Reproducibility of neuroendocrine lung tumor classification

For a tumor classification scheme to be useful, it must be reproducible and it must show clinical significance. Classification of neuroendocrine lung tumors is a difficult problem with little information about interobserver reproducibility. We sought to evaluate the classification of typical carcinoid (TC), atypical carcinoid (AC), large-cell neuroendocrine carcinoma (LCNEC), and small-cell carcinoma (SCC) tumors as proposed by W.D. Travis et al (Am J Surg Pathol 15:529, 1991). Forty neuroendocrine tumors were retrieved from the Armed Forces Institute of Pathology (AFIP) files and independently evaluated by five lung pathologists and classified as TC, AC, LCNEC, or SCC (pure SCC, mixed small cell/large cell, and combined SCC). A single hematoxylin and eosin-stained slide from each case was reviewed. Each participant was provided a set of tables summarizing the criteria for separation of the four major categories. Agreement was regarded as unanimous if all five pathologists agreed, a majority if four agreed, and a consensus if three or more pathologists agreed. The kappa statistic was calculated to measure the degree of agreement between two observers. A consensus diagnosis was achieved in all 40 cases (100%), a majority agreement in 31 of 40 (78%), and unanimous agreement in 22 of 40 (55%) of cases. Unanimous agreement occurred in seven of SCC (70%), seven of TC (58%), four of AC (50%), and four of LCNEC (40%). A majority diagnosis was achieved in 11 of 12 (92%) of TC, 9 of 10 (90%) of SCC, 6 of 8 (75%) of AC, and 5 of 10 (50%) of LCNEC. Most of the kappa values were 0.70 or greater, falling into the substantial agreement category. The most common disagreements fell between LCNEC and SCC, followed by TC and AC, and AC and LCNEC. The highest reproducibility occurred for SCC and TC, with disagreement in 8% and 10% of the diagnoses, respectively. For TC, 10% of the diagnoses rendered were AC. For AC, 15% of the diagnoses were rendered as TC, with 2.5% called LCNEC and 2.5% called SCC. For LCNEC, 18% and 4% of the diagnoses were called SCC and AC, respectively. For SCC, 4% of the diagnoses were called AC and 4% were called LCNEC. Thus, using the classification scheme tested, a consensus diagnosis can be achieved for virtually all neuroendocrine lung tumors with substantial agreement between experienced lung pathologists. Classification of NE tumors is most reproducible for classification of TC and SCC but less reproducible for AC and LCNEC. These results indicate a need for more careful definition and application of criteria for TC versus AC and SCC versus LCNEC.