Judged 1–5 on the expert rubric. The deterministic answer key is the same one on the environment page.
| funnel_construction | 5 |
| eligibility_gating | 2 |
| numerical_consistency | 4 |
| assumptions_revenue | 4 |
| faithfulness | 4 |
Now I have everything. Let me build the funnel from incidence.
The dataset gives SCLC total incidence; I gate down to the eligible 2L DLL3+ pool.
| Step | Fraction | Patients/yr |
|---|---|---|
| SCLC incidence (US, new/yr) | — | 33,000 |
| × Diagnosed | 0.95 | 31,350 |
| × Treated | 0.85 | 26,648 |
| × Extensive-stage | 0.70 | 18,653 |
| × DLL3-expressing | 0.85 | 15,855 |
| × Reach/fit for 2L therapy | 0.55 | 8,720 |
| × 2L line split | 0.50 | ~4,360 |
US addressable 2L ES-SCLC DLL3+ population ≈ 4,300–4,400 new patients/year.
A note on the two "2L-ish" gates: fit_for_2L_fraction (0.55) captures whether a patient is well enough to receive any second-line therapy, while the 2L line split (0.50) captures the share actually reaching/electing 2L treatment. I applied both since they describe distinct attrition (clinical fitness vs. line progression). If you view them as overlapping, the pool is larger — see sensitivity below.
Effective revenue per addressable patient/year = price × persistence:
- $220,000 × 0.55 = $121,000 per patient-year
(The 8-month treated duration is already baked into the 0.55 persistence factor — ~8/12 ≈ 0.67, further haircut for early discontinuation/mortality, so I don't double-count it.)
Peak revenue, fully-captured addressable pool:
- 4,360 patients × $121,000 ≈ $528M
This represents 100% of the addressable pool — i.e., the theoretical ceiling, not a realistic share. Applying a more realistic peak share for a branded 2L agent (with competition):
| Peak market share | Peak US revenue |
|---|---|
| 100% (full addressable ceiling) | ~$530M |
| 60% | ~$315M |
| 40% | ~$210M |
Want me to run the EU5 geography, or model a 1L expansion scenario for upside?
| funnel_construction | 4 |
| eligibility_gating | 3 |
| numerical_consistency | 4 |
| assumptions_revenue | 3 |
| faithfulness | 4 |
Below is a transparent US funnel and rough peak revenue sketch for a DLL3 T‑cell engager (tarlatamab‑like) in 2L extensive‑stage SCLC (ES‑SCLC) using the curated dataset.
US ES‑SCLC incidence (annual new pts):
- SCLC annual incidence: 33,000
- Extensive‑stage fraction: 70%
→ 23,100 ES‑SCLC / year
Two relevant gates provided:
These are conceptually overlapping; using the explicit 2L rate (50%) for the funnel:
→ 18,653 × 50% = 9,327 2L patients
→ 9,327 × 85% = 7,928 eligible patients/year
(Rounded for peak planning purposes.)
[
220,000 \times 0.55 = 121,000
]
≈ $121K per patient
Peak share assumption is the major swing factor.
Given high unmet need in 2L ES‑SCLC and limited competition:
Treated patients:
[
8,000 \times 50\% = 4,000
]
Revenue:
[
4,000 \times 121,000 ≈ \$484M
]
✅ ~$0.5B US peak revenue
[
8,000 \times 70\% = 5,600
]
[
5,600 \times 121,000 ≈ \$678M
]
✅ ~$0.7B US peak revenue
| Metric | Estimate |
|---|---|
| US addressable 2L DLL3+ ES‑SCLC patients | ~8,000/year |
| Effective revenue per patient | ~$121K |
| Peak US revenue | $0.5–0.7B |
If you'd like, I can:
- Layer in ex‑US (EU5)
- Model impact of moving to 1L
- Add probability‑adjusted revenue
- Compare to ADC competition scenarios
- Or convert this into a quick investor-style valuation framework
| funnel_construction | 3 |
| eligibility_gating | 2 |
| numerical_consistency | 3 |
| assumptions_revenue | 2 |
| faithfulness | 3 |
Perfect! Now let me build the addressable patient population funnel and calculate peak revenue.
| Stage | Count | Notes |
|---|---|---|
| US ES-SCLC Incidence | 33,000 | Annual new cases (incidence-based funnel) |
| Diagnosed & Treated | 26,675 | × 95% diagnosis rate × 85% treatment rate |
| DLL3 Expressed | 22,674 | × 85% DLL3+ prevalence |
| Fit for 2L | 12,471 | × 55% clinically fit for second-line |
| Progress to 2L | 6,236 | × 50% actually reach second-line (line split) |
| Addressable 2L Population | 6,236 patients/year | Ready for DLL3 T-cell engager |
| Metric | Value |
|---|---|
| Addressable patients/year | 6,236 |
| Annual price (list) | $220,000 |
| Treatment persistence | 0.55 (55% of year paid) |
| Effective price/patient | ~$121,000 (= $220k × 0.55) |
| Peak Annual Revenue | ~$755 million |
This aligns with tarlatamab's labeled indication and the inherent mortality/progression dynamics of ES-SCLC.
| funnel_construction | 2 |
| eligibility_gating | 2 |
| numerical_consistency | 3 |
| assumptions_revenue | 2 |
| faithfulness | 3 |
To size the US addressable patient population and estimate the rough peak revenue for a DLL3 T-cell engager (similar to tarlatamab) in second-line treatment of extensive-stage small cell lung cancer (ES-SCLC), we'll use the following key data:
Total Incidence of SCLC:
[
\text{Total Incidence} = 33,000 \text{ patients/year}
]
Patients with Extensive-stage SCLC:
[
\text{Extensive-stage incidence} = 33,000 \times 0.70 = 23,100 \text{ patients/year}
]
Patients expressing DLL3:
[
\text{DLL3-positive patients} = 23,100 \times 0.85 \approx 19,635 \text{ patients/year}
]
Patients fit for second-line therapy:
[
\text{Fit for 2L therapy} = 19,635 \times 0.55 \approx 10,803 \text{ patients/year}
]
Effective Revenue per Patient per Year:
[
\text{Effective Price} = 220,000 \times 0.55 \approx 121,000 \text{ USD/patient/year}
]
Total Addressable Revenue:
[
\text{Total Revenue} = 10,803 \times 121,000 \approx 1,308,763,000 \text{ USD}
]
This estimate provides a useful insight into the potential market opportunity for DLL3 T-cell engagers in the specified patient population.