Generating Enriched Synthetic German Hospital Claims Data - A Use Case Driven Approach.

Clinical data and above all individual patient data are highly sensitive. All the more it is important to protect these critical information while analyzing and exploring their specifics for further research. However, in order to enable students and other researchers to develop decision support systems and to use modern data analysis methods such as intelligent pattern recognition, the provision of clinical data is essential. In order to allow this while completely protecting the privacy of a patient, we present a mixed approach to generate semantically and clinically realistic data: (1) We use available synthetic data, extract information on patient visits and diagnoses and adapt them to the encoding systems of German claims data; (2) based on a statistical analysis of real German hospital data, we identify distributions of procedures, laboratory data and other measurements and transfer them to the synthetic patient's visits and diagnoses in a semi-automated way. This enabled us to provide students a data set that is as semantically and clinically realistic as possible to apply patient-level prediction algorithms within the development of clinical decision support systems without putting patient data at any risk.

[Evaluation of a future scenario concerning the use of big data applications to improve the care of people with rare diseases]. / Evaluation eines Zukunftsszenarios zur Nutzung von Big-Data-Anwendungen für die Verbesserung der Versorgung von Menschen mit seltenen Erkrankungen.

INTRODUCTION: In Germany there are about 4 million people living with a rare disease. Studies have shown that big data applications can improve diagnosis of and research on rare diseases more effectively. However, no concrete comprehensive concept for the use of big data in the care of people with rare diseases has so far been established in Germany. As part of the project "BIDA-SE", which is funded by the German Ministry of Health, a first scenario has been designed to show how big data applications can be usefully incorporated into the care of people with rare diseases. METHODS: The aim of the present study was to evaluate this scenario with regard to acceptance, (clinical) benefits, economic aspects, and limitations and barriers to its implementation. To evaluate the scenario, an online survey was conducted in Germany in October/November 2019 amongst a total of N = 9 physicians, N = 69 patients with rare diseases/patient representatives, N = 14 IT experts and N = 21 health care researchers. The online questionnaire consisted of both standardized, validated questions taken from already tested survey instruments and additional questions which were constructed on the basis of a preceding literature analysis. The evaluation of the survey was primarily descriptive, with a calculation of frequencies, mean values and standard deviations. RESULTS: The results of the evaluation show that the scenario has been accepted by a majority of all groups surveyed (physicians, patients/patient representatives, IT experts and health care researchers). From the point of view of physicians, patients/patient representatives and health care researchers, the scenario has the potential to accelerate the diagnosis and initiation of therapy and to improve cross-sectoral treatment. From the physician's and health care researcher's perspective, investments in the application presented in the scenario would be profitable. Financing the scenario would, however, require adjusting the reimbursement situation. The limitations and barriers identified by all groups for a medium-term implementation of the scenario can be grouped into seven thematic areas where action is needed: (1) financing and investment, (2) data protection and data security, (3) standards/data sources/data quality, (4) acceptance of technology, (5) integration into the daily work routine, (6) knowledge about availability as well as (7) habits and preferences/physician's role. DISCUSSION: With the present study, a first interdisciplinary, practical scenario using big data applications was evaluated with regard to acceptance, benefits and limitations/barriers. The scenario is widely accepted among the majority of all surveyed target groups and is considered (clinically) useful, although legal, organisational and technical barriers still need to be overcome for its medium-term implementation. The evaluation results contribute to the derivation of recommendations for action to ensure the medium-term implementation of the scenario and to channel access to the Centres for Rare Diseases in the future. CONCLUSION: Many activities have been initiated at a national level to improve the health care situation of people with rare diseases. The scenario developed in the "BIDA-SE" project complements these research activities and illustrates how big data applications can be usefully implemented into practice to improve the diagnosis and therapy of people with rare diseases in a sustainable way.

Design for a Modular Clinical Trial Recruitment Support System Based on FHIR and OMOP.

The MIRACUM consortium is developing a Clinical Trials Recruitment Support System to support the data-driven recruitment of patients for clinical trials. The design of the prototype includes both open source solutions (OMOP CDM, Atlas) and open standards for interoperability (FHIR). The aim of the prototype is to create a patient screening list of potential participants for a clinical study. The paper shows the modular structure and functionality of the prototype building the foundation for the practical implementation of the CTRSS and, at the same time, demonstrating the use of open source solutions and standards for the development of clinical support systems.

Formal Modelling of FHIR Based, Medical Data Exchange Using Algebraic Petri Nets.

Enabling interoperability is a challenging task in medical data exchange and is often addressed by the use of versatile communication standards like HL7 FHIR. Although daily routine and scientific experiences show its suitability, the use comes with major risks regarding safety and security of data. To overcome these problems, we present an approach to enable a formal verification of medical communication use cases. We identified the Neonatal Screening as a practical example in which two process participants (physician and screening laboratory) are involved. We analyzed the FHIR specification as well as identified necessary resources in that context and formally modeled them as algebraic specifications. By that, we were able to represent the participants' behavior and data flow with help of Algebraic Petri Nets. This strategy allows to formally verify the correctness of a system by specified requirements regarding data safety and data security.