ACUITEE: A Comprehensive Tool for Visualization, Editing and Curating textual Annotations in Clinical Data
Bibliographic record
Abstract
Annotation and management of clinical data remains a critical but challenging task due to the complexity and diversity of medical records.Providing a tool to simplify, shorten, and improve the annotation work of clinicians is essential as it leads both to process optimization and better patients' characterization.We present ACUITEE (Annotation and Curation User Interface for Terms Extraction Engines), a web application that addresses these challenges.It offers a simple way to improve clinical data annotation workflows by integrating automatic analysis, manual processing, and real-time visualization of medical notes.Using advanced natural language processing (NLP) techniques for phenotypes extraction such as PhenoBERT and efficient string-matching algorithms, ACUITEE maps free-text medical notes to ontology terms and enables clinicians to validate or refine these annotations through a user-friendly interface.The system supports fully automated, semi-automated and manual annotation modes, providing flexibility for different use cases.A key feature of ACUITEE is its interactive annotation interface, which enables clinicians to validate, edit, and curate ontology terms with precision, thereby speeding up the annotation process while maintaining high accuracy.This paper outlines ACUITEE's architecture, features, and applications and demonstrates its potential to facilitate clinical data annotation through increased efficiency, adaptability, and user engagement.ACUITEE is freely available at https://acuitee.labs.b-com.com/.The source code is available at https://github.com/b-com/ACUITEEfor local installation for protected health data.
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 | 0.007 | 0.030 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.008 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.048 | 0.022 |
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".