EUVIMEDEUVIMED entdecken
Open Access

Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data

Kazuki Yoshida iD, Tianrun Cai, Lily G Bessette, Erin Kim, Su Been Lee, Luke E Zabotka, Alec Sun, Julianna M Mastrorilli, Theresa A Oduol, Jun Liu, Daniel H Solomon iD, Seoyoung C Kim und 2 weitere

Pharmacoepidemiology and Drug Safety · 2024

DOI: 10.1002/pds.5684 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacoepidemiology and Drug Safety, 2024. Verfasst von Kazuki Yoshida und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Gout. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIAMS NIH HHS, National Institute of Arthritis and Musculoskeletal and Skin Diseases.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

We aimed to determine whether integrating concepts from the notes from the electronic health record (EHR) data using natural language processing (NLP) could improve the identification of gout flares.

Methods

Using Medicare claims linked with EHR, we selected gout patients who initiated the urate‐lowering therapy (ULT). Patients' 12‐month baseline period and on‐treatment follow‐up were segmented into 1‐month units. We retrieved EHR notes for months with gout diagnosis codes and processed notes for NLP concepts. We selected a random sample of 500 patients and reviewed each of their notes for the presence of a physician‐documented gout flare. Months containing at least 1 note mentioning gout flares were considered months with events. We used 60% of patients to train predictive models with LASSO. We evaluated the models by the area under the curve (AUC) in the validation data and examined positive/negative predictive values (P/NPV).

Results

We extracted and labeled 839 months of follow‐up (280 with gout flares). The claims‐only model selected 20 variables (AUC = 0.69). The NLP concept‐only model selected 15 (AUC = 0.69). The combined model selected 32 claims variables and 13 NLP concepts (AUC = 0.73). The claims‐only model had a PPV of 0.64 [0.50, 0.77] and an NPV of 0.71 [0.65, 0.76], whereas the combined model had a PPV of 0.76 [0.61, 0.88] and an NPV of 0.71 [0.65, 0.76].

Conclusion

Adding NLP concept variables to claims variables resulted in a small improvement in the identification of gout flares. Our data‐driven claims‐only model and our combined claims/NLP‐concept model outperformed existing rule‐based claims algorithms reliant on medication use, diagnosis, and procedure codes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GoutAgedHumansUnited StatesNatural Language ProcessingElectronic Health RecordsMedicareSymptom Flare UpAlgorithms

Stichwörter der Autor:innen

goutnatural language processing

Autor:innen und Institutionen

  • Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
  • Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA.
  • Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
  • Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.

ORCID-Profile: Kazuki Yoshida, Daniel H Solomon

Förderung

  • NIAMS NIH HHS
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases

Zitieren

APA

Yoshida, K., Cai, T., Bessette, L. G., Kim, E., Lee, S. B., Zabotka, L. E., Sun, A., Mastrorilli, J. M., Oduol, T. A., Liu, J., Solomon, D. H., Kim, S. C., Desai, R. J., & Liao, K. P. (2024). Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data. Pharmacoepidemiology and Drug Safety. https://doi.org/10.1002/pds.5684

Vancouver

Yoshida K, Cai T, Bessette LG, Kim E, Lee SB, Zabotka LE, et al. Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data. Pharmacoepidemiology and Drug Safety. 2024. doi:10.1002/pds.5684

BibTeX
@article{Yoshida2024,
  author = {Yoshida, Kazuki and Cai, Tianrun and Bessette, Lily G and Kim, Erin and Lee, Su Been and Zabotka, Luke E and Sun, Alec and Mastrorilli, Julianna M and Oduol, Theresa A and Liu, Jun and Solomon, Daniel H and Kim, Seoyoung C and Desai, Rishi J and Liao, Katherine P},
  title = {Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data},
  journal = {Pharmacoepidemiology and Drug Safety},
  year = {2024},
  doi = {10.1002/pds.5684}
}
Kostenlos starten →