EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Implementation of Duke Machine Learning Data Quality Assurance Framework in a Pakistani Healthcare Institution

Zarmeen Nasim iD, Nida Saddaf Khan, Mark Sendak, Khalid Aziz iD, Salma Tajuddin, Haroon Khan, Maaha Ayub, Mohummad Hassan Raza Raja, Mushyada Ali, Jee Young Kim, Henry David Jeffry Hogg, Alifia Hasan und 3 weitere

Health Informatics Journal · 2026

DOI: 10.1177/14604582261486769 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Health Informatics Journal, 2026. Verfasst von Zarmeen Nasim und 14 weiteren Autor:innen. Beteiligte Einrichtung: CITRIC Health Data Science Centre, Aga Khan University, Karachi, Pakistan. Hauptthemen laut MEDLINE: Machine Learning, Quality Assurance, Health Care, Data Accuracy. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Patrick J. McGovern Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

High-quality data are critical for developing healthcare machine learning (ML) models yet remain a major challenge in low- and middle-income countries (LMICs). This study evaluated the applicability of the Duke Institute for Health Innovation’s (DIHI) Machine Learning Data Quality Assurance (ML-DQA) framework in an LMIC setting using two ML projects at a tertiary care hospital in Pakistan.

Methods

We applied the ML-DQA framework to two ML projects, Sepsis Watch (SW) and In-hospital Mortality Prediction (IMP). The framework comprises four phases: pre-DQA, data element pre-processing, ML-DQA checks, and ML-DQA adjudication, and was used to evaluate data quality and usability for both models.

Results

In the pre-DQA phase, required data elements were identified through consultation with clinicians and project teams. During data element pre-processing, transformations and harmonization were performed, including consolidation of differently labelled glucose variables. ML-DQA checks assessed plausibility, conformance, and completeness, identifying elements that met quality standards. In the adjudication phase, reports were reviewed by two independent clinicians to determine suitability for model development.

Conclusions

The Duke ML-DQA framework effectively identified data limitations and informed model development, demonstrating its utility for assessing data quality and supporting ML implementation in resource-constrained settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningQuality Assurance, Health CareData AccuracyPakistanHumans

Stichwörter der Autor:innen

ML-DQA frameworkartificial intelligencedata quality assurancedigital health infrastructurehealth data qualitylow middle-income countriesmachine learning

Autor:innen und Institutionen

  • CITRIC Health Data Science Centre, Aga Khan University, Karachi, Pakistan.
  • McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX, USA.
  • The University of Texas MD Anderson Cancer Centre, Houston, TX, USA.
  • Duke Institute for Health Innovation, Duke University School of Medicine, Durham, NC, USA.
  • Chief Medical Information Office, Aga Khan University, Karachi, Pakistan.
  • Department of Medicine, Aga Khan University, Karachi, Pakistan.

ORCID-Profile: Zarmeen Nasim, Khalid Aziz

Förderung

  • Patrick J. McGovern Foundation

Zitieren

APA

Nasim, Z., Khan, N. S., Sendak, M., Aziz, K., Tajuddin, S., Khan, H., Ayub, M., Raza Raja, M. H., Ali, M., Kim, J. Y., Hogg, H. D. J., Hasan, A., Balu, S., Hoodbhoy, Z., & Samad, Z. (2026). Implementation of Duke Machine Learning Data Quality Assurance Framework in a Pakistani Healthcare Institution. Health Informatics Journal. https://doi.org/10.1177/14604582261486769

Vancouver

Nasim Z, Khan NS, Sendak M, Aziz K, Tajuddin S, Khan H, et al. Implementation of Duke Machine Learning Data Quality Assurance Framework in a Pakistani Healthcare Institution. Health Informatics Journal. 2026. doi:10.1177/14604582261486769

BibTeX
@article{Nasim2026,
  author = {Nasim, Zarmeen and Khan, Nida Saddaf and Sendak, Mark and Aziz, Khalid and Tajuddin, Salma and Khan, Haroon and Ayub, Maaha and Raza Raja, Mohummad Hassan and Ali, Mushyada and Kim, Jee Young and Hogg, Henry David Jeffry and Hasan, Alifia and Balu, Suresh and Hoodbhoy, Zahra and Samad, Zainab},
  title = {Implementation of Duke Machine Learning Data Quality Assurance Framework in a Pakistani Healthcare Institution},
  journal = {Health Informatics Journal},
  year = {2026},
  doi = {10.1177/14604582261486769}
}
Kostenlos starten →