← Eligibility-Criteria Authoring
Clinical / Medical · Medical monitor

Eligibility-Criteria Authoring — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T09:11:57.556894+00:00 · 3 tool calls · 38.5s · 7883 tokens
run id: eligibility_authoring_20260606_021119_01_author-the-inclusion-exclusion-criteria-for-a-ph

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 pull the relevant safety profile, precedent criteria, and lab thresholds to ground this in evidence.

⚙ 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: DLL3 T-Cell Engager (BiTE) in R/R ES-SCLC

Inclusion / Exclusion Criteria

Authored for a dose-escalation FIH study with mandatory step-up/priming dosing and cycle-1 inpatient CRS/ICANS observation. Design intent flagged where criteria deliberately trade enrollability against the CRS/neurotoxicity profile of the class.


INCLUSION CRITERIA

Disease
1. Histologically or cytologically confirmed extensive-stage small cell lung cancer (ES-SCLC).
2. Relapsed or refractory disease after ≥1 prior line of platinum-based chemotherapy. (Note: a prior anti-PD-(L)1, e.g., per IMpower133, is expected in most patients and is permitted; for FIH, do not over-restrict prior lines — keeping ≥1 rather than mandating a specific number preserves enrollability in a heavily pretreated population.)
3. At least one measurable lesion per RECIST v1.1.
4. (Optional biomarker enrichment) Archival or fresh tumor available for DLL3 expression assessment. For a FIH escalation, recommend collecting DLL3 status for correlative analysis but not gating enrollment on it until a threshold is defined — gating prematurely shrinks the pool without validated cutoff.

Performance & reserve
5. ECOG performance status 0–1.
6. Life expectancy ≥12 weeks.

Organ function (within ~7 days of first dose; no growth-factor/transfusion support within 14 days for hematologic values)
7. ANC ≥ 1.5 × 10⁹/L.
8. Platelets ≥ 100 × 10⁹/L.
9. Hemoglobin ≥ 9.0 g/dL, transfusion-independent.
10. Total bilirubin ≤ 1.5 × ULN (≤ 3 × ULN if documented Gilbert's or hepatic metastases).
11. AST/ALT ≤ 3 × ULN (≤ 5 × ULN if hepatic metastases).
12. Creatinine clearance ≥ 50 mL/min (Cockcroft-Gault).

Class-specific safety baselines (CRS/ICANS-driven)
13. Adequate cardiac reserve to tolerate CRS hemodynamic stress: LVEF ≥ 50% by ECHO/MUGA and no clinically significant cardiac disease (see exclusions).
14. Adequate pulmonary reserve: baseline O₂ saturation ≥ 92% on room air. (CRS can precipitate hypoxia; poor baseline pulmonary function compounds danger — relevant given SCLC's smoking-related comorbidity burden.)
15. Baseline normal neurologic exam with documented ICE (Immune effector Cell-associated Encephalopathy) score — establishes the reference point for ICANS grading.

General
16. Adequate washout from prior anticancer therapy: ≥3 weeks or 5 half-lives (whichever shorter) before first dose; recovery of prior toxicities to ≤ Grade 1 (excluding alopecia, stable neuropathy).
17. Age ≥18, able to comply with inpatient cycle-1 monitoring, and provide written informed consent.


EXCLUSION CRITERIA

CNS — central to ICANS risk mitigation
1. Active, untreated, or symptomatic CNS metastases. Treated and stable brain metastases are permitted if: completed local therapy ≥2–4 weeks prior, off therapeutic-dose corticosteroids (≤10 mg/day prednisone-equivalent), and radiographically stable. (This precedent-based allowance — used in DLL3 TCE programs — is the single biggest enrollability lever, since untreated CNS disease is common in SCLC; only active CNS disease is excluded because of ICANS overlap.)
2. Leptomeningeal disease / carcinomatous meningitis.
3. History of seizure disorder, or active autoimmune/inflammatory CNS disease — confounds and amplifies ICANS.

Cardiac/pulmonary — CRS tolerability
4. Recent myocardial infarction (≤6 months), unstable angina, NYHA Class III/IV heart failure, or other clinically significant uncontrolled cardiac disease.
5. Clinically significant baseline hypoxia or poor pulmonary reserve beyond inclusion #14 threshold.
6. QTc(F) > 470 ms (women) / > 450 ms (men), or congenital long-QT syndrome.

Immune/infectious — CRS confounding & on-target risk
7. Active autoimmune disease or condition requiring chronic systemic immunosuppression / high-dose corticosteroids. (Steroids blunt TCE efficacy and confound CRS grading.)
8. Active uncontrolled infection — CRS can mask or worsen sepsis; pyrexia overlaps with CRS presentation.
9. Known HIV with uncontrolled disease, or active HBV/HCV (controlled/treated viral disease may be permitted per protocol).
10. Live vaccine within 4 weeks of first dose.
11. Pre-existing hypogammaglobulinemia of clinical significance / history of recurrent serious infection (given on-target hypogammaglobulinemia and infection signal — consider monitoring rather than hard exclusion to protect enrollability).

General
12. Insufficient washout (see inclusion #16) or unresolved prior-therapy toxicity > Grade 1.
13. Second malignancy requiring active systemic treatment.
14. Pregnancy/lactation; refusal of effective contraception.
15. Any condition that, in the investigator's judgment, precludes safe completion of mandated cycle-1 inpatient monitoring.


Design Notes — Safety/Enrollability Balance

Lever Decision Rationale
Brain mets Exclude only active; allow treated/stable Largest enrollability gain; ICANS risk concentrated in active CNS disease
Prior lines ≥1 platinum line, no upper cap Heavily pretreated SCLC population; over-restricting starves the trial
DLL3 expression Collect, don't gate (FIH) No validated cutoff yet; gate later if escalation data warrant
Cardiac/pulmonary LVEF ≥50%, SpO₂ ≥92% Floor for CRS hemodynamic/hypoxic stress without excluding typical SCLC comorbidity
Hypogammaglobulinemia Monitor preferentially over exclude Manageable with Ig replacement; hard exclusion would over-cull

Protocol-level safeguards (not eligibility, but required by the class): step-up/priming dose schedule; cycle-1 inpatient observation through the CRS window; tocilizumab and corticosteroids on-site as mandated rescue; serial ferritin/CRP/vitals trending; baseline + scheduled ICE-score neuro assessments.

⚠️ These are precedent-grounded teaching-level criteria. Exact thresholds, washout windows, viral-disease handling, and any DLL3 cutoff must be finalized against the Investigator's Brochure, the specific molecule's PK/half-life, and regulatory/IRB input.

Want me to draft the corresponding CRS/ICANS grading-and-management appendix or the dose-limiting toxicity (DLT) definitions for the escalation cohorts next?

Final output

Phase 1 First-in-Human Trial: DLL3 T-Cell Engager (BiTE) in R/R ES-SCLC

Inclusion / Exclusion Criteria

Authored for a dose-escalation FIH study with mandatory step-up/priming dosing and cycle-1 inpatient CRS/ICANS observation. Design intent flagged where criteria deliberately trade enrollability against the CRS/neurotoxicity profile of the class.


INCLUSION CRITERIA

Disease
1. Histologically or cytologically confirmed extensive-stage small cell lung cancer (ES-SCLC).
2. Relapsed or refractory disease after ≥1 prior line of platinum-based chemotherapy. (Note: a prior anti-PD-(L)1, e.g., per IMpower133, is expected in most patients and is permitted; for FIH, do not over-restrict prior lines — keeping ≥1 rather than mandating a specific number preserves enrollability in a heavily pretreated population.)
3. At least one measurable lesion per RECIST v1.1.
4. (Optional biomarker enrichment) Archival or fresh tumor available for DLL3 expression assessment. For a FIH escalation, recommend collecting DLL3 status for correlative analysis but not gating enrollment on it until a threshold is defined — gating prematurely shrinks the pool without validated cutoff.

Performance & reserve
5. ECOG performance status 0–1.
6. Life expectancy ≥12 weeks.

Organ function (within ~7 days of first dose; no growth-factor/transfusion support within 14 days for hematologic values)
7. ANC ≥ 1.5 × 10⁹/L.
8. Platelets ≥ 100 × 10⁹/L.
9. Hemoglobin ≥ 9.0 g/dL, transfusion-independent.
10. Total bilirubin ≤ 1.5 × ULN (≤ 3 × ULN if documented Gilbert's or hepatic metastases).
11. AST/ALT ≤ 3 × ULN (≤ 5 × ULN if hepatic metastases).
12. Creatinine clearance ≥ 50 mL/min (Cockcroft-Gault).

Class-specific safety baselines (CRS/ICANS-driven)
13. Adequate cardiac reserve to tolerate CRS hemodynamic stress: LVEF ≥ 50% by ECHO/MUGA and no clinically significant cardiac disease (see exclusions).
14. Adequate pulmonary reserve: baseline O₂ saturation ≥ 92% on room air. (CRS can precipitate hypoxia; poor baseline pulmonary function compounds danger — relevant given SCLC's smoking-related comorbidity burden.)
15. Baseline normal neurologic exam with documented ICE (Immune effector Cell-associated Encephalopathy) score — establishes the reference point for ICANS grading.

General
16. Adequate washout from prior anticancer therapy: ≥3 weeks or 5 half-lives (whichever shorter) before first dose; recovery of prior toxicities to ≤ Grade 1 (excluding alopecia, stable neuropathy).
17. Age ≥18, able to comply with inpatient cycle-1 monitoring, and provide written informed consent.


EXCLUSION CRITERIA

CNS — central to ICANS risk mitigation
1. Active, untreated, or symptomatic CNS metastases. Treated and stable brain metastases are permitted if: completed local therapy ≥2–4 weeks prior, off therapeutic-dose corticosteroids (≤10 mg/day prednisone-equivalent), and radiographically stable. (This precedent-based allowance — used in DLL3 TCE programs — is the single biggest enrollability lever, since untreated CNS disease is common in SCLC; only active CNS disease is excluded because of ICANS overlap.)
2. Leptomeningeal disease / carcinomatous meningitis.
3. History of seizure disorder, or active autoimmune/inflammatory CNS disease — confounds and amplifies ICANS.

Cardiac/pulmonary — CRS tolerability
4. Recent myocardial infarction (≤6 months), unstable angina, NYHA Class III/IV heart failure, or other clinically significant uncontrolled cardiac disease.
5. Clinically significant baseline hypoxia or poor pulmonary reserve beyond inclusion #14 threshold.
6. QTc(F) > 470 ms (women) / > 450 ms (men), or congenital long-QT syndrome.

Immune/infectious — CRS confounding & on-target risk
7. Active autoimmune disease or condition requiring chronic systemic immunosuppression / high-dose corticosteroids. (Steroids blunt TCE efficacy and confound CRS grading.)
8. Active uncontrolled infection — CRS can mask or worsen sepsis; pyrexia overlaps with CRS presentation.
9. Known HIV with uncontrolled disease, or active HBV/HCV (controlled/treated viral disease may be permitted per protocol).
10. Live vaccine within 4 weeks of first dose.
11. Pre-existing hypogammaglobulinemia of clinical significance / history of recurrent serious infection (given on-target hypogammaglobulinemia and infection signal — consider monitoring rather than hard exclusion to protect enrollability).

General
12. Insufficient washout (see inclusion #16) or unresolved prior-therapy toxicity > Grade 1.
13. Second malignancy requiring active systemic treatment.
14. Pregnancy/lactation; refusal of effective contraception.
15. Any condition that, in the investigator's judgment, precludes safe completion of mandated cycle-1 inpatient monitoring.


Design Notes — Safety/Enrollability Balance

Lever Decision Rationale
Brain mets Exclude only active; allow treated/stable Largest enrollability gain; ICANS risk concentrated in active CNS disease
Prior lines ≥1 platinum line, no upper cap Heavily pretreated SCLC population; over-restricting starves the trial
DLL3 expression Collect, don't gate (FIH) No validated cutoff yet; gate later if escalation data warrant
Cardiac/pulmonary LVEF ≥50%, SpO₂ ≥92% Floor for CRS hemodynamic/hypoxic stress without excluding typical SCLC comorbidity
Hypogammaglobulinemia Monitor preferentially over exclude Manageable with Ig replacement; hard exclusion would over-cull

Protocol-level safeguards (not eligibility, but required by the class): step-up/priming dose schedule; cycle-1 inpatient observation through the CRS window; tocilizumab and corticosteroids on-site as mandated rescue; serial ferritin/CRP/vitals trending; baseline + scheduled ICE-score neuro assessments.

⚠️ These are precedent-grounded teaching-level criteria. Exact thresholds, washout windows, viral-disease handling, and any DLL3 cutoff must be finalized against the Investigator's Brochure, the specific molecule's PK/half-life, and regulatory/IRB input.

Want me to draft the corresponding CRS/ICANS grading-and-management appendix or the dose-limiting toxicity (DLT) definitions for the escalation cohorts next?

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