I'll size this opportunity step by step. Let me start by checking the dataset structure and pulling the relevant 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 Not a live data pull; do not cite as ground truth.",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"
}
}
}The indication is "HER2+ Breast", built from incidence. Let me pull all the relevant data.
{
"disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
"indication": "HER2+ Breast",
"label": "HER2-positive breast cancer",
"funnel_basis": "incidence",
"diagnosis_rate": 0.95,
"treatment_rate": 0.9,
"epidemiology": {
"US": {
"incidence_per_year": 300000,
"prevalence": 4000000
}
},
"note": "funnel_basis tells you whether to start the funnel from incidence (new patients/year) or prevalence (point count of living patients)."
}{
"disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
"indication": "HER2+ Breast",
"subtypes": {
"HER2_positive_fraction": 0.15,
"metastatic_fraction": 0.3
},
"line_splits": {
"1L": 0.55,
"2L": 0.3,
"3L+": 0.15
},
"notes": "HER2+ ~15% of breast cancer. A 2L+ metastatic ADC (e.g. T-DXd) gates on HER2-positivity AND metastatic disease. For a 2L slice, apply the 2L line-split to the metastatic HER2+ population."
}{
"disclaimer": "Teaching snapshot: curated, rounded epidemiology for funnel-building practice. Not a live data pull; do not cite as ground truth.",
"indication": "HER2+ Breast",
"annual_price": 160000,
"treated_months": 16,
"persistence": 0.8,
"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."
}Now I have everything I need. Let me build the funnel.
| Step | Factor | Patients |
|---|---|---|
| New breast cancer cases/year | 300,000 | 300,000 |
| × Diagnosed | 0.95 | 285,000 |
| × Treated | 0.90 | 256,500 |
| × HER2-positive | 0.15 | 38,475 |
| × Metastatic | 0.30 | 11,543 |
| × 2L line split | 0.30 | 3,463 |
US 2L addressable population ≈ 3,500 patients/year (incident).
Using the pricing inputs:
- Effective revenue per patient/year = $160,000 × 0.80 persistence = $128,000
Peak revenue ≈ 3,463 patients × $128,000 ≈ $443M
The funnel above counts ~3,500 newly eligible patients each year, but the mean treated duration is 16 months (1.33 years) — longer than a year. So at steady state, the prevalent on-therapy pool is larger than a single year's incident cohort:
(Note: with a duration adjustment, persistence and treated-months partly overlap conceptually — the persistence factor already captures the fraction-of-year paid. A clean way to present this is the two bookends below.)
| Estimate | Addressable | Peak revenue |
|---|---|---|
| Incident-cohort basis (no duration uplift) | ~3,500/yr | ~$440M |
| Steady-state on-therapy basis (16-mo duration uplift) | ~4,600 | ~$590M |
Bottom line: A T-DXd-like HER2 ADC in 2L metastatic HER2+ breast cancer addresses roughly 3,500 US patients/year, supporting a peak US revenue of roughly $0.4–0.6B, depending on whether you credit treatment duration beyond one year.
persistence (0.8) and treated_months (16). I'd lead with the ~$440M incident-cohort number as the cleaner, more defensible estimate and treat ~$590M as the duration-adjusted upper bound.Want me to extend this to EU5, layer in 1L/HER2-low expansion, or apply a market-share assumption?
Now I have everything I need. Let me build the funnel.
| Step | Factor | Patients |
|---|---|---|
| New breast cancer cases/year | 300,000 | 300,000 |
| × Diagnosed | 0.95 | 285,000 |
| × Treated | 0.90 | 256,500 |
| × HER2-positive | 0.15 | 38,475 |
| × Metastatic | 0.30 | 11,543 |
| × 2L line split | 0.30 | 3,463 |
US 2L addressable population ≈ 3,500 patients/year (incident).
Using the pricing inputs:
- Effective revenue per patient/year = $160,000 × 0.80 persistence = $128,000
Peak revenue ≈ 3,463 patients × $128,000 ≈ $443M
The funnel above counts ~3,500 newly eligible patients each year, but the mean treated duration is 16 months (1.33 years) — longer than a year. So at steady state, the prevalent on-therapy pool is larger than a single year's incident cohort:
(Note: with a duration adjustment, persistence and treated-months partly overlap conceptually — the persistence factor already captures the fraction-of-year paid. A clean way to present this is the two bookends below.)
| Estimate | Addressable | Peak revenue |
|---|---|---|
| Incident-cohort basis (no duration uplift) | ~3,500/yr | ~$440M |
| Steady-state on-therapy basis (16-mo duration uplift) | ~4,600 | ~$590M |
Bottom line: A T-DXd-like HER2 ADC in 2L metastatic HER2+ breast cancer addresses roughly 3,500 US patients/year, supporting a peak US revenue of roughly $0.4–0.6B, depending on whether you credit treatment duration beyond one year.
persistence (0.8) and treated_months (16). I'd lead with the ~$440M incident-cohort number as the cleaner, more defensible estimate and treat ~$590M as the duration-adjusted upper bound.Want me to extend this to EU5, layer in 1L/HER2-low expansion, or apply a market-share assumption?
Deterministic funnel for HER2+ Breast 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 step | Patients / value | Calculation |
|---|---|---|
| 1. Incidence (new/yr) | 300,000 | US HER2+ Breast; basis = incidence |
| 2. Diagnosed | 285,000 | x 95% diagnosis rate |
| 3. Drug-treated | 256,500 | x 90% treatment rate |
| 4. HER2-positive | 38,475 | x 15% |
| 5. Metastatic | 11,542 | x 30% |
| 6. Line gate: 2L (metastatic ADC) | 3,463 | x 30% (=1.0 if already encoded above) |
| = Addressable patients | 3,463 | eligibility = 4% of treated, x line |
| Peak capture @ 30% share | 1,039 | illustrative peak share assumption |
| Eff. revenue / patient-yr | $128,000 | $160,000 list x 80% persistence |
| ~ Peak revenue (USD/yr) | $132,969,600 | = captured patients x eff. revenue/pt |