EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Population-Level Digital Stroke Surveillance: Building a Fair and Accurate ICD-10 Detection Model

Charles Esenwa, Ava L Liberman, Natalie T Cheng, Joseph Dardick, Juan Felipe Daza-Ovalle, Daniel Labovitz, Jacqueline Lutz, Ciara Clancy, Kadija Ferryman

Cerebrovascular Diseases · 20.03.2026 · 1-7

DOI: 10.1159/000550393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cerebrovascular Diseases, online erschienen am 20.03.2026. Verfasst von Charles Esenwa und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Montefiore Health System, New York, New York, USA, cesenwa@montefiore.org. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The International Classification of Diseases, 10th Revision (ICD-10), is widely used for clinical care, quality assurance, and stroke research. Its ubiquity across healthcare systems makes it an attractive foundation for digital health tools that can support stroke surveillance and population health monitoring. However, a major limitation is that stroke detection algorithms derived from ICD codes have been developed primarily in socially homogenous populations, raising concerns about generalizability and fairness across racially diverse populations.

Methods

We developed and validated an acute ischemic stroke (AIS) detection algorithm using Classification and Regression Tree (CART) supervised machine learning, using a diverse derivation cohort. Input variables consisted of diagnostic and procedural ICD-10 codes, stratified by position and presence on admission. The model was trained on 75% and tested on 25% of the derivation cohort and externally validated in a second tertiary institution serving patients living in predominantly underrepresented and socially vulnerable communities. Performance of the algorithm was measured by sensitivity, specificity, positive predictive value (PPV), and Cohen’s κ. Subgroup analyses were conducted by sex and race/ethnicity.

Results

In the derivation cohort, the CART model achieved sensitivity of 96%, specificity of 90%, PPV of 99%, and κ = 0.78. Applied to the independent validation cohort, the algorithm identified 1,050 AIS cases and 1,664 non-AIS cases, with sensitivity 89%, specificity 95%, PPV of 92%, and κ = 0.84. Performance was comparable between women and men (κ = 0.80 for both), and strong across Black (κ = 0.81), Hispanic (κ = 0.76), and White (κ = 0.80) subgroups. Lower accuracy was observed in the Asian subgroup (κ = 0.73, PPV = 62%).

Conclusion

Our findings demonstrate that CART-based algorithms can provide accurate and interpretable AIS detection using ICD-10 data while explicitly addressing social fairness. The algorithm’s reproducibility across independent and diverse populations highlights its potential as a low-friction, scalable, and cost-efficient tool for clinical care, surveillance, and quality improvement. Importantly, subgroup analyses underscore the necessity of ongoing fairness evaluation as performance varied by race/ethnicity, particularly in the Asian subgroup. Limitations include potential missed cases in the gold standard, lack of confidence intervals due to retrospective data, and dependence on local coding practices. This study shows that ICD-10-based machine learning algorithms, specifically CART, can serve as a model for developing an accurate and equitable digital health platform for AIS surveillance.

Schlagwörter

Stichwörter der Autor:innen

Acute ischemic strokeInternational Classification of Disease-10Machine learning algorithmsRacial equity in healthcareStroke surveillance

Autor:innen und Institutionen

  • Department of Neurology, Montefiore Health System, New York, New York, USA, cesenwa@montefiore.org.
  • Department of Neurology, Weill Cornell Medicine, Cornell University, New York, New York, USA.
  • Department of Neurology and Neurosurgery, The Johns Hopkins Hospital, Johns Hopkins Medicine, Baltimore, Maryland, USA.
  • Department of Neurology, Montefiore Health System, New York, New York, USA.
  • Beats Medical, Dublin, Ireland.
  • Chobanian and Avedisian School of Medicine, Boston University, Boston, Massachusetts, USA.

Zitieren

APA

Esenwa, C., Liberman, A. L., Cheng, N. T., Dardick, J., Daza-Ovalle, J. F., Labovitz, D., Lutz, J., Clancy, C., & Ferryman, K. (2026). Population-Level Digital Stroke Surveillance: Building a Fair and Accurate ICD-10 Detection Model. Cerebrovascular Diseases, 1-7. https://doi.org/10.1159/000550393

Vancouver

Esenwa C, Liberman AL, Cheng NT, Dardick J, Daza-Ovalle JF, Labovitz D, et al. Population-Level Digital Stroke Surveillance: Building a Fair and Accurate ICD-10 Detection Model. Cerebrovascular Diseases. 2026:1-7. doi:10.1159/000550393

BibTeX
@article{Esenwa2026,
  author = {Esenwa, Charles and Liberman, Ava L and Cheng, Natalie T and Dardick, Joseph and Daza-Ovalle, Juan Felipe and Labovitz, Daniel and Lutz, Jacqueline and Clancy, Ciara and Ferryman, Kadija},
  title = {Population-Level Digital Stroke Surveillance: Building a Fair and Accurate ICD-10 Detection Model},
  journal = {Cerebrovascular Diseases},
  year = {2026},
  pages = {1--7},
  doi = {10.1159/000550393}
}
Kostenlos starten →