necessary reference information to author comprehensive inclusion/exclusion criteria for this Phase 1 trial.

⚙ 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

Phase 1 First-in-Human Trial of DLL3 T-Cell Engager (BiTE) in Relapsed/Refractory ES-SCLC

Inclusion/Exclusion Criteria


INCLUSION CRITERIA

Disease & Prior Treatment

  1. Histologically or cytologically confirmed extensive-stage small cell lung cancer (ES-SCLC).
  2. Relapsed or refractory disease after ≥1 prior platinum-based chemotherapy regimen (platinum-etoposide or equivalent).
  3. Measurable disease per RECIST v1.1 (≥10 mm in short axis on CT/MRI).
  4. Time since last prior chemotherapy ≥3 weeks (or ≥5 half-lives of the agent, whichever is longer) to allow washout and recovery.

Performance & Life Expectancy

  1. ECOG performance status 0 or 1.
  2. Estimated life expectancy ≥12 weeks.

Organ Function

  1. Hematologic:
    - Absolute neutrophil count (ANC) ≥1.5 × 10⁹/L
    - Platelets ≥100 × 10⁹/L (≥75 × 10⁹/L if marrow involvement by tumor)
    - Hemoglobin ≥9.0 g/dL, transfusion-independent for ≥1 week prior to enrollment

  2. Hepatic:
    - Total bilirubin ≤1.5 × ULN (≤3 × ULN if documented Gilbert's syndrome or hepatic metastases)
    - AST/ALT ≤3 × ULN (≤5 × ULN if liver metastases present)
    - Albumin ≥2.8 g/dL

  3. Renal:
    - Creatinine clearance (Cockcroft-Gault) ≥50 mL/min or serum creatinine ≤1.5 × ULN

  4. Cardiac:

    • Left ventricular ejection fraction (LVEF) ≥50% by ECHO or MUGA (required because CRS imposes hemodynamic stress)
    • QTc (Fridericia) ≤470 ms (women) or ≤450 ms (men)
    • No history of congenital long-QT syndrome

Informed Consent & Special Populations

  1. Signed informed consent; willingness to comply with intensive cycle-1 inpatient monitoring and frequent follow-up.
  2. If of childbearing potential: agreement to highly effective contraception during treatment and ≥3 months after final dose (T-cell engagers carry unknown teratogenic risk; adopt precautionary standard).

EXCLUSION CRITERIA

Central Nervous System & Neurotoxicity Risk

  1. Active, untreated, or symptomatic CNS metastases or leptomeningeal disease.
    - Rationale: ICANS risk is amplified in the presence of active brain disease; step-up dosing and neuro monitoring alone may be insufficient.
    - Exception: Patients with treated and radiographically stable CNS metastases (no progression for ≥4 weeks off CNS-directed therapy) may be enrolled only with mandatory baseline/on-treatment ICE (Immune Effector Cell-Associated Encephalopathy) scoring, frequent neuro exam, and MRI monitoring.

  2. Active seizure disorder or uncontrolled epilepsy; ongoing antiepileptic medication is a relative risk factor for ICANS and complicates CRS monitoring.

  3. History of stroke, intracranial hemorrhage, or posterior reversible encephalopathy syndrome (PRES) within 12 months.

  4. Known or suspected carcinomatous meningitis.

Autoimmune & Immunosuppression

  1. Active autoimmune disease requiring systemic corticosteroids (>10 mg/day prednisone equivalent) or other immunosuppressive therapy at enrollment.
    - Rationale: Baseline immunosuppression blunts T-cell engager efficacy and confounds CRS grading/management; excludes patients requiring chronic high-dose steroids.
    - Exception: Autoimmune thyroiditis, vitiligo, psoriasis, or other stable, mild conditions managed with topical/low-dose therapy are permitted.

  2. History of severe allergic reaction or hypersensitivity to biologic agents or monoclonal antibodies.

Cardiac & Hemodynamic Reserve

  1. Uncontrolled or poorly compensated heart failure (NYHA Class III or IV).
  2. Recent myocardial infarction, unstable angina, or significant coronary artery disease within 6 months.
  3. Uncontrolled hypertension (systolic >160 mmHg or diastolic >100 mmHg) despite antihypertensive therapy.
    - Rationale: CRS causes significant hemodynamic stress (tachycardia, hypertension, capillary leak); inadequate baseline reserve increases severe CRS and organ injury risk.

Infection & Hematologic Reserve

  1. Active, uncontrolled infection (bacterial, viral, or fungal) at enrollment.

    • Rationale: CRS and fever can mask or exacerbate active infection; T-cell engagers carry hypogammaglobulinemia risk, reducing infection control.
    • Note: Patients may be enrolled once infection is treated and documented resolved.
  2. Known history of HIV, chronic hepatitis B (HBsAg+), or hepatitis C infection (HCV RNA+).

    • Rationale: Immunocompromise and risk of reactivation/fulminant hepatitis during T-cell activation.
  3. Inadequate marrow reserve: prior allogeneic hematopoietic stem cell transplant (HSCT) within 2 years or history of Grade 4 hematologic toxicity from prior therapy that has not fully recovered.

Pulmonary & Respiratory Reserve

  1. Baseline hypoxia (O₂ saturation <92% on room air) or severe underlying pulmonary disease (FEV₁ <35% predicted, pulmonary fibrosis, or uncontrolled pulmonary hypertension).
    • Rationale: SCLC often causes airway obstruction; CRS-associated capillary leak worsens respiratory compromise. Poor baseline reserve precludes safe management of CRS-related hypoxia.

Concomitant Medications & Immunotherapy

  1. Live or attenuated vaccines within 4 weeks prior to or anticipated during study participation.

    • Rationale: Viral reactivation and vaccine-strain illness in the context of T-cell activation and potential hypogammaglobulinemia.
  2. Chronic systemic corticosteroids at doses >10 mg/day prednisone equivalent (short-term steroids for symptom management or CRS rescue permitted).

  3. Concurrent immunotherapy (checkpoint inhibitors, CAR-T, other TCEs) or investigational agents within 4 weeks (or 5 half-lives, whichever is longer).

    • Rationale: Phase 1 first-in-human requires clean CRS/ICANS attribution; overlapping immune activation is unmanageable in safety assessment.

Prior Therapies & Washout

  1. Prior exposure to a DLL3-targeted agent (DLL3 antibody, ADC, or T-cell engager).

    • Rationale: No clinical precedent for re-challenge; unknown immunogenicity.
  2. Chemotherapy, targeted therapy, or antibody therapy within 3 weeks of first dose (5 half-lives if agent has longer half-life).

  3. Radiation therapy ≥25% bone marrow within 4 weeks of enrollment.

  4. Prior malignancy within 3 years, except adequately treated non-melanoma skin cancer, in situ cervical cancer, or other non-SCLC malignancy treated without ongoing systemic therapy.

Other Contraindications

  1. Pregnancy or nursing (teratogenicity of T-cell engagers not yet characterized; adopt precautionary exclusion).

  2. Psychiatric or addictive disorders, or other conditions that, in the investigator's judgment, would impair the patient's ability to comply with study procedures or assess toxicity reliably.

  3. Insufficient vascular access for frequent blood draws and inpatient infusion management during CRS monitoring window (intravenous catheter required).


RATIONALE SUMMARY & ENROLLMENT BALANCE

Domain Criterion Logic Enrollment Impact
CRS/ICANS Mitigation Exclude active CNS disease, seizure, autoimmune CNS; mandate cardiac function & baseline neuro exam. Moderate (excludes ~10–15% of R/R ES-SCLC population with brain mets).
Cardiac & Hemodynamic LVEF ≥50%, no recent MI, controlled HTN. Moderate (excludes ~5–10% with cardiac comorbidity).
Hematologic Reserve ANC ≥1.5, Plt ≥100 (lower thresholds if marrow involved). Minimal (SCLC rarely extensively marrow-involved; ~3–5% excluded).
Hepatic & Renal Standard oncology cutoffs; relaxed for liver mets. Minimal (~2–5% excluded due to organ dysfunction).
Infection Control Active infection exclusion; HIV/HBV/HCV exclusion. Minimal (~3–5% excluded).
Pulmonary Reserve Baseline O₂ sat ≥92%, FEV₁ ≥35%. Moderate (~5–10% excluded; relevant for lung cancer).
Washout & Prior Therapy 3-week washout; ≥1 prior line; no prior DLL3 agents. Minimal (standard R/R eligibility filters ~5–10%).

Balancing Notes:
- Relaxation rationale: Allowing treated/stable CNS metastases (common in R/R SCLC with ~50% prevalence) after confirmation of radiographic stability preserves enrollability without materially increasing ICANS risk if neuro monitoring is rigorous.
- Tightness rationale: Cardiac function and baseline pulmonary reserve are mandated because CRS in an ES-SCLC cohort with compromised cardiopulmonary status risks rapid decompensation; these are non-negotiable for a first-in-human trial.
- Immunosuppression: Excluding chronic systemic steroids but permitting acute rescue steroids/tocilizumab balances CRS safety (early intervention) against clinical pragmatism.
- Estimated Cohort Enrollment: Approximately 70–80% of fit R/R ES-SCLC patients will meet criteria, supporting Phase 1 cohort assembly (typically 20–40 patients over escalation).


This framework grounds criteria in DLL3 T-cell engager and ES-SCLC precedent (tarlatamab trials), prioritizes ICANS/CRS risk, and maintains enrollability for first-in-human execution.

Final output

Phase 1 First-in-Human Trial of DLL3 T-Cell Engager (BiTE) in Relapsed/Refractory ES-SCLC

Inclusion/Exclusion Criteria


INCLUSION CRITERIA

Disease & Prior Treatment

  1. Histologically or cytologically confirmed extensive-stage small cell lung cancer (ES-SCLC).
  2. Relapsed or refractory disease after ≥1 prior platinum-based chemotherapy regimen (platinum-etoposide or equivalent).
  3. Measurable disease per RECIST v1.1 (≥10 mm in short axis on CT/MRI).
  4. Time since last prior chemotherapy ≥3 weeks (or ≥5 half-lives of the agent, whichever is longer) to allow washout and recovery.

Performance & Life Expectancy

  1. ECOG performance status 0 or 1.
  2. Estimated life expectancy ≥12 weeks.

Organ Function

  1. Hematologic:
    - Absolute neutrophil count (ANC) ≥1.5 × 10⁹/L
    - Platelets ≥100 × 10⁹/L (≥75 × 10⁹/L if marrow involvement by tumor)
    - Hemoglobin ≥9.0 g/dL, transfusion-independent for ≥1 week prior to enrollment

  2. Hepatic:
    - Total bilirubin ≤1.5 × ULN (≤3 × ULN if documented Gilbert's syndrome or hepatic metastases)
    - AST/ALT ≤3 × ULN (≤5 × ULN if liver metastases present)
    - Albumin ≥2.8 g/dL

  3. Renal:
    - Creatinine clearance (Cockcroft-Gault) ≥50 mL/min or serum creatinine ≤1.5 × ULN

  4. Cardiac:

    • Left ventricular ejection fraction (LVEF) ≥50% by ECHO or MUGA (required because CRS imposes hemodynamic stress)
    • QTc (Fridericia) ≤470 ms (women) or ≤450 ms (men)
    • No history of congenital long-QT syndrome

Informed Consent & Special Populations

  1. Signed informed consent; willingness to comply with intensive cycle-1 inpatient monitoring and frequent follow-up.
  2. If of childbearing potential: agreement to highly effective contraception during treatment and ≥3 months after final dose (T-cell engagers carry unknown teratogenic risk; adopt precautionary standard).

EXCLUSION CRITERIA

Central Nervous System & Neurotoxicity Risk

  1. Active, untreated, or symptomatic CNS metastases or leptomeningeal disease.
    - Rationale: ICANS risk is amplified in the presence of active brain disease; step-up dosing and neuro monitoring alone may be insufficient.
    - Exception: Patients with treated and radiographically stable CNS metastases (no progression for ≥4 weeks off CNS-directed therapy) may be enrolled only with mandatory baseline/on-treatment ICE (Immune Effector Cell-Associated Encephalopathy) scoring, frequent neuro exam, and MRI monitoring.

  2. Active seizure disorder or uncontrolled epilepsy; ongoing antiepileptic medication is a relative risk factor for ICANS and complicates CRS monitoring.

  3. History of stroke, intracranial hemorrhage, or posterior reversible encephalopathy syndrome (PRES) within 12 months.

  4. Known or suspected carcinomatous meningitis.

Autoimmune & Immunosuppression

  1. Active autoimmune disease requiring systemic corticosteroids (>10 mg/day prednisone equivalent) or other immunosuppressive therapy at enrollment.
    - Rationale: Baseline immunosuppression blunts T-cell engager efficacy and confounds CRS grading/management; excludes patients requiring chronic high-dose steroids.
    - Exception: Autoimmune thyroiditis, vitiligo, psoriasis, or other stable, mild conditions managed with topical/low-dose therapy are permitted.

  2. History of severe allergic reaction or hypersensitivity to biologic agents or monoclonal antibodies.

Cardiac & Hemodynamic Reserve

  1. Uncontrolled or poorly compensated heart failure (NYHA Class III or IV).
  2. Recent myocardial infarction, unstable angina, or significant coronary artery disease within 6 months.
  3. Uncontrolled hypertension (systolic >160 mmHg or diastolic >100 mmHg) despite antihypertensive therapy.
    - Rationale: CRS causes significant hemodynamic stress (tachycardia, hypertension, capillary leak); inadequate baseline reserve increases severe CRS and organ injury risk.

Infection & Hematologic Reserve

  1. Active, uncontrolled infection (bacterial, viral, or fungal) at enrollment.

    • Rationale: CRS and fever can mask or exacerbate active infection; T-cell engagers carry hypogammaglobulinemia risk, reducing infection control.
    • Note: Patients may be enrolled once infection is treated and documented resolved.
  2. Known history of HIV, chronic hepatitis B (HBsAg+), or hepatitis C infection (HCV RNA+).

    • Rationale: Immunocompromise and risk of reactivation/fulminant hepatitis during T-cell activation.
  3. Inadequate marrow reserve: prior allogeneic hematopoietic stem cell transplant (HSCT) within 2 years or history of Grade 4 hematologic toxicity from prior therapy that has not fully recovered.

Pulmonary & Respiratory Reserve

  1. Baseline hypoxia (O₂ saturation <92% on room air) or severe underlying pulmonary disease (FEV₁ <35% predicted, pulmonary fibrosis, or uncontrolled pulmonary hypertension).
    • Rationale: SCLC often causes airway obstruction; CRS-associated capillary leak worsens respiratory compromise. Poor baseline reserve precludes safe management of CRS-related hypoxia.

Concomitant Medications & Immunotherapy

  1. Live or attenuated vaccines within 4 weeks prior to or anticipated during study participation.

    • Rationale: Viral reactivation and vaccine-strain illness in the context of T-cell activation and potential hypogammaglobulinemia.
  2. Chronic systemic corticosteroids at doses >10 mg/day prednisone equivalent (short-term steroids for symptom management or CRS rescue permitted).

  3. Concurrent immunotherapy (checkpoint inhibitors, CAR-T, other TCEs) or investigational agents within 4 weeks (or 5 half-lives, whichever is longer).

    • Rationale: Phase 1 first-in-human requires clean CRS/ICANS attribution; overlapping immune activation is unmanageable in safety assessment.

Prior Therapies & Washout

  1. Prior exposure to a DLL3-targeted agent (DLL3 antibody, ADC, or T-cell engager).

    • Rationale: No clinical precedent for re-challenge; unknown immunogenicity.
  2. Chemotherapy, targeted therapy, or antibody therapy within 3 weeks of first dose (5 half-lives if agent has longer half-life).

  3. Radiation therapy ≥25% bone marrow within 4 weeks of enrollment.

  4. Prior malignancy within 3 years, except adequately treated non-melanoma skin cancer, in situ cervical cancer, or other non-SCLC malignancy treated without ongoing systemic therapy.

Other Contraindications

  1. Pregnancy or nursing (teratogenicity of T-cell engagers not yet characterized; adopt precautionary exclusion).

  2. Psychiatric or addictive disorders, or other conditions that, in the investigator's judgment, would impair the patient's ability to comply with study procedures or assess toxicity reliably.

  3. Insufficient vascular access for frequent blood draws and inpatient infusion management during CRS monitoring window (intravenous catheter required).


RATIONALE SUMMARY & ENROLLMENT BALANCE

Domain Criterion Logic Enrollment Impact
CRS/ICANS Mitigation Exclude active CNS disease, seizure, autoimmune CNS; mandate cardiac function & baseline neuro exam. Moderate (excludes ~10–15% of R/R ES-SCLC population with brain mets).
Cardiac & Hemodynamic LVEF ≥50%, no recent MI, controlled HTN. Moderate (excludes ~5–10% with cardiac comorbidity).
Hematologic Reserve ANC ≥1.5, Plt ≥100 (lower thresholds if marrow involved). Minimal (SCLC rarely extensively marrow-involved; ~3–5% excluded).
Hepatic & Renal Standard oncology cutoffs; relaxed for liver mets. Minimal (~2–5% excluded due to organ dysfunction).
Infection Control Active infection exclusion; HIV/HBV/HCV exclusion. Minimal (~3–5% excluded).
Pulmonary Reserve Baseline O₂ sat ≥92%, FEV₁ ≥35%. Moderate (~5–10% excluded; relevant for lung cancer).
Washout & Prior Therapy 3-week washout; ≥1 prior line; no prior DLL3 agents. Minimal (standard R/R eligibility filters ~5–10%).

Balancing Notes:
- Relaxation rationale: Allowing treated/stable CNS metastases (common in R/R SCLC with ~50% prevalence) after confirmation of radiographic stability preserves enrollability without materially increasing ICANS risk if neuro monitoring is rigorous.
- Tightness rationale: Cardiac function and baseline pulmonary reserve are mandated because CRS in an ES-SCLC cohort with compromised cardiopulmonary status risks rapid decompensation; these are non-negotiable for a first-in-human trial.
- Immunosuppression: Excluding chronic systemic steroids but permitting acute rescue steroids/tocilizumab balances CRS safety (early intervention) against clinical pragmatism.
- Estimated Cohort Enrollment: Approximately 70–80% of fit R/R ES-SCLC patients will meet criteria, supporting Phase 1 cohort assembly (typically 20–40 patients over escalation).


This framework grounds criteria in DLL3 T-cell engager and ES-SCLC precedent (tarlatamab trials), prioritizes ICANS/CRS risk, and maintains enrollability for first-in-human execution.

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