← Epidemiology-Based Market Sizing
Commercial / Forecasting · Commercial forecasting analyst

Epidemiology-Based Market Sizing — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T09:08:18.824431+00:00 · 4 tool calls · 20.6s · 6410 tokens
run id: market_sizing_20260606_020653_04_estimate-the-us-addressable-patient-funnel-and-r

Query

Estimate the US addressable patient funnel and rough peak revenue for an oral advanced therapy in moderate-to-severe ulcerative colitis.

Trajectory

Agent · turn 1

I'll help you estimate the US addressable patient funnel and peak revenue for an oral advanced therapy in moderate-to-severe ulcerative colitis. Let me start by exploring the available 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 Not a live data pull; do not cite as ground truth.",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

Ulcerative Colitis is available with a prevalence-based funnel for the US. Let me pull all the relevant data.

⚙ calls get_epidemiology(indication=Ulcerative Colitis, geography=US)
⚙ calls get_subtype_prevalence(indication=Ulcerative Colitis)
⚙ calls get_pricing(indication=Ulcerative Colitis)
↳ 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 Not a live data pull; do not cite as ground truth.",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": "Ulcerative Colitis",
  "label": "Ulcerative colitis (moderate-to-severe)",
  "funnel_basis": "prevalence",
  "diagnosis_rate": 0.85,
  "treatment_rate": 0.9,
  "epidemiology": {
    "US": {
      "incidence_per_year": 38000,
      "prevalence": 900000
    }
  },
  "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": "Ulcerative Colitis",
  "subtypes": {
    "moderate_to_severe_fraction": 0.35,
    "advanced_therapy_eligible_fraction": 0.6
  },
  "line_splits": {
    "1L_advanced": 0.6,
    "2L_advanced": 0.4
  },
  "notes": "Chronic disease: build from PREVALENCE, not incidence. ~35% of diagnosed UC is moderate-to-severe; of those ~60% are candidates for advanced therapy (biologics / JAK inhibitors / S1P modulators). Annual dosing, full year of therapy with discontinuation captured by persistence."
}
↳ 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": "Ulcerative Colitis",
  "annual_price": 45000,
  "treated_months": 12,
  "persistence": 0.75,
  "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 all the data needed. Let me build the funnel from prevalence (correct for a chronic disease) and sketch peak revenue.

US Addressable Patient Funnel — Moderate-to-Severe UC

Step Factor Patients
US prevalence (UC, all severity) 900,000 900,000
× Diagnosed 0.85 765,000
× Treated 0.90 688,500
× Moderate-to-severe fraction 0.35 240,975
× Advanced-therapy eligible 0.60 144,585

Total addressable population ≈ 145,000 patients (advanced-therapy-eligible, moderate-to-severe UC in the US).

Line-of-therapy split

Rough Peak Revenue Sketch

Effective revenue per addressable patient/year = annual price × persistence
= $45,000 × 0.75 = $33,750/patient/year

Peak revenue depends on the peak market share you capture of the ~145K addressable pool. Since this is a crowded class (biologics, JAK inhibitors, S1P modulators), here is a scenario range:

Peak share of addressable Treated patients Peak revenue
5% ~7,200 ~$245M
10% ~14,500 ~$490M
15% ~21,700 ~$730M
20% ~28,900 ~$975M

Total addressable revenue (100% capture, theoretical ceiling): 144,585 × $33,750 ≈ $4.9B.

Bottom line


Key assumptions & caveats:
- Funnel built from prevalence (correct for chronic disease), not incidence.
- Peak share is the main swing variable — I haven't been given a share assumption, so I've shown a scenario range rather than a single number.
- Persistence (0.75) captures discontinuation/mortality, reflecting that real-world adherence to advanced UC therapies erodes over the year.
- Figures use list price; net of rebates/gross-to-net (often 30–50% in this class) would meaningfully lower realized revenue — a real model should layer that on.
- This is a teaching snapshot with rounded, curated numbers — not a citable real-world data pull.

Would you like me to (a) apply a gross-to-net adjustment, (b) model a specific peak-share assumption, or (c) build the EU5 funnel for comparison?

Final output

I have all the data needed. Let me build the funnel from prevalence (correct for a chronic disease) and sketch peak revenue.

US Addressable Patient Funnel — Moderate-to-Severe UC

Step Factor Patients
US prevalence (UC, all severity) 900,000 900,000
× Diagnosed 0.85 765,000
× Treated 0.90 688,500
× Moderate-to-severe fraction 0.35 240,975
× Advanced-therapy eligible 0.60 144,585

Total addressable population ≈ 145,000 patients (advanced-therapy-eligible, moderate-to-severe UC in the US).

Line-of-therapy split

Rough Peak Revenue Sketch

Effective revenue per addressable patient/year = annual price × persistence
= $45,000 × 0.75 = $33,750/patient/year

Peak revenue depends on the peak market share you capture of the ~145K addressable pool. Since this is a crowded class (biologics, JAK inhibitors, S1P modulators), here is a scenario range:

Peak share of addressable Treated patients Peak revenue
5% ~7,200 ~$245M
10% ~14,500 ~$490M
15% ~21,700 ~$730M
20% ~28,900 ~$975M

Total addressable revenue (100% capture, theoretical ceiling): 144,585 × $33,750 ≈ $4.9B.

Bottom line


Key assumptions & caveats:
- Funnel built from prevalence (correct for chronic disease), not incidence.
- Peak share is the main swing variable — I haven't been given a share assumption, so I've shown a scenario range rather than a single number.
- Persistence (0.75) captures discontinuation/mortality, reflecting that real-world adherence to advanced UC therapies erodes over the year.
- Figures use list price; net of rebates/gross-to-net (often 30–50% in this class) would meaningfully lower realized revenue — a real model should layer that on.
- This is a teaching snapshot with rounded, curated numbers — not a citable real-world data pull.

Would you like me to (a) apply a gross-to-net adjustment, (b) model a specific peak-share assumption, or (c) build the EU5 funnel for comparison?

Reference answer key (deterministic) — open after grading

Deterministic funnel for Ulcerative Colitis in US built from the curated tool data (basis = prevalence). 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. Prevalence (point)900,000US Ulcerative Colitis; basis = prevalence
2. Diagnosed765,000x 85% diagnosis rate
3. Drug-treated688,500x 90% treatment rate
4. Moderate-to-severe240,975x 35%
5. Advanced-therapy eligible144,585x 60%
6. Line gate: 1L advanced86,751x 60% (=1.0 if already encoded above)
= Addressable patients86,751eligibility = 21% of treated, x line
Peak capture @ 30% share26,025illustrative peak share assumption
Eff. revenue / patient-yr$33,750$45,000 list x 75% persistence
~ Peak revenue (USD/yr)$878,353,875= 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