EUVIMEDEUVIMED entdecken
Crossref

Developing a Statistical Modeling‐Based Machine Learning Approach for Capturing Drug Dosing Using a Proton Pump Inhibitor Case

Amanda Massmann iD, Jordan F Baye iD, Max Weaver iD

Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy · 2026

DOI: 10.1002/phar.70083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 2026. Verfasst von Amanda Massmann und 2 weiteren Autor:innen. Beteiligte Einrichtung: Sanford Health, Sioux Falls, South Dakota, USA. Hauptthemen laut MEDLINE: Proton Pump Inhibitors, Machine Learning, Models, Statistical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop a statistical model to capture medication dosing for proton pump inhibitors (PPIs) using structured data from electronic health records (EHR).

Methods

Medication data for PPIs was extracted from a single health care system EHR to develop a statistical model. Nearly 20 years' worth of PPI prescriptions were extracted and 25% of unique dosing regimens were manually labeled by two clinical pharmacists. Several machine learning models were trained and evaluated to predict dose. Training was applied to 70% of the unique dosing regimens. The remaining unique dosing regimens were tested and validated with standard regression metrics: root mean squared error (RMSE) and R‐squared.

Results

A total of 17,271 distinct patients had orders for a PPI comprising 186,801 unique PPI orders. Distinct pairs built on medication descriptions and SIG combinations resulted in 10,739 unique entities. Clinical pharmacists manually labeled 2679 examples for medication entity extraction. Regression metrics (R‐squared, RMSE) were chosen as metrics to evaluate model performance. A stacked ensembled model proved to have the best results with a 0.09 RMSE and an R‐squared of 0.825.

Conclusion

The development of a statistical model to capture PPI dosing for both maintenance and complex dosing strategies was highly sensitive and accurate. A supervised learning prediction model helps overcome challenges in medication dosing identification by addressing concerns related to variability and complexity. Future strategies should focus on integrating unstructured data within the algorithm to further refine medication dosing capture.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Proton Pump InhibitorsMachine LearningModels, StatisticalHumansElectronic Health Records

Stichwörter der Autor:innen

algorithmselectronic health recordsnatural language processingneural networkspharmaceutical preparationsproton pump inhibitorsupervised machine learning

Substanzen

Proton Pump Inhibitors

Autor:innen und Institutionen

  • Sanford Health, Sioux Falls, South Dakota, USA.
  • Sanford School of Medicine, University of South Dakota, Vermillion, South Dakota, USA.
  • College of Pharmacy and Allied Health Professions, South Dakota State University, Brookings, South Dakota, USA.

ORCID-Profile: Amanda Massmann, Jordan F Baye, Max Weaver

Zitieren

APA

Massmann, A., Baye, J. F., & Weaver, M. (2026). Developing a Statistical Modeling‐Based Machine Learning Approach for Capturing Drug Dosing Using a Proton Pump Inhibitor Case. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy. https://doi.org/10.1002/phar.70083

Vancouver

Massmann A, Baye JF, Weaver M. Developing a Statistical Modeling‐Based Machine Learning Approach for Capturing Drug Dosing Using a Proton Pump Inhibitor Case. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy. 2026. doi:10.1002/phar.70083

BibTeX
@article{Massmann2026,
  author = {Massmann, Amanda and Baye, Jordan F and Weaver, Max},
  title = {Developing a Statistical Modeling‐Based Machine Learning Approach for Capturing Drug Dosing Using a Proton Pump Inhibitor Case},
  journal = {Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy},
  year = {2026},
  doi = {10.1002/phar.70083}
}
Kostenlos starten →