CoChat

Accurate Clinical Entity Recognition and Code Mapping of Anatomopathological Reports Using BioClinicalBERT Enhanced by Retrieval-Augmented Generation: A Hybrid Deep Learning Approach

Open access
Abdaoui, Hamida, Barki, Chamseddine, Dergaa, Ismail, Tlili, Karima, Ceylan, Halil İbrahim, Bragazzi, Nicola Luigi, de Giorgio, Andrea, Ben Salah, Ridha, Rahmouni, Hanene Boussi · 2025 · Bioengineering

The DOI matches its Crossref record; 61 of the 64 references it cites were found in a registry or an index, and 3 are not checked yet.

Abstract

Background: Anatomopathological reports are largely unstructured, which limits automated data extraction, interoperability, and large-scale research. Manual extraction and standardization are costly and difficult to scale. Objective: We developed and evaluated an automated pipeline for entity extraction and multi-ontology normalization of anatomopathological reports. Methods: A corpus of 560 reports from the Military Hospital of Tunis, Tunisia, was manually annotated for three entity types: sample type, test performed, and finding. The entity extraction utilized BioBERT v1.1, while the normalization combined BioClinicalBERT multi-label classification with retrieval-augmented generation, incorporating both dense and BM25 sparse retrieval over SNOMED CT, LOINC, and ICD-11. The performance was measured using precision, recall, F1-score, and statistical tests. Results: BioBERT achieved high extraction performance (F1: 0.97 for the sample type, 0.98 for the test performed, and 0.93 for the finding; overall 0.963, 95% CI: 0.933–0.982), with low absolute errors. For terminology mapping, the combination of BioClinicalBERT and dense retrieval outperformed the standalone and BM25-based approaches (macro-F1: 0.6159 for SNOMED CT, 0.9294 for LOINC, and 0.7201 for ICD-11). Cohen’s Kappa ranged from 0.7829 to 0.9773, indicating substantial to near-perfect agreement. Conclusions: The pipeline provides robust automated extraction and multi-ontology coding of anatomopathological entities, supporting transformer-based named entity recognition with retrieval-augmented generation. However, given the limitations of this study, multi-institutional validation is needed before clinical deployment.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/bioengineering13010030

Cites

61 of 64 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Confusion matrix of the BioBERT model on the test set. The values represent the number of tokens correctly or incorrectly classified for each entity.
Figure 1 Confusion matrix of the BioBERT model on the test set. The values represent the number of tokens correctly or incorrectly classified for each entity.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 64 references

Research works printed but not linked: 2

  1. Porkar, 2025, Enhancing Cancer Zone Diagnosis in MRI Images: A Novel SOM Neural Network Approach with Block Processing in the Presence of Noise, Iran. J. Blood Cancer, 17, 34
  2. Cohen, J. (2009). Statistical Power Analysis for the Behavioral Sciences, Psychology Press. [2nd ed.]. Reprint.

Cited by

See all 6

Metadata

Authors
Abdaoui, H., Barki, C., Dergaa, I., Tlili, K., Ceylan, H. İ., Bragazzi, N. L., de Giorgio, A., Ben Salah, R., & Rahmouni, H. B.
Affiliations
  • Tunis University (TN)
  • Manouba University (TN)
  • Military Hospital of Tunis (TN)
  • Physical Education of Sports Teaching Department, Faculty of Sports Sciences, Atatürk University, 25240 Erzurum, Türkiye
  • York University (CA)
  • Artificial Engineering, 80121 Naples, Italy
  • Laboratory of Biophysics and Medical Technologies, Higher Institute of Medical Technologies of Tunis (ISTMT), University of Tunis El Manar, Tunis 1006, Tunisia
Corresponding author
Bragazzi, Nicola Luigi
Venue
Bioengineering
Publisher
MDPI AG
Published
2025-12-27
Volume
13
Issue
1
Pages
30
ISSN
2306-5354 (ISSN-L)
OpenAlex
W7117468468
Cited by
6
References
47
Citations by year
2026: 6
FWCI
1.80
Type
journal article
Language
en
Open access
Locations
  • Bioengineering (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • Ataturk University - AVESIS (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
code mapping, BioClinicalBERT, retrieval-augmented generation, dense retrieval, BM25 retrieval, SNOMED CT, LOINC, ICD-11, named entity recognition, clinical text mining

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.