Precision starts with classification: What neuroendocrine cancers mean for health plans
Author: Candice Gagliardi, PharmD, BCOP
Disease progression in extrapulmonary neuroendocrine carcinoma (epNEC) carries a substantial economic burden that extends beyond drug spending. In an analysis presented at Academy of Managed Care Pharmacy (AMCP) Nexus 2026, patients with progression had an adjusted mean all-cause cost of $7,703 per patient per month (PPPM), compared with $2,860 among patients with stable or improved disease. Hospitalization costs showed an especially large difference, averaging $2,174 versus $322 PPPM.1 This substantial cost of progression underscores why accurately distinguishing neuroendocrine cancers with different prognoses and treatment approaches matters.
Why classification matters
Neuroendocrine neoplasms (NENs) are rare tumors that arise from neuroendocrine cells most commonly found in the gastrointestinal tract, pancreas and lungs, although they can occur in other organs.2,3 Histological classification is essential, but it can be challenging because of overlap among NEN subtypes and differentiation status.1 Tumor grade and differentiation provide important information about prognosis and treatment strategies.5 Pathologists interpret tumor grade by looking at Ki-67, a biomarker of cell division, to determine the tumor’s proliferation index, or how quickly the cells are dividing.4 Although standardized classification criteria have improved grading, variability in interpretation can remain.5
This distinction becomes particularly important in Grade 3 tumors, which can be difficult for pathologists to distinguish when comparing tumor cells to normal cells at the primary tumor site and differentiating well-differentiated neuroendocrine tumors (WD-NETs) from poorly differentiated neuroendocrine carcinomas (PD-NECs), taking into account the mitotic rate and Ki-67 proliferation index.3,4 In a 2016 study by Tang et al., pathologists reviewing high-grade pancreatic NENs disagreed on classification in more than half of the cases, highlighting the limitations of morphology alone.5 Although both WD-NETs and PD-NECs can demonstrate high proliferative activity, they are biologically distinct and may have differences in molecular alterations and mutation profiles.5,6 PD-NECs are generally more aggressive and progress rapidly. For example, median overall survival in pancreatic PD-NEC has been reported as approximately 11–12 months, while well-differentiated NETs generally have a much more favorable prognosis with a median survival exceeding 10 years.3,4 These differences make accurate classification important for both prognosis and treatment selection.
An emerging approach to improve classification
To address these classification challenges, Timothy Khumpan and colleagues conducted a retrospective study at Fox Chase Cancer Center using an artificial intelligence (AI) algorithm to distinguish PD-NECs from WD-NETs. The study included 21 WD-NET and 15 PD-NEC samples across 11 primary tumor sites and analyzed 730 genes for expression patterns. The researchers identified distinct molecular patterns in PD-NEC, including activation of pathways related to cell-cycle regulation, replication stress, and DNA damage response programs, along with a list of associated biomarkers that span DNA repair, chromatin regulation, cell-cycle checkpoints and neuroendocrine signaling. These findings suggest that patterns of gene expression may provide an additional tool for distinguishing WD-NETs from PD-NECs when histology alone is ambiguous.3 However, given the small sample size and rarity of these tumors, larger studies are needed to validate this approach before it can be incorporated into routine clinical practice.
Managed care takeaways
For health plans, the challenge of accurately classifying neuroendocrine cancers has implications beyond diagnosis. Distinguishing WD-NETs from PD-NECs can influence prognosis and treatment selection, making classification an important part of the broader treatment pathway. While approaches to tumor classification are becoming more precise, research is continuing to evaluate new and evolving treatment options across neuroendocrine cancers. Data is still anticipated from the ongoing clinical trials evaluating the use of Tecentriq with chemotherapy in advanced epNEC.8 In September 2026, the FDA approved two radioligands for the treatment of gastroenteropancreatic neuroendocrine tumors (GEP-NETs), Bravnetsa and Bexlutry, utilizing the NETTER-1 results from the reference product, Lutathera (lutetium Lu 177 dotatate).9–11 As both areas advance, health plans may need to consider how pathology, biomarker testing, imaging and treatment policies work together, rather than evaluating each component in isolation.
Emerging AI-assisted approaches to tumor classification also raise important questions about when new diagnostic technologies are ready for routine use. Developing this evidence can be particularly challenging for rare cancers like NENs because studies often include small, heterogeneous patient populations. The classifier discussed above, for example, included only 21 WD-NET and 15 PD-NEC samples, reinforcing the need for additional validation before routine clinical use. Health plans must consider if results provide clinical validity and to which population(s) those results can be applied.
Coverage is also only one piece of the puzzle. As diagnostic and treatment options evolve in parallel, health plans may need to align testing requirements, prior authorization criteria and treatment policies so that clinically meaningful results can be acted upon without unnecessary delays. This may be particularly relevant in aggressive cancers like epNEC, where progression has been associated with substantially higher healthcare costs.1 As classification becomes more precise, the challenge for managed care will be translating that precision into timely access to the right treatment.
All brand names are property of their respective owners.
References
- Vijayvergia, N., Liu, N., Liu, E., Curran, A., Scherrer, E., Vrieze, K., Christensen, A., Ijioma, S., & Gay, C. (2026). The economic burden of disease progression in extra-pulmonary neuroendocrine carcinoma (epNEC): A multimodal database analysis. Journal of Managed Care & Specialty Pharmacy, 32(10 Suppl.), S74. https://amcpnexus.org/sites/default/files/2026-10/2026_October%20JMCP%20Poster%20Abstract_SupplementFINAL.pdf
-
Yücel, Z., Akal, F., & Oltulu, P. (2024). Automated AI-based grading of neuroendocrine tumors using Ki-67 proliferation index: Comparative evaluation and performance analysis. Medical & Biological Engineering & Computing, 62, 1899–1904. https://doi.org/10.1007/s11517-024-03045-8
-
Khumpan, T., Chewe, K., Vijayvergia, N., Eleam, E., Quiñones-Romero, J. N., Peri, S., Yulan, G., Engstrom, P. F., Cai, K. Q., Pei, J., Alekbaeva, G. D., Campbell, K. S., Whetstine, J. R., Astsaturov, I., & Lee, H. (2026). AI-powered histopathology classifiers identify transcriptomic biomarkers associated with cell cycle regulation and increased mitotic activity in poorly differentiated neuroendocrine carcinoma. Human Genomics, 20(1), 142. https://doi.org/10.1186/s40246-026-01032-8
-
Neuroendocrine Tumor Research Foundation. (n.d.). NET grade & stage. https://netrf.org/for-patients/net-grade-stage/
-
Tang, L. H., Basturk, O., Sue, J. J., & Klimstra, D. S. (2016). A practical approach to the classification of WHO grade 3 (G3) WD-NET and poorly differentiated neuroendocrine carcinoma (PD-NEC) of the pancreas. American Journal of Surgical Pathology, 40(9), 1192–1202. https://doi.org/10.1097/PAS.0000000000000662
-
Simon, T., Riemer, P., Jarosch, A., Detjen, K., Di Domenico, A., Bormann, F., Menne, A., Khouja, S., Monjé, N., Childs, L. H., Lenze, D., Leser, U., Rossner, F., Morkel, M., Blüthgen, N., Pavel, M., Horst, D., Capper, D., Marinoni, I., … Sers, C. (2022). DNA methylation reveals distinct cells of origin for pancreatic neuroendocrine carcinomas and pancreatic neuroendocrine tumors. Genome Medicine, 14(1), 24. https://doi.org/10.1186/s13073-022-01018-w
-
Javaid, H., Petrescu, C. C., Schmunk, L. J., Monahan, J. M., O'Reilly, P., Garg, M., McGirr, L., Khasawneh, M. T., Al Lail, M., Ganta, D., Stubbs, T. M., Sun, B. B., Vitsios, D., & Martin-Herranz, D. E. (2025). The impact of artificial intelligence on biomarker discovery. Emerging Topics in Life Sciences, 8(2), 89–105. https://doi.org/10.1042/ETLS20243003
-
National Library of Medicine. (2026, November 12). Evaluating the addition of the immunotherapy drug atezolizumab to standard chemotherapy treatment for advanced or metastatic neuroendocrine carcinomas that originate outside the lung (Identifier NCT05058651). ClinicalTrials.gov. https://clinicaltrials.gov/study/NCT05058651
-
Ernst, D. (2026, September 24). FDA approves bravnetsa as equivalent to lutathera for GEP-NETs. EMPR. https://www.empr.com/news/bravnetsa-fda-approval-gep-nets/
-
Ernst, D. (2026, September 15). FDA approves radioligand equivalent bexlutry for SSTR+ GEP-NETs. EMPR. https://www.empr.com/news/fda-approves-radioligand-equivalent-bexlutry-for-sstr-gep-nets/
-
Strosberg, J. R., Caplin, M. E., Kunz, P. L., Ruszniewski, P. B., Bodei, L., Hendifar, A., Mittra, E., Wolin, E. M., Yao, J. C., Pavel, M. E., Grande, E., Van Cutsem, E., Seregni, E., Duarte, H., Gericke, G., Bartalotta, A., Mariani, M. F., Demange, A., Mutevelic, S., & Krenning, E. P. (2021). 177 Lu-Dotatate plus long-acting octreotide versus high‑dose long-acting octreotide in patients with midgut neuroendocrine tumours (NETTER-1): Final overall survival and long-term safety results from an open-label, randomised, controlled, phase 3 trial. The Lancet Oncology, 22(12), 1752–1763. https://www.doi.org/10.1016/S1470-2045(21)00572-6