How to Overcome Lack of Health Record Data and Privacy Obstacles in Initial Phases of Medical Data Analysis Projects

keywords: Health record, FHIR, HL7, home care, machine learning, Questionnaire, QuestionnaireResponse, Synthea™
The lack of electronic health record data in general and especially at initial phases of medical research projects is common and is one of the main reasons for delay or failure of such projects. One of the health areas with little attention is the home care area, where patients are being supported by their families or informal caregiver at home. In this paper we present related work on medical data formats and synthetical data generation of medical health records. Furthermore, it presents an approach to generate synthetic electronic health records (HER) that are readily available; suited to research; and free of legal, privacy, security and intellectual property restrictions to be used in home care research projects. We adapted and used Synthea™, an open-source software framework that simulates the lifespans of synthetic patients to generate synthetic EHRs. This paper presents the use case of home care from the capturing of user requirements of home care patients, translating the requirements into a data model, feeding the data model into Synthea™ framework, which produces synthetical health data records mainly as QuestionnaireResponse instance of the Fast Healthcare Interoperability Resources (FHIR) to using these EHRs to build an initial machine learning data model for home care.
reference: Vol. 41, 2022, No. 1, pp. 233–252