EUVIMEDEUVIMED entdecken
ValidierungsstudieMultizentrische StudieOpen Access

A Hybrid Rule-Based and Machine Learning–Based Clinical Decision Support System to Support Prescription Review: Development and External Validation Study

Jonghyun Jeong, Kyu-Nam Heo, A Jeong Kim, Jin Hee Baek, Yun Hee Jo, Sunghwan Kim, Mingi Jo, Young-Mi Ah, Ji Min Han, Sae Won Choi, Junho Song, Sangil Min und 1 weitere

Journal of Medical Internet Research · 23.09.2026 · 28 · e101202-e101202

DOI: 10.2196/101202 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Medical Internet Research, online erschienen am 23.09.2026. Verfasst von Jonghyun Jeong und 12 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmacy, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea, 82-2-3668-7472. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Machine Learning, Anticoagulants, Drug Prescriptions. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Anticoagulants are high-alert medications with substantial risk of serious bleeding, yet dosing and prescribing errors remain common. Although clinical decision support systems (CDSSs) can mitigate these errors, their impact is constrained by alert fatigue and limited interpretability.

Objective

We developed and validated a hybrid CDSS that integrates rule-based logic with machine learning to improve the safe use of anticoagulants.

Methods

This multicenter study used electronic health record data on anticoagulant prescriptions from 3 tertiary hospitals (1 for system development and internal validation and 2 for external validation). The hybrid CDSS combined a knowledge-based rule engine with a machine learning model trained to predict whether an anticoagulant prescription would require pharmacist intervention. The system was iteratively refined through pilot testing, internal validation, and external validation.

Results

A total of 75,200 anticoagulant prescriptions were used for model development. The final hybrid CDSS comprised 44 patient-specific rules and 1129 drug-drug interaction rules, combined with a CatBoost classifier (version 1.2.5; Yandex) for alert prioritization. During internal validation, 88 (18.9%) alerts were generated; all were technically correct; 88.6% (n=78) were deemed clinically relevant; 86.4% (n=76) were considered clinically useful; and 13.6% (n=12) required pharmacist intervention. In external validation across 2 hospitals, alert rates ranged from 22.6% (7/31) to 32.1% (310/966), with 18.8% (22/117) to 57.1% (4/7) of alerts requiring pharmacist intervention. The hybrid CDSS showed strong discrimination (area under the receiver operating characteristic curve 0.871‐0.963). No false negatives were identified, but the estimates should be interpreted cautiously given the short validation periods and limited number of intervention-requiring prescriptions.

Conclusions

A hybrid CDSS integrating rule-based logic with machine learning demonstrated high technical accuracy and clinical relevance across multiple institutions, suggesting its potential as a practical tool for supporting pharmacist-led anticoagulant prescription review.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalMachine LearningAnticoagulantsDrug PrescriptionsHumansBoosting Machine Learning AlgorithmsElectronic Health RecordsPredictive Learning Models

Stichwörter der Autor:innen

anticoagulantsclinical decision support systemelectronic health recordsmachine learningmedication errorspatient safety

Substanzen

Anticoagulants

Autor:innen und Institutionen

  • College of Pharmacy, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea, 82-2-3668-7472.
  • College of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National University, Seoul, Republic of Korea.
  • Department of Pharmacy, Seoul National University Hospital, Seoul, Republic of Korea.
  • ZerOne AI Inc, Seoul, Republic of Korea.
  • College of Pharmacy, Yeungnam University, Daegu, Republic of Korea.
  • College of Pharmacy, Chungbuk National University, Cheongju, Republic of Korea.

Zitieren

APA

Jeong, J., Heo, K. N., Kim, A. J., Baek, J. H., Jo, Y. H., Kim, S., Jo, M., Ah, Y. M., Han, J. M., Choi, S. W., Song, J., Min, S., & Lee, J. Y. (2026). A Hybrid Rule-Based and Machine Learning–Based Clinical Decision Support System to Support Prescription Review: Development and External Validation Study. Journal of Medical Internet Research, 28, e101202-e101202. https://doi.org/10.2196/101202

Vancouver

Jeong J, Heo KN, Kim AJ, Baek JH, Jo YH, Kim S, et al. A Hybrid Rule-Based and Machine Learning–Based Clinical Decision Support System to Support Prescription Review: Development and External Validation Study. Journal of Medical Internet Research. 2026;28:e101202-e101202. doi:10.2196/101202

BibTeX
@article{Jeong2026,
  author = {Jeong, Jonghyun and Heo, Kyu-Nam and Kim, A Jeong and Baek, Jin Hee and Jo, Yun Hee and Kim, Sunghwan and Jo, Mingi and Ah, Young-Mi and Han, Ji Min and Choi, Sae Won and Song, Junho and Min, Sangil and Lee, Ju-Yeun},
  title = {A Hybrid Rule-Based and Machine Learning–Based Clinical Decision Support System to Support Prescription Review: Development and External Validation Study},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e101202--e101202},
  doi = {10.2196/101202}
}
Kostenlos starten →