BioGrade · expert reasoning data for biopharma agentsEnvironmentsBenchmarkCompare modelsData flywheelThesis
← Epidemiology-Based Market Sizing
Commercial / Forecasting · Commercial forecasting analyst

Epidemiology-Based Market Sizing — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T09:07:13.727303+00:00 · 4 tool calls · 20.3s · 6443 tokens
run id: market_sizing_20260606_020653_01_size-the-us-addressable-patient-population-and-r

Query

Size the US addressable patient population and rough peak revenue for a DLL3 T-cell engager (tarlatamab-like) in second-line extensive-stage small cell lung cancer.

Trajectory

Agent · turn 1

I'll size this DLL3 T-cell engager opportunity in 2L ES-SCLC. Let me start by understanding the dataset and pulling the relevant data.

⚙ calls list_indications()
↳ list_indications result
show data
{
  "disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
  "indications": {
    "NSCLC": {
      "label": "Non-small cell lung cancer (EGFR-mutant subset of interest)",
      "geographies": [
        "US",
        "EU5"
      ],
      "funnel_basis": "incidence"
    },
    "HER2+ Breast": {
      "label": "HER2-positive breast cancer",
      "geographies": [
        "US",
        "EU5"
      ],
      "funnel_basis": "incidence"
    },
    "ES-SCLC": {
      "label": "Extensive-stage small cell lung cancer",
      "geographies": [
        "US",
        "EU5"
      ],
      "funnel_basis": "incidence"
    },
    "Ulcerative Colitis": {
      "label": "Ulcerative colitis (moderate-to-severe)",
      "geographies": [
        "US",
        "EU5"
      ],
      "funnel_basis": "prevalence"
    },
    "ATTR-CM": {
      "label": "Transthyretin amyloid cardiomyopathy",
      "geographies": [
        "US",
        "EU5"
      ],
      "funnel_basis": "prevalence"
    }
  }
}
Agent · turn 2

ES-SCLC is available and is incidence-based. Let me pull all the relevant data for the US.

⚙ calls get_epidemiology(indication=ES-SCLC, geography=US)
⚙ calls get_subtype_prevalence(indication=ES-SCLC)
⚙ calls get_pricing(indication=ES-SCLC)
↳ get_epidemiology result
show data
{
  "disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
  "indication": "ES-SCLC",
  "label": "Extensive-stage small cell lung cancer",
  "funnel_basis": "incidence",
  "diagnosis_rate": 0.95,
  "treatment_rate": 0.85,
  "epidemiology": {
    "US": {
      "incidence_per_year": 33000,
      "prevalence": 38000
    }
  },
  "note": "funnel_basis tells you whether to start the funnel from incidence (new patients/year) or prevalence (point count of living patients)."
}
↳ get_subtype_prevalence result
show data
{
  "disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
  "indication": "ES-SCLC",
  "subtypes": {
    "extensive_stage_fraction": 0.7,
    "DLL3_expression_fraction": 0.85,
    "fit_for_2L_fraction": 0.55
  },
  "line_splits": {
    "1L": 0.95,
    "2L": 0.5,
    "3L+": 0.2
  },
  "notes": "SCLC is ~13% of lung cancer; counts here are SCLC totals. ~70% present extensive-stage. DLL3 is expressed in ~85% of SCLC. A DLL3 T-cell engager (e.g. tarlatamab) is used 2L+; gate ES-SCLC on DLL3 expression AND being fit for second-line therapy. Short treated duration reflects rapid progression and high mortality."
}
↳ get_pricing result
show data
{
  "disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
  "indication": "ES-SCLC",
  "annual_price": 220000,
  "treated_months": 8,
  "persistence": 0.55,
  "note": "annual_price is the list price for a full year. persistence is the fraction of a year actually paid for (discontinuation/mortality). Effective revenue per addressable patient/year = annual_price x persistence."
}
Agent · turn 3

I have everything needed. Let me build the funnel and revenue sketch.

Patient Funnel — DLL3 T-cell Engager in 2L ES-SCLC (US)

Step Factor Patients/year
SCLC incidence (US) 33,000 33,000
× Diagnosed 0.95 31,350
× Extensive-stage 0.70 21,945
× Treated 0.85 18,653
× Reach 2L (line split) 0.50 9,326
× DLL3-expressing 0.85 7,927
× Fit for 2L therapy 0.55 4,360

US addressable population ≈ 4,400 patients/year (2L ES-SCLC, DLL3+, fit).

A note on funnel logic: I started from incidence (correct for a fast-moving, high-mortality cancer where the annual flow of new patients is the right denominator), applied diagnosis and stage gating, then the treatment rate, then the 2L line split, and finally the two drug-specific gates (DLL3 expression AND fit-for-2L). I applied the 2L line split rather than stacking 1L → 2L, since the 0.50 represents the share of treated patients who actually progress to and receive second-line therapy.

Rough Peak Revenue

Effective revenue per addressable patient/year = annual price × persistence:
- $220,000 × 0.55 = $121,000/patient/year

This persistence factor (0.55 of a year) is consistent with the ~8-month treated duration, reflecting the rapid progression and high mortality in this setting.

Unadjusted peak (100% capture):
- 4,360 × $121,000 ≈ $528M

With a realistic peak market share (T-cell engagers face competition, REMS/cytokine-release management burden, and academic-center concentration — assume ~40–50% peak penetration):

Peak share Peak US revenue
30% ~$160M
40% ~$210M
50% ~$265M

Bottom line

Caveats

Would you like me to (a) extend this to 2L+ including 3L, (b) add EU5, or (c) run a sensitivity table on the fit/share assumptions?

Final output

I have everything needed. Let me build the funnel and revenue sketch.

Patient Funnel — DLL3 T-cell Engager in 2L ES-SCLC (US)

Step Factor Patients/year
SCLC incidence (US) 33,000 33,000
× Diagnosed 0.95 31,350
× Extensive-stage 0.70 21,945
× Treated 0.85 18,653
× Reach 2L (line split) 0.50 9,326
× DLL3-expressing 0.85 7,927
× Fit for 2L therapy 0.55 4,360

US addressable population ≈ 4,400 patients/year (2L ES-SCLC, DLL3+, fit).

A note on funnel logic: I started from incidence (correct for a fast-moving, high-mortality cancer where the annual flow of new patients is the right denominator), applied diagnosis and stage gating, then the treatment rate, then the 2L line split, and finally the two drug-specific gates (DLL3 expression AND fit-for-2L). I applied the 2L line split rather than stacking 1L → 2L, since the 0.50 represents the share of treated patients who actually progress to and receive second-line therapy.

Rough Peak Revenue

Effective revenue per addressable patient/year = annual price × persistence:
- $220,000 × 0.55 = $121,000/patient/year

This persistence factor (0.55 of a year) is consistent with the ~8-month treated duration, reflecting the rapid progression and high mortality in this setting.

Unadjusted peak (100% capture):
- 4,360 × $121,000 ≈ $528M

With a realistic peak market share (T-cell engagers face competition, REMS/cytokine-release management burden, and academic-center concentration — assume ~40–50% peak penetration):

Peak share Peak US revenue
30% ~$160M
40% ~$210M
50% ~$265M

Bottom line

Caveats

Would you like me to (a) extend this to 2L+ including 3L, (b) add EU5, or (c) run a sensitivity table on the fit/share assumptions?

Reference answer key (deterministic) — open after grading

Deterministic funnel for ES-SCLC in US built from the curated tool data (basis = incidence). Eligibility gating is the product of the subtype fractions that apply to this drug, then the line-of-therapy gate. The peak-revenue sketch uses an illustrative 30% peak share; a strong agent may choose a different, well-justified share. Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.

Funnel stepPatients / valueCalculation
1. Incidence (new/yr)33,000US ES-SCLC; basis = incidence
2. Diagnosed31,350x 95% diagnosis rate
3. Drug-treated26,648x 85% treatment rate
4. Extensive-stage18,653x 70%
5. DLL3-expressing15,855x 85%
6. Fit for 2L therapy8,720x 55%
7. Line gate: 2L+8,720x 100% (=1.0 if already encoded above)
= Addressable patients8,720eligibility = 33% of treated, x line
Peak capture @ 30% share2,616illustrative peak share assumption
Eff. revenue / patient-yr$121,000$220,000 list x 55% persistence
~ Peak revenue (USD/yr)$316,550,316= captured patients x eff. revenue/pt

Expert grading

Epidemiology sourcing & funnel construction 1 (poor) 5 (excellent)
5: Pulls the right epidemiology via the tools, correctly chooses incidence vs prevalence as the funnel basis for the disease (incidence for acute/short-survival oncology, prevalence for chronic disease), and lays out a clean population -> diagnosed -> treated -> eligible -> addressable chain for the queried geography.
1: Builds the funnel from the wrong base (e.g. prevalence for an incidence-driven cancer, or vice versa), skips diagnosis/treatment steps, ignores the requested geography, or reasons from memory instead of the tool data.
Eligibility / biomarker gating correctness 1 (poor) 5 (excellent)
5: Applies the correct biomarker / subtype / stage gates for THIS drug and only those — e.g. advanced-stage AND activating EGFR mutation for a 1L EGFR TKI, DLL3-expressing AND fit-for-2L for a DLL3 engager, HER2+ AND metastatic for a 2L ADC — and applies the line-of-therapy gate without double-counting.
1: Omits a required gate (e.g. forgets the EGFR-mutant or DLL3 filter), applies an irrelevant or wrong-direction gate, double-counts a line split already implied by another gate, or multiplies fractions that should not stack.
Numerical correctness & internal consistency 1 (poor) 5 (excellent)
5: Every multiplication checks out against the returned tool numbers; intermediate counts are consistent and monotonically shrinking down the funnel; the final addressable number is reproducible from the stated inputs.
1: Arithmetic errors, mismatched units, numbers that don't follow from the cited fractions, or a funnel step larger than the one above it.
Assumptions & peak-share / revenue reasoning 1 (poor) 5 (excellent)
5: States and justifies the peak-share and pricing assumptions, applies persistence / treated duration sensibly, and produces a revenue sketch (addressable x share x effective price) whose magnitude is defensible; flags the key sensitivities.
1: Pulls a peak share or price out of thin air with no rationale, ignores persistence/duration, garbles the revenue formula, or presents a point estimate with no acknowledgement of uncertainty.
Evidence faithfulness 1 (poor) 5 (excellent)
5: Every number traces to a specific tool output (epidemiology counts, subtype fractions, price); no fabricated rates or invented epidemiology; the curated/teaching nature of the data is respected and not overstated as live truth.
1: Invents incidence/prevalence or subtype fractions not returned by the tools, contradicts the tool data, or presents the snapshot numbers as authoritative real-world figures.
Overall verdict
Your name / ID