Impact of Next-generation Sequencing on Interobserver Agreement and Diagnosis of Spitzoid Neoplasms
Bibliographic record
Abstract
Atypical Spitzoid melanocytic tumors are diagnostically challenging. Many studies have suggested various genomic markers to improve classification and prognostication. We aimed to assess whether next-generation sequencing studies using the Tempus xO assay assessing mutations in 1711 cancer-related genes and performing whole transcriptome mRNA sequencing for structural alterations could improve diagnostic agreement and accuracy in assessing neoplasms with Spitzoid histologic features. Twenty expert pathologists were asked to review 70 consultation level cases with Spitzoid features, once with limited clinical information and again with additional genomic information. There was an improvement in overall agreement with additional genomic information. Most significantly, there was increase in agreement of the diagnosis of conventional melanoma from moderate (κ=0.470, SE=0.0105) to substantial (κ=0.645, SE=0.0143) as measured by an average Cohen κ. Clinical follow-up was available in all 70 cases which substantiated that the improved agreement was clinically significant. Among 3 patients with distant metastatic disease, there was a highly significant increase in diagnostic recognition of the cases as conventional melanoma with genomics (P<0.005). In one case, none of 20 pathologists recognized a tumor with BRAF and TERT promoter mutations associated with fatal outcome as a conventional melanoma when only limited clinical information was provided, whereas 60% of pathologists correctly diagnosed this case when genomic information was also available. There was also a significant improvement in agreement of which lesions should be classified in the Spitz category/WHO Pathway from an average Cohen κ of 0.360 (SE=0.00921) to 0.607 (SE=0.0232) with genomics.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.115 | 0.199 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".