Testing Algorithms for the Diagnosis of Malignant Glandular Tumors of the Uterine Cervix Histotyped per the International Endocervical Adenocarcinoma Criteria and Classification (IECC) System
Bibliographic record
Abstract
The International Endocervical adenocarcinoma Criteria and Classification (IECC) categorizes tumors into human papilloma virus (HPV) associated (HPVA), not associated (NHPV), and invasive adenocarcinoma not otherwise specified (IA NOS). HPVA and NHPV encompass 11 histotypes and an algorithm of mucin content, HPV ribonucleic acid (RNA), estrogen receptor and GATA3 is proposed for the diagnosis of most. In this study, the IECC algorithm's diagnoses were compared with hematoxylin and eosin (H&E) based IECC histotyping. Kappa statistics measured performance agreement. With additional markers, hierarchical clustering by random forest (RF) classification identified the most discriminating between tumor types, and investigated other algorithms. Three pathologists independently reviewed digitized H&E images of n=152 primary cervical adenocarcinomas for IECC histotype and mucin content, and tissue microarrays for expression of HPV RNA by in situ hybridization and 16 antibodies by immunohistochemistry. Results were finalized by consensus. There were n=113 HPVA, n=22 NHPV, and n=17 IA NOS. Mucin was obvious in n=36 and limited in n=116. Among n=124 with satisfactory test results, HPV RNA was positive in n=96, estrogen receptor in n=72, and GATA3 in n=15. The IECC algorithm diagnosed n=99 which agreed with H&E histotyping in n=64 for a fair κ of 0.36 (95% confidence interval, 0.21-0.50): n=12 were undiagnosed and n=13 were IA NOS. Small sample sizes restricted RF to HPVA versus NHPV which were discriminated by p16, HPV RNA, and MUC6 with an area under the curve of 0.74 (95% confidence interval, 0.58-0.90). The IECC algorithm for histotyping under-performed. The RF algorithmin for categorization was favorable, but validation in larger studies and investigation of additional algorithms to discriminate between all IECC histotypes are needed.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".