Using Deep Learning to Generate and Classify Thyroid Cytopathology Reports According to The Bethesda System
Bibliographic record
Abstract
The purpose of this paper is to study approaches to the intellectual processing of Russianlanguage textual medical information concerning the thyroid cytopathology description to solve the issues of their classification and generation of the text of the medical report, as well as augmentation of descriptions in their acute shortage.Over the past decade, the field of biomedicine has not undergone significant changes.Approaches to analyzing patients' problems are mostly based on manual processing and expert knowledge of doctors.The paper considers the creation of a machine-learning pipeline containing a full cycle of data preprocessing and model training in the field of thyroid nodules fine-needle aspiration classification according to the Bethesda thyroid cytopathology reporting system.Sequential and transformer neural networks were used to design the architecture of deep learning models.The paper proposes approaches for cleaning and preprocessing raw medical descriptions to the required type.The obtained results show that sequential neural networks have greater accuracy on small data sets, and transformation architectures are superior to others when generating cytopathological reports on large amounts of data.The solution obtained in the study can be used as an additional reference tool for thyroid cytologists.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".