BERT-based natural language processing analysis of French CT reports: Application to the measurement of the positivity rate for pulmonary embolism

Jupin-Delevaux, E.; Djahnine, A.; Talbot, F.; Richard, A.; Gouttard, S.; Mansuy, A.; Douek, P.; Boussel, L.

doi:10.1016/j.redii.2023.100027

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transformers are a class of model in NLP that have shown remarkable success in generating rich text embeddings. In the context of this work, from the possible transformer architectures currently available for NLP, the BERT [90][91][92][93][94] family was chosen. The BERT transformer family has been proven to be especially well suited to text classification, with NER (Name Entity Recognition) being the type of task that is best aligned with the work proposed here.…”

Section: Skills Extractionmentioning

confidence: 99%

A Methodological Framework for Designing Personalised Training Programs to Support Personnel Upskilling in Industry 5.0

Fraile,

Psarommatis,

Alarcón

et al. 2023

Computers

View full text Add to dashboard Cite

Industry 5.0 emphasises social sustainability and highlights the critical need for personnel upskilling and reskilling to achieve the seamless integration of human expertise and advanced technology. This paper presents a methodological framework for designing personalised training programs that support personnel upskilling, with the goal of fostering flexibility and resilience amid rapid changes in the industrial landscape. The proposed framework encompasses seven stages: (1) Integration with Existing Systems, (2) Data Collection, (3) Data Preparation, (4) Skills-Models Extraction, (5) Assessment of Skills and Qualifications, (6) Recommendations for Training Program, (7) Evaluation and Continuous Improvement. By leveraging Large Language Models (LLMs) and human-centric principles, our methodology enables the creation of tailored training programs to help organisations promote a culture of proactive learning. This work thus contributes to the sustainable development of the human workforce, facilitating access to high-quality training and fostering personnel well-being and satisfaction. Through a food-processing use case, this paper demonstrates how this methodology can help organisations identify skill gaps and upskilling opportunities and use these insights to drive personnel upskilling in Industry 5.0.

show abstract

Section: Skills Extractionmentioning

confidence: 99%

A Methodological Framework for Designing Personalised Training Programs to Support Personnel Upskilling in Industry 5.0

Fraile,

Psarommatis,

Alarcón

et al. 2023

Computers

View full text Add to dashboard Cite

show abstract

“…Readily available methods to automate information extraction from imaging reports to address this question are lacking. Existing solutions rely on either ( a ) rule-based methods requiring language- and institution-specific dictionaries or ( b ) bidirectional encoder representations from transformers (or BERT)–based models dependent on subsequent fine-tuning ( 8 ). Although well suited for pretargeted tasks, these methods usually lack the expected flexibility to match the diversity of radiology reports and intended aims; tedious and specific training or adaptation to the institutional data are still necessary ( 1 ).…”

Section: Introductionmentioning

confidence: 99%

Performance of an Open-Source Large Language Model in Extracting Information from Free-Text Radiology Reports

Le Guellec,

Lefèvre,

Geay

et al. 2024

Radiology: Artificial Intelligence

View full text Add to dashboard Cite

Purpose To assess the performance of a local open-source large language model (LLM) in various information extraction tasks from real-life emergency brain MRI reports. Materials and Methods All consecutive emergency brain MRI reports written in 2022 from a French quaternary center were retrospectively reviewed. Two radiologists identified MRI scans that were performed in the emergency department for headaches. Four radiologists scored the reports’ conclusions as either normal or abnormal. Abnormalities were labeled as either headache-causing or incidental. Vicuna (LMSYS Org), an open-source LLM, performed the same tasks. Vicuna’s performance metrics were evaluated using the radiologists’ consensus as the reference standard. Results Among the 2398 reports during the study period, radiologists identified 595 that included headaches in the indication (median age of patients, 35 years [IQR, 26–51 years]; 68% [403 of 595] women). A positive finding was reported in 227 of 595 (38%) cases, 136 of which could explain the headache. The LLM had a sensitivity of 98.0% (95% CI: 96.5, 99.0) and specificity of 99.3% (95% CI: 98.8, 99.7) for detecting the presence of headache in the clinical context, a sensitivity of 99.4% (95% CI: 98.3, 99.9) and specificity of 98.6% (95% CI: 92.2, 100.0) for the use of contrast medium injection, a sensitivity of 96.0% (95% CI: 92.5, 98.2) and specificity of 98.9% (95% CI: 97.2, 99.7) for study categorization as either normal or abnormal, and a sensitivity of 88.2% (95% CI: 81.6, 93.1) and specificity of 73% (95% CI: 62, 81) for causal inference between MRI findings and headache. Conclusion An open-source LLM was able to extract information from free-text radiology reports with excellent accuracy without requiring further training. Keywords: Large Language Model (LLM), Generative Pretrained Transformers (GPT), Open Source, Information Extraction, Report, Brain, MRI Supplemental material is available for this article. Published under a CC BY 4.0 license. See also the commentary by Akinci D’Antonoli and Bluethgen in this issue.

show abstract

Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution

Djahnine,

Lazarus,

Lederlin

et al. 2024

Diagnostic and Interventional Imaging

View full text Add to dashboard Cite

BERT-based natural language processing analysis of French CT reports: Application to the measurement of the positivity rate for pulmonary embolism

Cited by 4 publications

References 32 publications

A Methodological Framework for Designing Personalised Training Programs to Support Personnel Upskilling in Industry 5.0

A Methodological Framework for Designing Personalised Training Programs to Support Personnel Upskilling in Industry 5.0

Performance of an Open-Source Large Language Model in Extracting Information from Free-Text Radiology Reports

Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution

Contact Info

Product

Resources

About