EUVIMEDObjevte EUVIMED
Open access

Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes

Feiqing Huang iD, Jue Hou iD, Ningxuan Zhou iD, Kimberly Greco iD, Chenyu Lin iD, Sara Morini Sweet iD, Jun Wen iD, Lechen Shen iD, Nicolas Gonzalez iD, Sinian Zhang iD, Katherine P Liao iD, Tianrun Cai iD and 3 more

Journal of Medical Internet Research · 2025-05-12 · 27 · e71873

DOI: 10.2196/71873 ↗

At a glance

Journal article in Journal of Medical Internet Research, published online on 2025-05-12. Written by Feiqing Huang and 14 co-authors. Institution: Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, United States. Major MEDLINE topics: Electronic Health Records. Cited 10 times so far (Crossref); 45 references. The full text is freely available in PubMed Central. Funded by: NINDS NIH HHS, FDA HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Managing chronic diseases requires ongoing monitoring of disease activity and therapeutic responses to optimize treatment plans. With the growing availability of disease-modifying therapies, it is crucial to investigate comparative effectiveness and long-term outcomes beyond those available from randomized clinical trials. We introduce a comprehensive pipeline for generating reproducible and generalizable real-world evidence on disease outcomes by leveraging electronic health record data. The pipeline first generates scalable disease outcomes by linking electronic health record data with registry data containing a small sample of labeled outcomes. It then applies causal analysis using these scalable outcomes to evaluate therapies for chronic diseases. The implementation of the pipeline is illustrated in a case study based on multiple sclerosis. Our approach addresses challenges in real-world evidence generation for disease activity of chronic conditions, specifically the lack of direct observations on key outcomes and biases arising from imperfect or incomplete data. We present advanced machine learning techniques such as semisupervised and ensemble methods to impute missing outcome data, further incorporating steps for calibrated causal analyses and bias correction.

Subjects

MeSH terms (MEDLINE)

Electronic Health RecordsHumansChronic DiseaseMultiple SclerosisMachine LearningLongitudinal Studies

Author keywords

calibrationcausal inferencechronic disease outcomesdata imputationelectronic health recordslongitudinal disease activitymachine learningreal-world evidence

Authors and institutions

  • Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, United States.
  • Harvard-MIT Center for Regulatory Science, Harvard Medical School, Boston, MA, United States.
  • Division of Biostatistics and Health Data Science, School of Public Health, University of Minnesota, Minneapolis, MN, United States.
  • Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States.
  • Department of Engineering, University of Toronto, Toronto, ON, Canada.
  • Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, Boston, MA, United States.

ORCID profiles: Feiqing Huang, Jue Hou, Ningxuan Zhou, Kimberly Greco, Chenyu Lin, Sara Morini Sweet, Jun Wen, Lechen Shen, Nicolas Gonzalez, Sinian Zhang, Katherine P Liao, Tianrun Cai, Zongqi Xia, Florence T Bourgeois, Tianxi Cai

Funding

  • NINDS NIH HHS
  • FDA HHS

Cite

APA

Huang, F., Hou, J., Zhou, N., Greco, K., Lin, C., Sweet, S. M., Wen, J., Shen, L., Gonzalez, N., Zhang, S., Liao, K. P., Cai, T., Xia, Z., Bourgeois, F. T., & Cai, T. (2025). Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes. Journal of Medical Internet Research, 27, e71873. https://doi.org/10.2196/71873

Vancouver

Huang F, Hou J, Zhou N, Greco K, Lin C, Sweet SM, et al. Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes. Journal of Medical Internet Research. 2025;27:e71873. doi:10.2196/71873

BibTeX
@article{Huang2025,
  author = {Huang, Feiqing and Hou, Jue and Zhou, Ningxuan and Greco, Kimberly and Lin, Chenyu and Sweet, Sara Morini and Wen, Jun and Shen, Lechen and Gonzalez, Nicolas and Zhang, Sinian and Liao, Katherine P and Cai, Tianrun and Xia, Zongqi and Bourgeois, Florence T and Cai, Tianxi},
  title = {Advancing the Use of Longitudinal Electronic Health Records: Tutorial for Uncovering Real-World Evidence in Chronic Disease Outcomes},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e71873},
  doi = {10.2196/71873}
}
Start for free →