Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Mar 17, 2022
Date Accepted: Jul 10, 2022
(closed for review but you can still tweet)
Development of an Interoperable and Easily Transferable Clinical Decision Support System Deployment Platform: System Design, and Development Studies
ABSTRACT
Background:
The clinical decision support system (CDSS) is known as a technology that enhances clinical efficacy and safety. However, it has not fulfilled its potential benefit, mainly due to clinical data standard and non-interoperable platform.
Objective:
In this paper, we introduce the common data model-based intelligent algorithm network environment (CANE) platform that supports the implementation and deployment of CDSS.
Methods:
CDSS’s reasoning engines, usually represented as R or Python objects, are deployed into the CANE platform and converted to C# objects. When a clinician requests CANE decision support in the electronic health record system, patients’ information is transformed to the Health Level 7 fast healthcare interoperability resources format and transmitted to the CANE server inside the hospital firewall. Upon receiving the necessary data, the CANE system modules perform the following tasks: 1) the preprocessing module converts the fast healthcare interoperability resources into input data required by the specific reasoning engine; 2) the reasoning engine module operates the target algorithms; 3) the integration module communicates with the other institutions’ CANE system to request and transmit a summary report to aid in decision support, and it creates a user interface by integrating the summary report and the results calculated by the reasoning engine.
Results:
We developed CANE system that the any algorithms mounted in the system can be directly called through the RESTful API when it integrated with an EMR system. Eight algorithms were developed and deployed in the CANE system. As one of the knowledge-based algorithms, physician can screen patients who suspected as a sepsis and also get treatment guides for sepsis patients by using CANE system. Also, as a one example of non-knowledge-based algorithms, CANE system supports emergency physician' clinical decision about optimum resource allocation by predicting patient's acuity and prognosis at triage stage.
Conclusions:
In this paper, we successfully developed the common data model-based platform that adhere to medical informatics standards and programming language neutral. This system could contribute improving clinical practice by supporting the deployment of various CDSS into real clinical practice.
Citation
