Skip to content
Review Open access

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

Sep 2026 · Journal of Medical Internet Research · Vol 28 · 0 citations · 28 references
Medicine

TL;DR

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.

Abstract

Abstract 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.

Read PDF

Similar papers

Review Open access Sep 2026

Machine learning models in clinical decision support systems: a scoping review

Machine learning (ML) has increasingly been integrated into clinical decision support systems (CDSS) to improve diagnostic accuracy and clinical decision-making. However, variability in performance, adoption, and implementation across healthcare settings necessitates comprehensive evidence synthesis. This scoping revie...

D. C. Innocent, R. C. Innocent, Increase Praise Innocent · 0 citations
Open access Aug 2026

Hybrid Rule-Based and Machine Learning Architecture for Reducing Alert Fatigue in Clinical Decision Support Systems

Clinical decision support systems operating in hospital environments generate large numbers of alerts based on continuously monitored clinical data. A major challenge in such systems is alert fatigue, caused by excessive numbers of notifications and unnecessary escalation of alert severity, which may reduce clinicians’...

A. Werner, Aldona Rosner, Joanna Żywiec et al. · 0 citations
Open access 2026

A Percentile Rank-Based Multi-Criteria Decision-Making Algorithm for Interpretable Hypertension Risk Stratification in Clinical Decision Support Systems

Hypertension risk prediction remains a critical challenge in data-driven healthcare systems, particularly in low- and middle-income countries (LMICs). In many of these settings, timely monitoring and diagnosis remain difficult. Machine learning (ML) methods have been applied for hypertension risk prediction; however, t...

Atabo Onuche Gideon, Barka Piyinkir Ndahi, Idoko Daniel Jonah · 0 citations
Open access Aug 2026

Development and Evaluation of an Explainable AI-Driven Decision Support System for Clinical and Operational Healthcare Management

Healthcare organizations need to have an integrated decision-support system that can enhance patient risk assessment and optimize their use of resources. But the lack of transparency and separation between the use of AI in clinical use and administrative applications puts adoption challenges in the way.Conceive and eva...

P. B · 0 citations
Open access Aug 2026

An Interpretable Machine Learning Framework with Clinical Nomogram for Predicting In-Hospital Mortality in Acute Ischemic Stroke Using High-Granularity Bedside Data.

BACKGROUND This multicenter study developed and validated an interpretable machine learning model integrating granular nursing and emergency department data collected within the first 24 hours to predict in-hospital mortality in acute ischemic stroke (AIS). METHODS We analyzed a retrospective cohort of 5,014 adult AI...

Guo-Ying Li, Chan Gong · 0 citations
Open access Aug 2026

Enhancing Cardiovascular Disease Diagnosis With Data-Driven Predictive Systems

The proposed approach uses a Quantum Neural Network for machine learning for machine learning in an intelligent Cardiovascular Disease (CVD) prediction system that has the highest sensitivity and specificity in the current literature, matching exact expert opinions.

Hutashani B. Rayate, M. Nikose, P. Burade · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.