EUVIMEDEUVIMED entdecken
Crossref

LinkMD: Linking Medical and Dental Records with 4 Linking Algorithms

J S Patel iD, E Dinh

Journal of Dental Research · 2026

DOI: 10.1177/00220345251383863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Dental Research, 2026. Verfasst von J S Patel und 1 weiteren Autor:innen. Beteiligte Einrichtung: Center for Artificial Intelligence, Data Science, and Informatics, Department of Oral Health Sciences, Artificial Intelligence, Data Science, and Inf…. Hauptthemen laut MEDLINE: Algorithms, Electronic Health Records, Dental Records, Medical Record Linkage. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite well-established connections between oral and systemic health, electronic health records (EHRs) and electronic dental records (EDRs) remain largely siloed due to infrastructural and interoperability challenges. This separation limits interdisciplinary care and data-driven research to generate practice-based evidence. We developed and validated 4 algorithmic frameworks specifically designed to link EHR with EDR across nonintegrated systems. Using data from more than 1.7 million medical records and 222,480 dental records spanning a 10-y period at Temple University, we evaluated 4 linkage strategies: (1) direct Social Security number matching, (2) unweighted similarity scoring, (3) weighted average similarity scoring, and (4) a probabilistic expectation-conditional maximization classification model. We compared these approaches using expert-reviewed validation of 1,000 candidate record pairs and selected optimal similarity thresholds for high-fidelity linkages. Our weighted average similarity algorithm demonstrated the best performance with 100% specificity (correctly avoiding false matches), 99% sensitivity (correctly identifying all true matches), and 99% accuracy (proportion of all correct linkages out of total comparisons) at the threshold of 0.82 for successfully linking 121,771 unique patients and 144,229 patients’ linkage with 96% sensitivity, 78% specificity, and 89% accuracy. After linking the datasets, the completeness of key patient demographic information significantly improved, with missing race data reduced from 79% to 11% and missing ethnicity data from 82% to 17%. We designed the algorithm to be transparent and vendor neutral, making it potentially adaptable to any institution or practice regardless of their existing EHR/EDR systems. This provides a foundation for developing a clinical decision support systems that facilitate real-time health information exchange, supporting safer dental procedures, timely medical referrals, and integrative research. Our findings provide a critical bridge between medicine and dentistry, which have remained largely divorced from each other. Future work will focus on multi-institutional validation, implementation, and integration into routine clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsElectronic Health RecordsDental RecordsMedical Record LinkageHumans

Stichwörter der Autor:innen

artificial intelligencebig datadata linkagehealth information exchangehealth information interoperabilityinformatics

Autor:innen und Institutionen

  • Center for Artificial Intelligence, Data Science, and Informatics, Department of Oral Health Sciences, Artificial Intelligence, Data Science, and Informatics School of Dentistry, Philadelphia, PA, USA.
  • Knight Campus for Accelerating Scientific Impact, University of Oregon, Eugene, OR, USA.

ORCID-Profile: J S Patel

Zitieren

APA

Patel, J. S., & Dinh, E. (2026). LinkMD: Linking Medical and Dental Records with 4 Linking Algorithms. Journal of Dental Research. https://doi.org/10.1177/00220345251383863

Vancouver

Patel JS, Dinh E. LinkMD: Linking Medical and Dental Records with 4 Linking Algorithms. Journal of Dental Research. 2026. doi:10.1177/00220345251383863

BibTeX
@article{Patel2026,
  author = {Patel, J S and Dinh, E},
  title = {LinkMD: Linking Medical and Dental Records with 4 Linking Algorithms},
  journal = {Journal of Dental Research},
  year = {2026},
  doi = {10.1177/00220345251383863}
}
Kostenlos starten →