Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
A Configurable Clinical Decision Support System for Model-Informed Precision Dosing: System Architecture and Operational Principles
ABSTRACT
Background:
Therapeutic Drug Monitoring (TDM) supports individualized pharmacotherapy, yet its implementation in routine care remains limited by operational constraints, data quality issues, and the need for expert interpretation. Model-Informed Precision Dosing (MIPD) addresses several of these limitations through population pharmacokinetic modeling and Bayesian forecasting, but its effective deployment in clinical practice still requires human TDM experts.
Objective:
This paper presents Tucuxi‑CDSS, a configurable and open-source Clinical Decision Support System (CDSS) designed to enable safe, standardized, and automated MIPD-guided dose individualization, with a particular focus on safeguarding against pre-analytical and data-entry errors.
Methods:
We detail Tucuxi-CDSS system architecture, data validation workflow, decision logic, and configuration mechanisms, with a particular focus on safeguarding against pre-analytical and data-entry errors. The system is built around extensive configurability through XML-based drug files, language files, and reporting templates. Verification was performed through unit testing and system-level tests, while validation was conducted by comparing CDSS outputs against those of a human TDM expert in an in-silico study.
Results:
The resulting system supports end-to-end MIPD workflows, from data import and automated error detection through dosage adaptation and clinical report generation. A pilot deployment for rifampicin dosing optimization in routine tuberculosis care is currently underway in Tanzania, and an illustrative use case with imatinib demonstrates the system's covariate handling and reporting capabilities. We also briefly present the results of the validation test where we compare its effectiveness against a human TDM expert in an in-silico study.
Conclusions:
Tucuxi‑CDSS provides a modular, extensible, and open-source platform capable of delivering expert-level TDM oversight in settings where trained pharmacologists are scarce. Its performance evaluation against a TDM expert is presented in a companion paper and supports future prospective studies on CDSS adoption in clinical practice.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.