Bibliographic record
Abstract
PURPOSE: The Papnet system was initially designed for rescreening negative Pap tests but may also be an effective primary screener. METHODS: A set of 2,200 archival slides diagnosed by conventional, manual screening as 2,000 (90%) WNL, 47 (2.1%) carcinomas, 50 (2.3%), HSIL, 50 (2.3%) LSIL, and 53 (2.4%) ASCUS/AGUS were compared to the results of Papnet-assisted, primary screening. Following Papnet scanning, the digitized images were triaged and classified as abnormal or negative. All abnormals had a full manual screening, whereas negatives had a limited screening. Results by each screening method were compared and discordant cases were peer reviewed for a consensus result. Screening efficacy by each method was measured against a standard result composed of the concordant and consensus results. RESULTS: There were 101 concordant and 181 discordant abnormal results. The standard result for the slide set was 1,953 (88.9%) WNL, 87 (3.9%) ASCUS/AGUS, 52 (2.4%) LSIL, 62 (2.8%) HSIL, 39 (1.8%) carcinomas, and 5 (0.2%) unsatisfactory. Papnet versus manual sensitivity rates were 87.6% vs 72.3% at the ASCUS/AGUS threshold, 85.6% vs 82.4% at the LSIL threshold, and 89.1% vs 90.1% at the HSIL threshold. CONCLUSIONS: Papnet-assisted, primary screening equals conventional, manual screening in the detection of a wide range of cell abnormalities and is more effective in the detection of abnormalities at the lower end of the abnormal spectrum.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".