EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY-NC-ND 4.0

Electronic health record-based prediction models for dementia detection: a systematic review of model performance and quality

Alicia Lu iD, Velandai Srikanth, Sarah Westworth, Yue-Guang Baey, Chris Moran, Richard Beare, Kristy Siostrom, Nadine Andrew, Taya Collyer

Journal of the American Medical Informatics Association · 2026

DOI: 10.1093/jamia/ocag048 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of the American Medical Informatics Association, 2026. Verfasst von Alicia Lu und 8 weiteren Autor:innen. Beteiligte Einrichtung: National Centre for Healthy Ageing, Monash University and Peninsula Health, Frankston, VIC 3199, Australia. Hauptthemen laut MEDLINE: Electronic Health Records, Dementia, Models, Statistical. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Australian Government Research Training Program, Monash University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Leveraging routine electronic health records (EHR) for dementia detection is a growing field, but quality and clinical utility of existing models are unclear. This systematic review aimed to evaluate performance, methodological quality, and risk of bias of EHR-based dementia prediction models. Materials and Methods We systematically searched Medline, EMBASE, Scopus, IEEE Xplore, and ACM from conception until July 2024. All studies and grey literature describing development or validation of probabilistic prediction models using EHR data for dementia detection were included. Risk of bias was assessed using PROBAST.

Results

Fifty-six studies (434 prediction models, 155 external validations) were included. Most models were prognostic (66%), used US data (71%), relied solely on structured data, and 47 (11%) were externally validated. Modeled outcomes were extremely heterogeneous: gold-standard clinical criteria were used in 17 models (4%), with others reliant on diagnostic codes for case ascertainment. Discriminative metrics were frequently reported (82% of models), but calibration was rarely assessed (16%). All models were judged high risk of bias, driven by poor outcome definition, inadequate handling of missing data, and potential overfitting.

Discussion

Our review highlights significant issues with methodological rigor and reporting transparency in existing EHR dementia prediction models. Ambiguous outcomes, flawed case ascertainment, and incomplete performance reporting, all limit clinical usefulness. Overall, model performance was difficult to assess and compare across studies due to incomplete reporting.

Conclusion

Electronic health record-based dementia prediction is still in its infancy. Methodological rigor and interdisciplinary collaboration are essential to meet clinical needs and achieve real-world impact.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsDementiaModels, StatisticalHumansPrediction AlgorithmsPredictive Learning ModelsBias

Stichwörter der Autor:innen

dementiadiagnosiselectronic health recordsmachine learningpredictive learning models

Autor:innen und Institutionen

  • National Centre for Healthy Ageing, Monash University and Peninsula Health, Frankston, VIC 3199, Australia.
  • Peninsula Clinical School, School of Translational Medicine, Monash University, Frankston, VIC 3199, Australia.
  • Department of Geriatric Medicine, Peninsula Health, Mornington, VIC 3931, Australia.
  • Aged Care Department, Austin Health, Heidelberg, VIC 3084, Australia.
  • Department of Aged Care, Alfred Health, Caulfield, VIC 3162, Australia.
  • School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3004, Australia.

ORCID-Profile: Alicia Lu

Förderung

  • Australian Government Research Training Program
  • Monash University

Zitieren

APA

Lu, A., Srikanth, V., Westworth, S., Baey, Y. G., Moran, C., Beare, R., Siostrom, K., Andrew, N., & Collyer, T. (2026). Electronic health record-based prediction models for dementia detection: a systematic review of model performance and quality. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag048

Vancouver

Lu A, Srikanth V, Westworth S, Baey YG, Moran C, Beare R, et al. Electronic health record-based prediction models for dementia detection: a systematic review of model performance and quality. Journal of the American Medical Informatics Association. 2026. doi:10.1093/jamia/ocag048

BibTeX
@article{Lu2026,
  author = {Lu, Alicia and Srikanth, Velandai and Westworth, Sarah and Baey, Yue-Guang and Moran, Chris and Beare, Richard and Siostrom, Kristy and Andrew, Nadine and Collyer, Taya},
  title = {Electronic health record-based prediction models for dementia detection: a systematic review of model performance and quality},
  journal = {Journal of the American Medical Informatics Association},
  year = {2026},
  doi = {10.1093/jamia/ocag048}
}
Kostenlos starten →