EHR-Independent Predictive Decision Support Architecture Based on OMOP

Abstract

Background The increasing availability of molecular and clinical data of cancer patients combined with novel machine learning techniques has the potential to enhance clinical decision support, example, for assessing a patient's relapse risk. While these prediction models often produce promising results, a deployment in clinical settings is rarely pursued. Objectives In this study, we demonstrate how prediction tools can be integrated generically into a clinical setting and provide an exemplary use case for predicting relapse risk in melanoma patients. Methods To make the decision support architecture independent of the electronic health record (EHR) and transferable to different hospital environments, it was based on the widely used Observational Medical Outcomes Partnership (OMOP) common data model (CDM) rather than on a proprietary EHR data structure. The usability of our exemplary implementation was evaluated by means of conducting user interviews including the thinking-aloud protocol and the system usability scale (SUS) questionnaire. Results An extract-transform-load process was developed to extract relevant clinical and molecular data from their original sources and map them to OMOP. Further, the OMOP WebAPI was adapted to retrieve all data for a single patient and transfer them into the decision support Web application for enabling physicians to easily consult the prediction service including monitoring of transferred data. The evaluation of the application resulted in a SUS score of 86.7. Conclusion This work proposes an EHR-independent means of integrating prediction models for deployment in clinical settings, utilizing the OMOP CDM. The usability evaluation revealed that the application is generally suitable for routine use while also illustrating small aspects for improvement.

PCaGuard: A Software Platform to Support Optimal Management of Prostate Cancer

“…In the era of colorectal cancer, Becker et al have evaluated an open-source workflow system based on business process model and notation (BPMN) with unified medical language system (UMLS) for colorectal cancer screening. 38 Since electronic health records (EHRs) contain more and more data, researchers develop methods to extract characteristics either from data 39,40 or scanned and other outside documents contained in EHRs. 41 In the market, data management systems available clinical, such as REDCap, OpenClinica, and eClinicalOS, but these systems are either commercial or not suitable for this project because the whole workflow is time consuming, error prone, and requires the integration of different components.…”

The Usage of OHDSI OMOP – A Scoping Review

“…We identified 10 publications from German author teams but none of them is related to a clinical study based on observational patient data with a medical background [10,11,[17][18][19][20][21][22][23][24]. All of them are related to mapping issues, architectural concepts or tool development based on OMOP.…”

Untitled

“…Also, CDS interventions supported specialized services in the emergency department, geriatric wards, trauma units, and other units. [9][10][11][15][16][17][18][19]21,22 These findings suggest that CDS is supporting specialized and decentralized pharmacists' roles in a variety of clinical domains in hospital departments.…”

“…[5][6][7] CDS can be developed and refined through clinician observations, suggestions, and preferences. [8][9][10] Some examples of CDS include passively providing clinicians with helpful information without interrupting their workflow or process, such as order facilitators (e.g., order sets and default settings), relevant information displays (e.g., info-buttons and links to additional resources), and even in-line displays of information (e.g., allergy or dose alerts). 11 CDS also includes active or interruptive alerting, such as hard-stop alerts and reminders.…”