EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions

Thomas Petit-Jean iD, Christel Gérardin iD, Emmanuelle Berthelot iD, Gilles Chatellier iD, Marie Frank iD, Xavier Tannier iD, Emmanuelle Kempf iD, Romain Bey iD

Journal of the American Medical Informatics Association · 20.05.2024 · 31 (6) · 1280-1290

DOI: 10.1093/jamia/ocae069 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 04.04.2024. Verfasst von Thomas Petit-Jean und 7 weiteren Autor:innen. Beteiligte Einrichtung: Innovation and Data Unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, 75012, France. Hauptthemen laut MEDLINE: Natural Language Processing, Electronic Health Records, Workflow, Machine Learning. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AP-HP Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop and validate a natural language processing (NLP) pipeline that detects 18 conditions in French clinical notes, including 16 comorbidities of the Charlson index, while exploring a collaborative and privacy-enhancing workflow. Materials and Methods The detection pipeline relied both on rule-based and machine learning algorithms, respectively, for named entity recognition and entity qualification, respectively. We used a large language model pre-trained on millions of clinical notes along with annotated clinical notes in the context of 3 cohort studies related to oncology, cardiology, and rheumatology. The overall workflow was conceived to foster collaboration between studies while respecting the privacy constraints of the data warehouse. We estimated the added values of the advanced technologies and of the collaborative setting.

Results

The pipeline reached macro-averaged F1-score positive predictive value, sensitivity, and specificity of 95.7 (95%CI 94.5-96.3), 95.4 (95%CI 94.0-96.3), 96.0 (95%CI 94.0-96.7), and 99.2 (95%CI 99.0-99.4), respectively. F1-scores were superior to those observed using alternative technologies or non-collaborative settings. The models were shared through a secured registry.

Conclusions

We demonstrated that a community of investigators working on a common clinical data warehouse could efficiently and securely collaborate to develop, validate and use sensitive artificial intelligence models. In particular, we provided an efficient and robust NLP pipeline that detects conditions mentioned in clinical notes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingElectronic Health RecordsWorkflowMachine LearningHumansData WarehousingAlgorithmsFranceConfidentiality

Stichwörter der Autor:innen

Charlson score indexcomorbiditiesdomain adaptationnatural language processingprivacy

Autor:innen und Institutionen

  • Innovation and Data Unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, 75012, France.
  • Institut Pierre-Louis d'Epidémiologie et de Santé Publique, INSERM, Sorbonne Université, Paris, 75012, France.
  • Department of Cardiology, Hôpital Bicêtre, Assistance Publique-Hôpitaux de Paris, Le Kremlin Bicêtre, 94270, France.
  • Department of Medical Informatics, Assistance Publique-Hôpitaux de Paris, Centre-Université de Paris (APHP-CUP), Université de Paris, Paris, 75015, France.
  • Department of Medical Informatics, Hôpitaux Universitaires Paris-Saclay, Assistance Publique-Hôpitaux de Paris, Le Kremlin-Bicêtre, 94270, France.
  • Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances pour la e-Santé (LIMICS), INSERM, Université Sorbonne Paris Nord, Sorbonne Université, Paris, 75005, France.

ORCID-Profile: Thomas Petit-Jean, Christel Gérardin, Emmanuelle Berthelot, Gilles Chatellier, Marie Frank, Xavier Tannier, Emmanuelle Kempf, Romain Bey

Förderung

  • AP-HP Foundation

Zitieren

APA

Petit-Jean, T., Gérardin, C., Berthelot, E., Chatellier, G., Frank, M., Tannier, X., Kempf, E., & Bey, R. (2024). Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions. Journal of the American Medical Informatics Association, 31(6), 1280-1290. https://doi.org/10.1093/jamia/ocae069

Vancouver

Petit-Jean T, Gérardin C, Berthelot E, Chatellier G, Frank M, Tannier X, et al. Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions. Journal of the American Medical Informatics Association. 2024;31(6):1280-1290. doi:10.1093/jamia/ocae069

BibTeX
@article{PetitJean2024,
  author = {Petit-Jean, Thomas and Gérardin, Christel and Berthelot, Emmanuelle and Chatellier, Gilles and Frank, Marie and Tannier, Xavier and Kempf, Emmanuelle and Bey, Romain},
  title = {Collaborative and privacy-enhancing workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions},
  journal = {Journal of the American Medical Informatics Association},
  year = {2024},
  volume = {31},
  number = {6},
  pages = {1280--1290},
  doi = {10.1093/jamia/ocae069}
}
Kostenlos starten →