Related Experiment Video
Updated: May 25, 2025
07:41
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
8.8K
Structuring and centralizing breast cancer real-world biomarker data from pathology reports through C-LAB® artificial
Florent Le Borgne1, Camille Garnier2, Camille Morisseau1
1Data Factory & Analytics Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France.
Digital Health
|February 27, 2025
Summary
An AI platform, C-LAB®, effectively structured breast cancer biomarker data from pathology reports, achieving over 80% agreement with human extraction. This technology promises to streamline data management for precision diagnostics.
Area of Science:
- Biomedical Informatics
- Computational Pathology
- Artificial Intelligence in Medicine
Background:
- Breast cancer pathology reports are often unstructured and heterogeneous, posing challenges for data extraction.
- Centralizing biomarker data is crucial for accurate diagnostics and treatment planning.
Purpose of the Study:
- To evaluate the effectiveness of the C-LAB® artificial intelligence (AI) platform in extracting, structuring, and centralizing biomarker data from breast cancer pathology reports.
- To assess the AI platform's performance on a challenging, heterogeneous dataset from the Institut de Cancérologie de l'Ouest (ICO).
Main Methods:
- The C-LAB® AI platform was deployed to analyze HER2 and hormonal receptor data from breast cancer pathology reports.
- An iterative process involving 292 reports refined the rule-based extraction algorithm.
- The finalized algorithm was applied to 2323 reports, with performance assessed against a subset (666 reports) available in the structured ESME database.
Main Results:
- C-LAB® achieved over 80% agreement (precision, recall, F1-score) with human extractions for structuring biomarker data.
- The platform demonstrated effectiveness despite dataset variability and optical character recognition errors.
- The AI platform showed potential to reduce manual workload and enable scalable, real-time reporting.
Conclusions:
- AI technologies like C-LAB® can transform complex pathology data into accessible digital formats.
- This facilitates precision management in diseases like breast cancer, improving diagnostics and treatment.
- C-LAB® shows significant potential for enhancing breast cancer data analysis and clinical decision-making.
