EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deterministic Overlapping Multimorbidity Phenotypes for Leakage-Safe EHR Modeling of Incident Cognitive Impairment in All of Us

Zahra Rahemi iD, Meisam Omidi iD

Journal of Interdisciplinary Research Applied to Medicine · 28.05.2026 · 6 (2) · 9

DOI: 10.3390/jdream6020009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Interdisciplinary Research Applied to Medicine, online erschienen am 28.05.2026. Verfasst von Zahra Rahemi und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Nursing, Clemson University, Clemson, SC 29634, USA. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIH HHS, University of North Texas Health Science Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

In electronic health record (EHR) research, multimorbidity is commonly represented by summary indices that may oversimplify disease co-occurrence or by unsupervised cluster labels that may lack stability across samples. This study evaluated a leakage-safe framework for deterministic, overlapping multimorbidity phenotyping.

Methods

Data from the All of Us Research Program were used to study 23,435 adults aged 50 years and older, anchored at their first SARS-CoV-2-positive test. Eleven pre-index Charlson component indicators were used as the binary baseline representation. Stable co-occurrence patterns were explored using association rule mining with bootstrap recurrence criteria. K-modes clustering was used as a discovery aid, while final phenotype membership was defined by deterministic rule functions.

Results

The framework produced three overlapping phenotype flags and a transparent 8-state overlap structure. The analytic cohort included 1462 incident cognitive impairment cases. Two phenotype flags were associated with higher odds of incident cognitive impairment. However, adding the phenotype flags to baseline models yielded only marginal improvements in discrimination.

Conclusions

The framework’s primary value lies in providing a reproducible, transparent, and overlap-aware representation of multimorbidity rather than in producing substantial predictive gains. This approach may support interpretable baseline phenotyping and leakage-safe modeling in real-world EHR studies.

Schlagwörter

Stichwörter der Autor:innen

association rule miningcognitive impairmentdeterministic rule functionselectronic health recordsk-modes clusteringleakage-safe modelingmultimorbidity phenotypingoverlap-aware representation

Autor:innen und Institutionen

  • School of Nursing, Clemson University, Clemson, SC 29634, USA.
  • School of Dentistry, Marquette University, Milwaukee, WI 53233, USA.

ORCID-Profile: Zahra Rahemi, Meisam Omidi

Förderung

  • NIA NIH HHS
  • NIH HHS
  • University of North Texas Health Science Center
  • National Institutes of Health
  • National Institute on Aging
  • Alzheimer’s Association

Zitieren

APA

Rahemi, Z., & Omidi, M. (2026). Deterministic Overlapping Multimorbidity Phenotypes for Leakage-Safe EHR Modeling of Incident Cognitive Impairment in All of Us. Journal of Interdisciplinary Research Applied to Medicine, 6(2), 9. https://doi.org/10.3390/jdream6020009

Vancouver

Rahemi Z, Omidi M. Deterministic Overlapping Multimorbidity Phenotypes for Leakage-Safe EHR Modeling of Incident Cognitive Impairment in All of Us. Journal of Interdisciplinary Research Applied to Medicine. 2026;6(2):9. doi:10.3390/jdream6020009

BibTeX
@article{Rahemi2026,
  author = {Rahemi, Zahra and Omidi, Meisam},
  title = {Deterministic Overlapping Multimorbidity Phenotypes for Leakage-Safe EHR Modeling of Incident Cognitive Impairment in All of Us},
  journal = {Journal of Interdisciplinary Research Applied to Medicine},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {9},
  doi = {10.3390/jdream6020009}
}
Kostenlos starten →