ROAD2H: Development and evaluation of an open-source explainable artificial intelligence approach for managing co-morbidity and clinical guidelines

Introduction

Clinical decision support (CDS) systems (CDSSs) that integrate clinical guidelines need to reflect real-world co-morbidity. In patient-specific clinical contexts, transparent recommendations that allow for contraindications and other conflicts arising from co-morbidity are a requirement. In this work, we develop and evaluate a non-proprietary, standards-based approach to the deployment of computable guidelines with explainable argumentation, integrated with a commercial electronic health record (EHR) system in Serbia, a middle-income country in West Balkans.

Methods

We used an ontological framework, the Transition-based Medical Recommendation (TMR) model, to represent, and reason about, guideline concepts, and chose the 2017 International global initiative for chronic obstructive lung disease (GOLD) guideline and a Serbian hospital as the deployment and evaluation site, respectively. To mitigate potential guideline conflicts, we used a TMR-based implementation of the Assumptions-Based Argumentation framework extended with preferences and Goals (ABA+G). Remote EHR integration of computable guidelines was via a microservice architecture based on HL7 FHIR and CDS Hooks. A prototype integration was developed to manage chronic obstructive pulmonary disease (COPD) with comorbid cardiovascular or chronic kidney diseases, and a mixed-methods evaluation was conducted with 20 simulated cases and five pulmonologists.

Results

Pulmonologists agreed 97% of the time with the GOLD-based COPD symptom severity assessment assigned to each patient by the CDSS, and 98% of the time with one of the proposed COPD care plans. Comments were favourable on the principles of explainable argumentation; inclusion of additional co-morbidities was suggested in the future along with customisation of the level of explanation with expertise.

Conclusion

An ontological model provided a flexible means of providing argumentation and explainable artificial intelligence for a long-term condition. Extension to other guidelines and multiple co-morbidities is needed to test the approach further.

Smart hospital: achieving interoperability and raw data collection from medical devices in clinical routine

Introduction

Today, modern technology is used to diagnose and treat cardiovascular disease. These medical devices provide exact measures and raw data such as imaging data or biosignals. So far, the Broad Integration of These Health Data into Hospital Information Technology Structures-Especially in Germany-is Lacking, and if data integration takes place, only non-Evaluable Findings are Usually Integrated into the Hospital Information Technology Structures. A Comprehensive Integration of raw Data and Structured Medical Information has not yet Been Established. The aim of this project was to design and implement an interoperable database (cardio-vascular-information-system, CVIS) for the automated integration of al medical device data (parameters and raw data) in cardio-vascular medicine.

Methods

The CVIS serves as a data integration and preparation system at the interface between the various devices and the hospital IT infrastructure. In our project, we were able to establish a database with integration of proprietary device interfaces, which could be integrated into the electronic health record (EHR) with various HL7 and web interfaces.

Results

In the period between 1.7.2020 and 30.6.2022, the data integrated into this database were evaluated. During this time, 114,858 patients were automatically included in the database and medical data of 50,295 of them were entered. For technical examinations, more than 4.5 million readings (an average of 28.5 per examination) and 684,696 image data and raw signals (28,935 ECG files, 655,761 structured reports, 91,113 x-ray objects, 559,648 ultrasound objects in 54 different examination types, 5,000 endoscopy objects) were integrated into the database. Over 10.2 million bidirectional HL7 messages (approximately 14,000/day) were successfully processed. 98,458 documents were transferred to the central document management system, 55,154 materials (average 7.77 per order) were recorded and stored in the database, 21,196 diagnoses and 50,353 services/OPS were recorded and transferred. On average, 3.3 examinations per patient were recorded; in addition, there are an average of 13 laboratory examinations.

Discussion

Fully automated data integration from medical devices including the raw data is feasible and already creates a comprehensive database for multimodal modern analysis approaches in a short time. This is the basis for national and international projects by extracting research data using FHIR.

Integration of Patient-Reported Outcome Data Collected Via Web Applications and Mobile Apps Into a Nation-Wide COVID-19 Research Platform Using Fast Healthcare Interoperability Resources: Development Study

BACKGROUND

The Network University Medicine projects are an important part of the German COVID-19 research infrastructure. They comprise 2 subprojects: COVID-19 Data Exchange (CODEX) and Coordination on Mobile Pandemic Apps Best Practice and Solution Sharing (COMPASS). CODEX provides a centralized and secure data storage platform for research data, whereas in COMPASS, expert panels were gathered to develop a reference app framework for capturing patient-reported outcomes (PROs) that can be used by any researcher.

OBJECTIVE

Our study aims to integrate the data collected with the COMPASS reference app framework into the central CODEX platform, so that they can be used by secondary researchers. Although both projects used the Fast Healthcare Interoperability Resources (FHIR) standard, it was not used in a way that data could be shared directly. Given the short time frame and the parallel developments within the CODEX platform, a pragmatic and robust solution for an interface component was required.

METHODS

We have developed a means to facilitate and promote the use of the German Corona Consensus (GECCO) data set, a core data set for COVID-19 research in Germany. In this way, we ensured semantic interoperability for the app-collected PRO data with the COMPASS app. We also developed an interface component to sustain syntactic interoperability.

RESULTS

The use of different FHIR types by the COMPASS reference app framework (the general-purpose FHIR Questionnaire) and the CODEX platform (eg, Patient, Condition, and Observation) was found to be the most significant obstacle. Therefore, we developed an interface component that realigns the Questionnaire items with the corresponding items in the GECCO data set and provides the correct resources for the CODEX platform. We extended the existing COMPASS questionnaire editor with an import function for GECCO items, which also tags them for the interface component. This ensures syntactic interoperability and eases the reuse of the GECCO data set for researchers.

CONCLUSIONS

This paper shows how PRO data, which are collected across various studies conducted by different researchers, can be captured in a research-compatible way. This means that the data can be shared with a central research infrastructure and be reused by other researchers to gain more insights about COVID-19 and its sequelae.

Design and Development of Learning Management System Huemul for Teaching Fast Healthcare Interoperability Resource: Algorithm Development and Validation Study

BACKGROUND

Interoperability between health information systems is a fundamental requirement to guarantee the continuity of health care for the population. The Fast Healthcare Interoperability Resource (FHIR) is the standard that enables the design and development of interoperable systems with broad adoption worldwide. However, FHIR training curriculums need an easily administered web-based self-learning platform with modules to create scenarios and questions that the learner answers. This paper proposes a system for teaching FHIR that automatically evaluates the answers, providing the learner with continuous feedback and progress.

OBJECTIVE

We are designing and developing a learning management system for creating, applying, deploying, and automatically assessing FHIR web-based courses.

METHODS

The system requirements for teaching FHIR were collected through interviews with experts involved in academic and professional FHIR activities (universities and health institutions). The interviews were semistructured, recording and documenting each meeting. In addition, we used an ad hoc instrument to register and analyze all the needs to elicit the requirements. Finally, the information obtained was triangulated with the available evidence. This analysis was carried out with Atlas-ti software. For design purposes, the requirements were divided into functional and nonfunctional. The functional requirements were (1) a test and question manager, (2) an application programming interface (API) to orchestrate components, (3) a test evaluator that automatically evaluates the responses, and (4) a client application for students. Security and usability are essential nonfunctional requirements to design functional and secure interfaces. The software development methodology was based on the traditional spiral model. The end users of the proposed system are (1) the system administrator for all technical aspects of the server, (2) the teacher designing the courses, and (3) the students interested in learning FHIR.

RESULTS

The main result described in this work is Huemul, a learning management system for training on FHIR, which includes the following components: (1) Huemul Admin: a web application to create users, tests, and questions and define scores; (2) Huemul API: module for communication between different software components (FHIR server, client, and engine); (3) Huemul Engine: component for answers evaluation to identify differences and validate the content; and (4) Huemul Client: the web application for users to show the test and questions. Huemul was successfully implemented with 416 students associated with the 10 active courses on the platform. In addition, the teachers have created 60 tests and 695 questions. Overall, the 416 students who completed their courses rated Huemul highly.

CONCLUSIONS

Huemul is the first platform that allows the creation of courses, tests, and questions that enable the automatic evaluation and feedback of FHIR operations. Huemul has been implemented in multiple FHIR teaching scenarios for health care professionals. Professionals trained on FHIR with Huemul are leading successful national and international initiatives.

Structured Queries to AQL: Querying OpenEHR Data Leveraging a FHIR-Based Infrastructure for Federated Feasibility Queries

In digital healthcare, data heterogeneity is a reoccurring issue caused by proprietary source systems. It is often overcome by utilizing ETL processes resulting in data warehouses, which ensure common data models for interoperability. Unfortunately, the achieved interoperability is usually limited to an institutional level. The broad solution space to achieve interoperability with different health data standards is part of the problem, resulting in different standards used at various institutions. For cross-institutional use cases like federated feasibility queries, the issue of heterogeneity is reintroduced. This work showcases how the existing German infrastructure for federated feasibility queries based on Hl7 FHIR can be extended to support openEHR without further data transformation. By utilizing an intermediate query format that can be transferred to FHIR Search, CQL, and AQL.

Digital Health Consent - for Better Interoperability and Consumer Control

We present a framework for digital health consent in support of computable expression of medico-legal policies to govern consumer data sharing across providers. The approach is aligned with HL7 FHIR© standard, and is based on generic formalism for policy modelling, grounded in normative systems and deontic logic. We show the use of the framework for a clinical research scenario.

A FHIR Native Radiology Informatics Platform

FHIR is a new standard that is rapidly being adopted in healthcare. We describe and implement a Radiology informatics platform (RIS) that is FHIR native and incorporates the ability to execute AI algorithms to aid with the interpretation of scans. Our design utilises the FHIR workflow pattern as an application programming interface with functionality provided by independent micro services thus granting flexibility and expandability.

Interoperability Is a Process - The Data Sharing Framework

Common syntax and data semantics are core components of healthcare interoperability standards. However, interoperable data exchange processes are also needed to enable the integration of existing systems between organizations. While solutions for healthcare delivery processes are available and have been widely adopted, support for processes targeting bio-medical research is limited. Our Data Sharing Framework creates a platform to implement research processes like cohort size estimation, reviews and approvals of research proposals, consent checks, record linkage, pseudonymization and data sharing across organizations. The described framework implements a distributed business process engine for executing BPMN 2.0 processes with synchronization and data exchange using FHIR R4 resources. Our reference implementation has been rolled out to 38 organizations across three research consortia in Germany and is available as open source under the Apache 2.0 license.

Design of HL7 FHIR Profiles for Pathology Reports Integrated with Pathology Images

This paper describes the development of Health Level Seven Fast Healthcare Interoperability Resource (FHIR) profiles for pathology reports integrated with whole slide images and clinical data to create a pathology research database. A report template was designed to collect structured reports, enabling pathologists to select structured terms based on a checklist, allowing for the standardization of terms used to describe tumor features. We gathered and analyzed 190 non-small-cell lung cancer pathology reports in free text format, which were then structured by mapping the itemized vocabulary to FHIR observation resources, using international standard terminologies, such as the International Classification of Diseases, LOINC, and SNOMED CT. The resulting FHIR profiles were published as an implementation guide, which includes 25 profiles for essential data elements, value sets, and structured definitions for integrating clinical data and pathology images associated with the pathology report. These profiles enable the exchange of structured data between systems and facilitate the integration of pathology data into electronic health records, which can improve the quality of care for patients with cancer.

CBL on FHIR: A FHIR-Based Platform for Health Professional Education

A FHIR based platform for case-based instruction of health professions students has been developed and field tested. The system provides a non-technical case authoring tool; supports individual and team learning using digital virtual patients; and allows integration of SMART Apps into cases via its simulated EMR. Successful trials at the University of Queensland have led to adoption at the University of Melbourne.

Clinical Decision Support to Reduce Opioid Prescriptions for Dental Extractions using SMART on FHIR: Implementation Report

BACKGROUND

Clinical decision support (CDS) has the potential to improve clinical decision-making consistent with evidence-based care. CDS can be designed to save health care providers time and help them provide safe and personalized analgesic prescribing.

OBJECTIVE

The aim of this report is to describe the development of a CDS system designed to provide dentists with personalized pain management recommendations to reduce opioid prescribing following extractions. The use of CDS is also examined.

METHODS

This study was conducted in HealthPartners, which uses an electronic health record (EHR) system that integrates both medical and dental information upon which the CDS application was developed based on SMART (Substitutable Medical Applications and Reusable Technologies) on FHIR (Fast Healthcare Interoperability Resources). The various tools used to bring relevant medical conditions, medications, patient history, and other relevant data into the CDS interface are described. The CDS application runs a drug interaction algorithm developed by our organization and provides patient-specific recommendations. The CDS included access to the state Prescription Monitoring Program database.

IMPLEMENTATION (RESULTS)

The pain management CDS was implemented as part of a study examining opioid prescribing among patients undergoing dental extraction procedures from February 17, 2020, to May 14, 2021. Provider-level use of CDS at extraction encounters ranged from 0% to 87.4% with 12.1% of providers opening the CDS for no encounters, 39.4% opening the CDS for 1%-20% of encounters, 36.4% opening it for 21%-50% of encounters, and 12.1% opening it for 51%-87% of encounters.

CONCLUSIONS

The pain management CDS is an EHR-embedded, provider-facing tool to help dentists make personalized pain management recommendations following dental extractions. The SMART on FHIR-based pain management CDS adapted well to the point-of-care dental setting and led to the design of a scalable CDS tool that is EHR vendor agnostic.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03584789; https://clinicaltrials.gov/study/NCT03584789.

Real-time algorithmic exchange and processing of pharmaceutical quality data and information

Herein, a modern method is proposed for exchanging and processing real-time medicinal product information using Health Level 7 International's (HL7) Fast Healthcare Interoperability Resources (FHIR®) standard, Application Programming Interfaces (API), digitization and artificial intelligence. FHIR is presently in use largely to facilitate interactions between patient-facing healthcare institutions, such as hospitals, doctor's offices, and laboratories, for electronic health record management and exchange. There are several ongoing efforts to adapt the FHIR standard for regulatory use cases to support the needs of the global biopharmaceutical industry, including the exchange of Electronic Product Information (ePI); chemistry, manufacturing, and controls (CMC) data; and adverse event reporting. Once in place, this new method of data exchange is expected to (1) improve efficiency by reducing the time and effort needed to manage regulatory information; (2) accelerate decision making; (3) encourage innovation in pharmaceutical manufacturing; (4) improve the ability and agility of information exchange. Currently, the end-to-end timescale for the pharmaceutical regulatory workflow is measured in months and years. This new paradigm will use FHIR APIs and other supporting technologies to reduce the potential time for data exchange from months to days, hours, minutes, and eventually sub-seconds. With such drastic improvements in speed provided by digitization, automation, and interoperability, the biopharmaceutical industry can reach more patients, and more quickly than at any time in the industry's 100+ year history. The present work will focus on examining specific real-world implementation examples for using FHIR to support exchange of CMC information within and across the biopharmaceutical industry.

ResearchMatch on FHIR: Development and evaluation of a recruitment registry and electronic health record system interface for volunteer profile completion

Background

Obtaining complete and accurate information in recruitment registries is essential for matching potential participants to research studies for which they qualify. Since electronic health record (EHR) systems are required to make patient data available to external systems, an interface between EHRs and recruitment registries may improve accuracy and completeness of volunteers' profiles. We tested this hypothesis on ResearchMatch (RM), a disease- and institution-neutral recruitment registry with 1357 studies across 255 institutions.

Methods

We developed an interface where volunteers signing up for RM can authorize transfer of demographic data, medical conditions, and medications from the EHR into a registration form. We obtained feedback from a panel of community members to determine acceptability of the planned integration. We then developed the EHR interface and performed an evaluation study of 100 patients to determine whether RM profiles generated with EHR-assisted adjudication included more conditions and medications than those without the EHR connection.

Results

Community member feedback revealed that members of the public were willing to authenticate into the EHR from RM with proper messaging about choice and privacy. The evaluation study showed that out of 100 participants, 75 included more conditions and 69 included more medications in RM profiles completed with the EHR connection than those without. Participants also completed the EHR-connected profiles in 16 fewer seconds than non-EHR-connected profiles.

Conclusions

The EHR to RM integration could lead to more complete profiles, less participant burden, and better study matches for many of the over 148,000 volunteers who participate in ResearchMatch.

A systematic review of data elements of computerized physician order entry (CPOE): mapping the data to FHIR

OBJECTIVE

Medication errors are the third leading cause of death. There are several methods to prevent prescription errors, one of which is to use a Computerized Physician Order Entry system (CPOE). In a CPOE system, necessary data needs to be collected so that making decisions about prescribing medications and treatment plans could be made. Although many CPOE systems have been developed worldwide, studies have yet to identify the necessary data and data elements of CPOE systems. This study aims to identify data elements of CPOE and standardize these data with Fast Healthcare Interoperability Resources (FHIR) to facilitate data sharing and integration with the electronic health record (EHR) system and reduce data diversity.

METHODS

PubMed, Web of Science, Embase, and Scopus databases for studies up to October 2019 were searched. Two reviewers independently assessed original articles to determine eligibility for inclusion in this review. All articles describing data elements of a COPE system were included. Data elements were obtained from the included articles' text, tables, and figures.Classification of the extracted data elements and mapping them to FHIR was done to facilitate data sharing and integration with the electronic health record (EHR) system and reduce data diversity. The final data elements of CPOE were categorized into five main categories of FHIR (foundation, base, clinical, financial, and specialized) and 146 resources, where possible. One of the researchers did mapping and checked and verified by the second researcher. If a data element could not be mapped to any FHIR resources, this data element was considered an extension to the most relevant resource.

RESULTS

We retrieved 5162 articles through database searches. After the full-text assessment, 21 articles were included. In total, 270 data elements were identified and mapped to the FHIR standard. These elements have been reported in 26 FHIR resources of 146 ones (18%). In total, 71 data elements were considered an extension.

CONCLUSIONS

The results of this study showed that the same data elements were not used in the CPOE systems, and the degree of homogeneity of these systems is limited. The mapping of extracted data with data elements used in the FHIR standard shows the extent to which these systems comply with existing standards. Considering the standards in these systems' design helps developers design more coherent systems that can share data with other systems.

Striking a match between FHIR-based patient data and FHIR-based eligibility criteria

Inputs and Outputs

The Strike-a-Match Function, written in JavaScript version ES6+, accepts the input of two datasets (one dataset defining eligibility criteria for research studies or clinical decision support, and one dataset defining characteristics for an individual patient). It returns an output signaling whether the patient characteristics are a match for the eligibility criteria.

Purpose

Ultimately, such a system will play a "matchmaker" role in facilitating point-of-care recognition of patient-specific clinical decision support.

Specifications

The eligibility criteria are defined in HL7 FHIR (version R5) EvidenceVariable Resource JSON structure. The patient characteristics are provided in an FHIR Bundle Resource JSON including one Patient Resource and one or more Observation and Condition Resources which could be obtained from the patient's electronic health record.

Application

The Strike-a-Match Function determines whether or not the patient is a match to the eligibility criteria and an Eligibility Criteria Matching Software Demonstration interface provides a human-readable display of matching results by criteria for the clinician or patient to consider. This is the first software application, serving as proof of principle, that compares patient characteristics and eligibility criteria with all data exchanged using HL7 FHIR JSON. An Eligibility Criteria Matching Software Library at https://fevir.net/110192 provides a method for sharing functions using the same information model.

Towards a Bavarian Oncology Real World Data Research Platform

INTRODUCTION

In the last decade numerous real-world data networks have been established in order to leverage the value of data from electronic health records for medical research. In Germany, a nation-wide network based on electronic health record data from all German university hospitals has been established within the Medical Informatics Initiative (MII) and recently opened for researcherst' access through the German Portal for Medical Research Data (FDPG). In Bavaria, the six university hospitals have joined forces within the Bavarian Cancer Research Center (BZKF). The oncology departments aim at establishing a federated observational research network based on the framework of the MII/FDPG and extending it with a clear focus on oncological clinical data, imaging data and molecular high throughput analysis data.

METHODS

We describe necessary adaptions and extensions of existing MII components with the goal of establishing a Bavarian oncology real world data research platform with its first use case of performing federated feasibility queries on clinical oncology data.

RESULTS

We share insights from developing a feasibility platform prototype and presenting it to end users. Our main discovery was that oncological data is characterized by a higher degree of interdependence and complexity compared to the MII core dataset that is already integrated into the FDPG.

DISCUSSION

The significance of our work lies in the requirements we formulated for extending already existing MII components to match oncology specific data and to meet oncology researchers needs while simultaneously transferring back our results and experiences into further developments within the MII.

Building an Electronic Medical Record System Exchanged in FHIR Format and Its Visual Presentation

Currently, the Taiwan Electronic Medical Record Exchange Center uses the Clinical Document Architecture (CDA) framework, which is based on the international medical standard. The CDA R2 standard, defined in 2005, is used for cross-institution retrieval of electronic medical records (Ministry of Health and Welfare, Information Department, 2021). However, CDA R2 only supports the exchange of clinical documents and is limited to the XML format. Due to the lack of a standardized framework for medical data exchange in Taiwan, different standards and specifications result in different data interface methods between systems, requiring customization for each system by healthcare institutions or the government. The inconsistency in data formats requires healthcare institutions and the government to spend more time on data parsing and mapping, resulting in slow integration of medical data. In this study, we simulated healthcare institutions using Fast Healthcare Interoperability Resources (FHIR) for medical information exchange and utilized the exchanged medical information to create a dynamic dashboard to assist healthcare professionals in making medical decisions. To ensure information security, we employed Hyper Text Transfer Protocol Secure (HTTPS) for secure transmission, which encrypts the transmitted medical record data using the Transport Layer Security (TLS) protocol, preventing deliberate interception and tampering of medical record data between the two systems. Finally, to test the load and performance of static and dynamic resources and web applications, we conducted a system performance evaluation using Apache JMeter. The results of this study demonstrate that replacing the gateway of the Electronic Medical Record Exchange Center with an FHIR server effectively reduces the time and cost spent by developers on data format conversion while also mitigating the information security risks associated with the previous VPN solution. Additionally, by utilizing dynamic charts, healthcare professionals are assisted in making medical decisions.

Machine Learning-Enabled Clinical Information Systems Using Fast Healthcare Interoperability Resources Data Standards: Scoping Review

Background

Machine learning-enabled clinical information systems (ML-CISs) have the potential to drive health care delivery and research. The Fast Healthcare Interoperability Resources (FHIR) data standard has been increasingly applied in developing these systems. However, methods for applying FHIR to ML-CISs are variable.

Objective

This study evaluates and compares the functionalities, strengths, and weaknesses of existing systems and proposes guidelines for optimizing future work with ML-CISs.

Methods

Embase, PubMed, and Web of Science were searched for articles describing machine learning systems that were used for clinical data analytics or decision support in compliance with FHIR standards. Information regarding each system's functionality, data sources, formats, security, performance, resource requirements, scalability, strengths, and limitations was compared across systems.

Results

A total of 39 articles describing FHIR-based ML-CISs were divided into the following three categories according to their primary focus: clinical decision support systems (n=18), data management and analytic platforms (n=10), or auxiliary modules and application programming interfaces (n=11). Model strengths included novel use of cloud systems, Bayesian networks, visualization strategies, and techniques for translating unstructured or free-text data to FHIR frameworks. Many intelligent systems lacked electronic health record interoperability and externally validated evidence of clinical efficacy.

Conclusions

Shortcomings in current ML-CISs can be addressed by incorporating modular and interoperable data management, analytic platforms, secure interinstitutional data exchange, and application programming interfaces with adequate scalability to support both real-time and prospective clinical applications that use electronic health record platforms with diverse implementations.

An Extract-Transform-Load Process Design for the Incremental Loading of German Real-World Data Based on FHIR and OMOP CDM: Algorithm Development and Validation

Background

In the Medical Informatics in Research and Care in University Medicine (MIRACUM) consortium, an IT-based clinical trial recruitment support system was developed based on the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). Currently, OMOP CDM is populated with German Fast Healthcare Interoperability Resources (FHIR) using an Extract-Transform-Load (ETL) process, which was designed as a bulk load. However, the computational effort that comes with an everyday full load is not efficient for daily recruitment.

Objective

The aim of this study is to extend our existing ETL process with the option of incremental loading to efficiently support daily updated data.

Methods

Based on our existing bulk ETL process, we performed an analysis to determine the requirements of incremental loading. Furthermore, a literature review was conducted to identify adaptable approaches. Based on this, we implemented three methods to integrate incremental loading into our ETL process. Lastly, a test suite was defined to evaluate the incremental loading for data correctness and performance compared to bulk loading.

Results

The resulting ETL process supports bulk and incremental loading. Performance tests show that the incremental load took 87.5% less execution time than the bulk load (2.12 min compared to 17.07 min) related to changes of 1 day, while no data differences occurred in OMOP CDM.

Conclusions

Since incremental loading is more efficient than a daily bulk load and both loading options result in the same amount of data, we recommend using bulk load for an initial load and switching to incremental load for daily updates. The resulting incremental ETL logic can be applied internationally since it is not restricted to German FHIR profiles.

Interoperable, Domain-Specific Extensions for the German Corona Consensus (GECCO) COVID-19 Research Data Set Using an Interdisciplinary, Consensus-Based Workflow: Data Set Development Study

Background: The COVID-19 pandemic has spurred large-scale, interinstitutional research efforts. To enable these efforts, researchers must agree on data set definitions that not only cover all elements relevant to the respective medical specialty but also are syntactically and semantically interoperable. Therefore, the German Corona Consensus (GECCO) data set was developed as a harmonized, interoperable collection of the most relevant data elements for COVID-19-related patient research. As the GECCO data set is a compact core data set comprising data across all medical fields, the focused research within particular medical domains demands the definition of extension modules that include data elements that are the most relevant to the research performed in those individual medical specialties. Objective: We aimed to (1) specify a workflow for the development of interoperable data set definitions that involves close collaboration between medical experts and information scientists and (2) apply the workflow to develop data set definitions that include data elements that are the most relevant to COVID-19-related patient research regarding immunization, pediatrics, and cardiology. Methods: We developed a workflow to create data set definitions that were (1) content-wise as relevant as possible to a specific field of study and (2) universally usable across computer systems, institutions, and countries (ie, interoperable). We then gathered medical experts from 3 specialties-infectious diseases (with a focus on immunization), pediatrics, and cardiology-to select data elements that were the most relevant to COVID-19-related patient research in the respective specialty. We mapped the data elements to international standardized vocabularies and created data exchange specifications, using Health Level Seven International (HL7) Fast Healthcare Interoperability Resources (FHIR). All steps were performed in close interdisciplinary collaboration with medical domain experts and medical information specialists. Profiles and vocabulary mappings were syntactically and semantically validated in a 2-stage process. Results: We created GECCO extension modules for the immunization, pediatrics, and cardiology domains according to pandemic-related requests. The data elements included in each module were selected, according to the developed consensus-based workflow, by medical experts from these specialties to ensure that the contents aligned with their research needs. We defined data set specifications for 48 immunization, 150 pediatrics, and 52 cardiology data elements that complement the GECCO core data set. We created and published implementation guides, example implementations, and data set annotations for each extension module. Conclusions: The GECCO extension modules, which contain data elements that are the most relevant to COVID-19-related patient research on infectious diseases (with a focus on immunization), pediatrics, and cardiology, were defined in an interdisciplinary, iterative, consensus-based workflow that may serve as a blueprint for developing further data set definitions. The GECCO extension modules provide standardized and harmonized definitions of specialty-related data sets that can help enable interinstitutional and cross-country COVID-19 research in these specialties.

FHIR-PYrate: a data science friendly Python package to query FHIR servers

BACKGROUND

We present FHIR-PYrate, a Python package to handle the full clinical data collection and extraction process. The software is to be plugged into a modern hospital domain, where electronic patient records are used to handle the entire patient's history. Most research institutes follow the same procedures to build study cohorts, but mainly in a non-standardized and repetitive way. As a result, researchers spend time writing boilerplate code, which could be used for more challenging tasks.

METHODS

The package can improve and simplify existing processes in the clinical research environment. It collects all needed functionalities into a straightforward interface that can be used to query a FHIR server, download imaging studies and filter clinical documents. The full capacity of the search mechanism of the FHIR REST API is available to the user, leading to a uniform querying process for all resources, thus simplifying the customization of each use case. Additionally, valuable features like parallelization and filtering are included to make it more performant.

RESULTS

As an exemplary practical application, the package can be used to analyze the prognostic significance of routine CT imaging and clinical data in breast cancer with tumor metastases in the lungs. In this example, the initial patient cohort is first collected using ICD-10 codes. For these patients, the survival information is also gathered. Some additional clinical data is retrieved, and CT scans of the thorax are downloaded. Finally, the survival analysis can be computed using a deep learning model with the CT scans, the TNM staging and positivity of relevant markers as input. This process may vary depending on the FHIR server and available clinical data, and can be customized to cover even more use cases.

CONCLUSIONS

FHIR-PYrate opens up the possibility to quickly and easily retrieve FHIR data, download image data, and search medical documents for keywords within a Python package. With the demonstrated functionality, FHIR-PYrate opens an easy way to assemble research collectives automatically.

Playing in the clinical decision support sandbox: tools and training for all

Objectives

Introduce the CDS-Sandbox, a cloud-based virtual machine created to facilitate Clinical Decision Support (CDS) developers and implementers in the use of FHIR- and CQL-based open-source tools and technologies for building and testing CDS artifacts.

Materials and Methods

The CDS-Sandbox includes components that enable workflows for authoring and testing CDS artifacts. Two workshops at the 2020 and 2021 AMIA Annual Symposia were conducted to demonstrate the use of the open-source CDS tools.

Results

The CDS-Sandbox successfully integrated the use of open-source CDS tools. Both workshops were well attended. Participants demonstrated use and understanding of the workshop materials and provided positive feedback after the workshops.

Discussion

The CDS-Sandbox and publicly available tutorial materials facilitated an understanding of the leading-edge open-source CDS infrastructure components.

Conclusion

The CDS-Sandbox supports integrated use of the key CDS open-source tools that may be used to introduce CDS concepts and practice to the clinical informatics community.

Arden Syntax on FHIR

Arden Syntax, a medical knowledge representation and processing language for clinical decision support tasks supervised by Health Level Seven International (HL7), was extended with HL7's Fast Healthcare Interoperability Resources (FHIR) constructs to allow standardized data access. The new version, Arden Syntax version 3.0, was successfully balloted as part of the audited, consensus-based, iterative HL7 standards development process.

Evaluation of the Availability of Nursing Quality Indicators in German FHIR Implementations

Standardized nursing data sets facilitate data analysis and help to improve nursing research and quality management in Germany. Recently, governmental standardization approaches have favored the FHIR standard and helped to define it as the state of the art for healthcare interoperability and data exchange. In this study, we identify common data elements used for nursing quality research purposes by analyzing nursing quality data sets and databases. We then compare the results with current FHIR implementations in Germany to find most relevant data fields and overlaps. Our results show that most of the patient focused information has already been modelled in national standardization efforts and FHIR implementations. However, representation of data fields describing nursing staff related information, such as experience, workload or satisfaction, is missing or lacking.

Representing NIH Genetic Test Registry Data in the FHIR Genomic Study Resource

The National Institute of Health (NIH) Genetic Testing Registry (GTR) provides a variety of information about genetic tests such as relevant methods, conditions, and performing laboratories. This study mapped a subset of GTR data to the newly developed HL7®-FHIR® Genomic Study resource. Using open-source tools, a web application was developed to implement data mapping and provides many GTR test records as Genomic Study resources. The developed system demonstrates the feasibility of using open-source tools and the FHIR Genomic Study resource to represent publicly available genetic testing information. This study validates the overall design of the Genomic Study resource and proposes two enhancements to support additional data elements.

eHealth4U: A DEMO of a Prototype National Electronic Health Record for Cyprus

In this paper we present a demonstration of a prototype national Electronic Health Record platform for Cyprus. This prototype is developed using the HL7 FHIR interoperability standard in combination with terminologies widely adopted by the clinical community such as the SNOMED CT and the LOINC. The system is organized in such a way to be user-friendly for its users, being the doctors and the citizens. The health-related data of this EHR are separated into three main sections, being the "Medical History", the "Clinical Examination" and the "Laboratory results". Business requirements include the Patient Summary as defined by the guidelines of the eHealth network and the International Patient Summary which are used as the base for all the sections of our EHR, together with additional medical information and functionality such as the organization of medical teams or the history of medical visits and episodes of care. From the doctor's point of view, one can search for patients who have granted the doctor with a consent and read or add/edit their EHR data by initiating a new visit as defined in the Cyprus National Law for eHealth. At the same time, doctors can organize their medical teams by managing the locations of each team and the members that belong to each team.

MYeHealthAppCY: A Healthcare Mobile Application in Cyprus

This paper presents MYeHealthAppCY, an mHealth solution designed to provide patients and healthcare providers in Cyprus with access to medical data. The application includes features such as an at-a-glance view of patient summary, comprehensive prescription management, teleconsultation, and the ability to store and access European Digital COVID Certificates (EUDCC). The application is an integral part of the eHealth4U platform targeting to implement a prototype EHR platform for national use. The application developed is based on FHIR and follows a strict adherence to widely used coding standards. The application was evaluated receiving satisfactory scores; however, significant work is still needed to deploy the application in production.

FHIR DataProvider for ReactAdmin: Leveraging User Interface Creation for Medical Web Applications

In medical data science, FHIR provides an increasingly used information model, which will lead to the creation of FHIR warehouses in the future. To efficiently work with a FHIR-based representation, users need a visual representation. The modern UI framework ReactAdmin (RA) enhances usability by leveraging current web standards such as React and Material Design. Rapid development and implementation of usable modern UIs is made possible by its high modularity and many widgets available in the framework. For data connection to different data sources RA needs a DataProvider (DP), which maps the communication from the server to the provided components. In this work, we present a DataProvider for FHIR that enables future UI developments for FHIR servers using RA. A demo application demonstrates the DP's capabilities. The code is published under MIT license.

Health Digital Twins with Clinical Decision Support

This paper studies the feasibility of incorporating clinical decision support (CDS) into health digital twins (HDTs). A HDT is visualized in a web application, health data are stored in a FHIR-based electronic health record, and an Arden-Syntax-based CDS interpretation and alert service is connected. The prototype focuses on interoperability of these components. The study confirms the feasibility of CDS integration into HDTs and provides insight into possibilities for further expansion.

Towards FAIR Data Standardization Using FHIR Genomics Resources Integration in Obstetrics-Gynecology Department Systems

The paper presents a current situation of the FHIR Genomics resource and an assessment of FAIR data usage and possible future directions. FHIR Genomics forges a path towards data interoperability. By integrating both the FAIR principles and the FHIR resources, we can achieve a higher standardization across healthcare data collection and a smoother data exchange. By exemplifying on the FHIR Genomics resource, we want to pave the way towards the integration of genomic data into an Obstetrics-Gynecology Information system as a future direction to be able to identify possible disease predisposition in fetus.

Wearable Device Health Data Mapping to Open mHealth and FHIR Data Formats

Health data collected by wearables and apps can be useful as part of patient-generated health data (PGHD) or personal health data for medical diagnosis or general health monitoring. Mobile health apps are more and more accepted, generate evidence and might be increasingly used in personal medicine. Data retrieved from wearables and apps are mostly not following a medical data standard and cannot be retrieved from the vendors in a straightforward way. The present work started the implementation of a Digital Health Convener and described the process to collect data from several wearables - starting with Fitbit data - and transforms this data to standardized JSON files following the Open mHealth (OmH) IEEE and the HL7 FHIR standard. The project achieved is provided as open source and can be extended and used in future projects to generate OmH and FHIR conform PGHD.

HL7-FHIR-Based ContSys Formal Ontology for Enabling Continuity of Care Data Interoperability

The rapid advancement of digital technologies and recent global pandemic-like scenarios have pressed our society to reform and adapt health and social care toward personalizing the home care setting. This transformation assists in avoiding treatment in crowded secondary health care facilities and improves the experience and impact on both healthcare professionals and service users alike. The interoperability challenge through standards-based roadmaps is the lynchpin toward enabling the efficient interconnection between health and social care services. Hence, facilitating safe and trustworthy data workflow from one healthcare system to another is a crucial aspect of the communication process. In this paper, we showcase a methodology as to how we can extract, transform and load data in a semi-automated process using a common semantic standardized data model (CSSDM) to generate a personalized healthcare knowledge graph (KG). CSSDM is based on a formal ontology of ISO 13940:2015 ContSys for conceptual grounding and FHIR-based specification to accommodate structural attributes to generate KG. The goal of CSSDM is to offer an alternative pathway to discuss interoperability by supporting a unique collaboration between a company creating a health information system and a cloud-enabled health service. The resulting pathway of communication provides access to multiple stakeholders for sharing high-quality data and information.

Transforming Healthcare Analytics with FHIR: A Framework for Standardizing and Analyzing Clinical Data

In this study, we discussed our contribution to building a data analytic framework that supports clinical statistics and analysis by leveraging a scalable standards-based data model named Fast Healthcare Interoperability Resource (FHIR). We developed an intelligent algorithm that is used to facilitate the clinical data analytics process on FHIR-based data. We designed several workflows for patient clinical data used in two hospital information systems, namely patient registration and laboratory information systems. These workflows exploit various FHIR Application programming interface (APIs) to facilitate patient-centered and cohort-based interactive analyses. We developed an FHIR database implementation that utilizes FHIR APIs and a range of operations to facilitate descriptive data analytics (DDA) and patient cohort selection. A prototype user interface for DDA was developed with support for visualizing healthcare data analysis results in various forms. Healthcare professionals and researchers would use the developed framework to perform analytics on clinical data used in healthcare settings. Our experimental results demonstrate the proposed framework's ability to generate various analytics from clinical data represented in the FHIR resources.

Creating a Medical Imaging Workflow Based on FHIR, DICOMweb, and SVG

This paper proposes a web-based workflow scheme for the organization of medical images using FHIR and DICOM servers equipped with standard RESTful APIs. In our integrated workflow, the client systems (including order placer, scheduler, imaging modality, viewer, and report creator) use standard FHIR and DICOMweb APIs. The proposed scheme also facilitates the creation of reports formatted as standard FHIR resources. This paper leverages W3C Scalable Vector Graphics (SVG) to record the image graphic annotations, and encapsulates the SVG image annotation in FHIR observation. FHIR DiagnosticReports and Observations are used to encapsulate reports, findings, and annotations, thereby facilitating the implementation and integration of the scheme within existing structures. The proposed scheme also provides the potential to make it possible to convert results of Computer Aided Detection/Diagnosis from medical images into FHIR DiagnosticReports and Observations to be stored on a FHIR server. The resulting web-based solution uses FHIR XML and/or JSON data to record and exchange information related to imaging workflow. It can also be used to store imaging reports, findings, and annotations linked to the images using the DICOM WADO-RS protocol. As a result, it is possible to integrate all information that is created in medical imaging workflow. Finally, the proposed scheme is easily integrated with other FHIR systems.

quEHRy: a question answering system to query electronic health records

OBJECTIVE

We propose a system, quEHRy, to retrieve precise, interpretable answers to natural language questions from structured data in electronic health records (EHRs).

MATERIALS AND METHODS

We develop/synthesize the main components of quEHRy: concept normalization (MetaMap), time frame classification (new), semantic parsing (existing), visualization with question understanding (new), and query module for FHIR mapping/processing (new). We evaluate quEHRy on 2 clinical question answering (QA) datasets. We evaluate each component separately as well as holistically to gain deeper insights. We also conduct a thorough error analysis for a crucial subcomponent, medical concept normalization.

RESULTS

Using gold concepts, the precision of quEHRy is 98.33% and 90.91% for the 2 datasets, while the overall accuracy was 97.41% and 87.75%. Precision was 94.03% and 87.79% even after employing an automated medical concept extraction system (MetaMap). Most incorrectly predicted medical concepts were broader in nature than gold-annotated concepts (representative of the ones present in EHRs), eg, Diabetes versus Diabetes Mellitus, Non-Insulin-Dependent.

DISCUSSION

The primary performance barrier to deployment of the system is due to errors in medical concept extraction (a component not studied in this article), which affects the downstream generation of correct logical structures. This indicates the need to build QA-specific clinical concept normalizers that understand EHR context to extract the "relevant" medical concepts from questions.

CONCLUSION

We present an end-to-end QA system that allows information access from EHRs using natural language and returns an exact, verifiable answer. Our proposed system is high-precision and interpretable, checking off the requirements for clinical use.

Enhancing Data Protection via Auditable Informational Separation of Powers Between Workflow Engine Based Agents: Conceptualization, Implementation, and First Cross-Institutional Experiences

German best practice standards for secondary use of patient data require pseudonymization and informational separation of powers assuring that identifying data (IDAT), pseudonyms (PSN), and medical data (MDAT) are never simultaneously knowable by any party involved in data provisioning and use. We describe a solution meeting these requirements based on the dynamic interaction of three software agents: the clinical domain agent (CDA), which processes IDAT and MDAT, the trusted third party agent (TTA), which processes IDAT and PSN, and the research domain agent (RDA), which processes PSN and MDAT and delivers pseudonymized datasets. CDA and RDA implement a distributed workflow by employing an off-the-shelf workflow engine. TTA wraps the gPAS framework for pseudonym generation and persistence. All agent interactions are implemented via secured REST-APIs. Rollout to three university hospitals was seamless. The workflow engine allowed meeting various overarching requirements, including auditability of data transfer and pseudonymization, with minimal additional implementation effort. Using a distributed agent architecture based on workflow engine technology thus proved to be an efficient way to meet technical and organizational requirements for provisioning patient data for research purposes in a data protection compliant way.

Breaking Barriers for Interoperability: A Reference Implementation of CSV-FHIR Transformation Using Open-Source Tools

FHIR is a widely accepted interoperability standard for exchanging medical data, but data transformation from the primary health information systems into FHIR is usually challenging and requires advanced technical skills and infrastructure. There is a critical need for low-cost solutions, and using Mirth Connect as an open-source tool provides this opportunity. We developed a reference implementation to transform data from CSV (the most common data format) into FHIR resources using Mirth Connect without any advanced technical resources or programming skills. This reference implementation is tested successfully for both quality and performance, and it enables reproducing and improving the implemented approach by healthcare providers to transform raw data into FHIR resources. For ensuring replicability, the used channel, mapping, and templates are available publicly on GitHub (https://github.com/alkarkoukly/CSV-FHIR-Transformer).

Interdisciplinary Teams in Health Informatics: Using FHIR Standards to Share Computable Knowledge

The use and shareability of Clinical Quality Language (CQL) artefacts is an important aspect in enabling the exchange and interoperability of clinical data to support both clinical decisions and research in the medical informatics field. This paper, while basing on use cases and synthetic data, developed purposeful CQL reusable libraries to showcase the possibilities of multidisciplinary teams and how CQLs could be best used to support clinical decision making.

From FAIR4Health Project to 1+MG Initiative: A Spain - Italy Collaboration

Results of two major projects funded by the European Union are taken into consideration: Fair4Health regarding the possibility of sharing clinical data in various environments applying FAIR principles and 1+Million Genome for the in-depth study of the human genome in Europe. Specifically, the Gaslini hospital plans to move on both areas joining the Hospital on FHIR initiative matured within the fair4health project and also collaborate with other Italian healthcare facilities through the implementation of a Proof of Concept (PoC) in the 1+MG. The aim of this short paper is to evaluate the applicability of some of the tools of the fair4health project to the Gaslini infrastructure to facilitate its participation in the PoC. One of the aims is also to prove the possibility of reuse the results of well-performed European funded projects to boost routine research in qualified healthcare facilities.

Mapping the SPHN Dataset to FHIR

Several European health data research initiatives aim to make health data FAIR for research and healthcare, and supply their national communities with coordinated data models, infrastructures, and tools. We present a first map of the Swiss Personalized Healthcare Network dataset to Fast Healthcare Interoperability Resources (FHIR®). All concepts could be mapped using 22 FHIR resources and three datatypes. Deeper analyses will follow before creating a FHIR specification, to potentially enable data conversion and exchange between research networks.

Assessing Quality of Life Using FHIR - How to Combine Patient Reported Outcome with Patient Generated Data for Better Compliance

Quality of life (QoL) is affected by environmental influences and varies between patients. A combined measurement through Patient Reported Outcomes (PROs) and Patient Generated Data (PGD) may enhance the detection of QoL impairments by a longitudinal survey. Leveraging different approaches of QoL measurement techniques, the challenge is to combine data in a standardized, interoperable way. We developed an app (Lion-App) to semantically annotate data from sensor systems as well as PROs to be merged in an overall analysis of QoL. A FHIR implementation guide was defined for a standardized assessment. To access sensor data the interfaces of Apple Health or Google Fit are used instead of integrating various provider directly into the system. Since QoL cannot be collected exclusively via sensor values, a combination of PROs and PGD is necessary. PGD enable a progression of QoL which offers more insight into personal limitations whereas PROs give insight about personal burden. The use of FHIR enables structured exchange of data while personalized analyses might improve therapy and outcome.

Model-Driven Dementia Prevention and Intervention Platform

Most types of dementia, including Alzheimer's disease, are not curable. However, there are risk factors, such as obesity or hypertension, that can promote the development of dementia. Holistic treatment of these risk factors can prevent the onset of dementia or delay it in its early stages. To support individualized treatment of risk factors in dementia, this paper presents a model-driven digital platform. It enables monitoring of biomarkers using smart devices from the internet of medical things (IoMT) for the target group. The collected data from such devices can be used to optimize and adjust treatment in a patient in the loop manner. To this end, providers such as Google Fit and Withings have been connected to the platform as example data sources. To achieve treatment and monitoring data interoperability with existing medical systems, internationally accepted standards such as FHIR are used. The configuration and control of the personalized treatment processes are achieved using a self-developed domain-specific language. For this language, an associated diagram editor was implemented, which allows the management of the treatment processes through graphical models. This graphical representation should help treatment providers to understand and manage these processes more easily. To investigate this hypothesis, a usability study was conducted with twelve participants. We were able to show that such graphical representations provide advantages in clarity in reviewing the system, but lack in easy set-up (compared to wizard-style systems).

Implementation of Interoperable Healthcare Standards for Community Healthcare

Building an integrated data model that includes not only clinical data but also personal health records has become increasingly important. We aimed to build a big data healthcare platform by developing a common data model that can be utilized in the healthcare field. To this end, we acquired health data from various communities to establish community care digital healthcare service models. Further, to improve personal health data interoperability, we ensured conformance to international standards, namely, the Systemized Nomenclature of Medicine Clinical Terms (SNOMED-CT) and transmission standards, namely, Health Level 7 Fast Healthcare Interoperability Resource (HL7 FHIR). Furthermore, FHIR resource profiling was designed to transmit and receive data, following the HL7 FHIR R4 guidelines.

No Transfer Without Validation: A Data Sharing Framework Use Case

Availability and accessibility are important preconditions for using real-world patient data across organizations. To facilitate and enable the analysis of data collected at a large number of independent healthcare providers, syntactic- and semantic uniformity need to be achieved and verified. With this paper, we present a data transfer process implemented using the Data Sharing Framework to ensure only valid and pseudonymized data is transferred to a central research repository and feedback on success or failure is provided. Our implementation is used within the CODEX project of the German Network University Medicine to validate COVID-19 datasets at patient enrolling organizations and securely transfer them as FHIR resources to a central repository.

RD-MON - Building a Rare Disease Monitor to Enhance Awareness for Patients with Rare Diseases in Intensive Care

Rare diseases are commonly defined by an incidence of less than 5/10000 inhabitants. There are some 8000 different rare diseases known. So even if a single rare disease is seldom, together they pose a relevant problem for diagnosis and treatment. This is especially true if a patient is treated for another common disease. University hospital of Gießen is part of the CORD-MI Project on rare diseases within the German Medical Informatics Initiative (MII) and a member of the MIRACUM consortium within the MII. As part of the ongoing Development for a clinical research study monitor within the use case 1 of MIRACUM, the study monitor has been configured to detect patients with rare diseases during their routine clinical encounters. The goal was to send a documentation request to the corresponding patient chart within the patient data management system for extended disease documentation to enhance clinical awareness for the patients' potential problems. The project was started in late 2022 and has so far been successfully tuned to detect patients with Mucoviscidosis and place notifications within the patient chart of the patient data management system (PDMS) on intensive care units.

Evaluating a CDS Hook for FHIR Questionnaires in a SMART on FHIR App and an Existing Dermatological CDS System

BACKGROUND

To deploy clinical decision support (CDS) systems in routine patient care they have to be certified as a medical device. The European Medical Device Regulation explicitly asks for the use of standards and interoperability in the approval process.

OBJECTIVES

We extended an existing dermatological CDS system with emerging standards for CDS interoperability, to facilitate a future integration into existing healthcare infrastructure, and approval as a medical device.

METHODS

The data collection part of a CDS system was extended with the endpoints required by the CDS Hooks specification. FHIR QuestionnaireResponse resources trigger a newly defined hook.

RESULTS

One hundred and seventeen clinical observations and patient variables needed for the ranking of a disease were mapped to SNOMED CT or LOINC and modeled as FHIR Questionnaire which is rendered using LHC LForms in a SMART on FHIR app with the SMART Dev Sandbox.

CONCLUSION

SMART on FHIR in combination with CDS Hooks facilitates the integration of existing CDS systems into EHR systems, potentially improving education and patient care.

Developing a minimum data set for cardiovascular Computerized Physician Order Entry (CPOE) and mapping the data set to FHIR: A multi-method approach

Many medical errors occur in the process of treating cardiovascular patients, and most of these errors are related to prescription errors. There are several, one of the methods to prevent prescription errors is the use of a computerized physician order entry (CPOE) system. One of the obstacles of implementing this system is improper design and non-compliance with user needs. one of the issues that should be considered in designing information systems is having a standard minimum data set (MDS). Although many computerized physicians order entry (CPOE) systems have been developed in the world, no study has identified the necessary data and minimum data set (MDS) of CPOE system, and published the process of creating this MDS. This study aimed to develop an MDS for cardiovascular CPOE and standardize it with Fast Healthcare Interoperability Resources (FHIR). A multi-method approach including systematic review for identifying data elements of CPOE, reviewing the content of medical records, validation of the data elements using the expert panel and, determination of the necessary data elements using a survey was conducted. Classification of the data elements and mapping them to FHIR were done to facilitate data sharing and integration with the electronic health record (EHR) system as well as to reduce data diversity. The final data elements of MDS were categorized into 5 main categories of FHIR (foundation, base, clinical, financial, and specialized) and 146 resources, where possible. Mapping was done by one of the researchers and checked and verified by the second researcher. Non-mapped data elements were added to relevant resources as extensions of existing FHIR resources. In total, 270 data elements were identified from the systematic review. After reviewing the content of 20 patients' medical records, 28 data elements were identified. After combination of data elements of two previous phases and removing duplication, 282 data elements remained. Data elements that were considered necessary to be included in CPOE by conducting a survey among cardiovascular physicians were 109 elements. From 146 resources of FHIR, the data elements of this MDS are covered by 5 resources. This study introduced an MDS for cardiovascular CPOE by combining suggested data elements of previous research, and the practical and local requirements identified in patients' medical records. To facilitate data sharing and integration with EHR, reduce data diversity, and also to categorize data, this MDS was standardized with FHIR. The steps we used to develop this MDS could be a model for creating MDS in other CPOEs and health information systems. This is the first time that the process of developing an MDS for cardiovascular CPOE has been presented in the literature.

A Standardized Clinical Data Harmonization Pipeline for Scalable AI Application Deployment (FHIR-DHP): Validation and Usability Study

BACKGROUND

Increasing digitalization in the medical domain gives rise to large amounts of health care data, which has the potential to expand clinical knowledge and transform patient care if leveraged through artificial intelligence (AI). Yet, big data and AI oftentimes cannot unlock their full potential at scale, owing to nonstandardized data formats, lack of technical and semantic data interoperability, and limited cooperation between stakeholders in the health care system. Despite the existence of standardized data formats for the medical domain, such as Fast Healthcare Interoperability Resources (FHIR), their prevalence and usability for AI remain limited.

OBJECTIVE

In this paper, we developed a data harmonization pipeline (DHP) for clinical data sets relying on the common FHIR data standard.

METHODS

We validated the performance and usability of our FHIR-DHP with data from the Medical Information Mart for Intensive Care IV database.

RESULTS

We present the FHIR-DHP workflow in respect of the transformation of "raw" hospital records into a harmonized, AI-friendly data representation. The pipeline consists of the following 5 key preprocessing steps: querying of data from hospital database, FHIR mapping, syntactic validation, transfer of harmonized data into the patient-model database, and export of data in an AI-friendly format for further medical applications. A detailed example of FHIR-DHP execution was presented for clinical diagnoses records.

CONCLUSIONS

Our approach enables the scalable and needs-driven data modeling of large and heterogenous clinical data sets. The FHIR-DHP is a pivotal step toward increasing cooperation, interoperability, and quality of patient care in the clinical routine and for medical research.

Representation of evidence-based clinical practice guideline recommendations on FHIR

BACKGROUND

Various formalisms have been developed to represent clinical practice guideline recommendations in a computer-interpretable way. However, none of the existing formalisms leverage the structured and computable information that emerge from the evidence-based guideline development process. Thus, we here propose a FHIR-based format that uses computer-interpretable representations of the knowledge artifacts that emerge during the process of evidence-based guideline development to directly serve as the basis of evidence-based recommendations.

METHODS

We identified the information required to represent evidence-based clinical practice guideline recommendations and reviewed the knowledge artifacts emerging during the evidence-based guideline development process. We then conducted a consensus-based design process with domain experts to develop an information model for guideline recommendation representation that is structurally aligned to the evidence-based guideline recommendation development process and a corresponding representation based on FHIR resources developed for evidence-based medicine (EBMonFHIR). The resulting recommendations were modelled and represented in conformance with the FHIR Clinical Guidelines (CPG-on-FHIR) implementation guide.

RESULTS

The information model of evidence-based clinical guideline recommendations and its EBMonFHIR-/CPG-on-FHIR-based representation contain the clinical contents of individual guideline recommendations, a set of metadata for the recommendations, the ratings for the recommendations (e.g., strength of recommendation, certainty of overall evidence), the ratings of certainty of evidence for individual outcomes (e.g., risk of bias) and links to the underlying evidence (systematic reviews based on primary studies). We created profiles and an implementation guide for all FHIR resources required to represent the knowledge artifacts generated during evidence-based guideline development and their re-use as the basis for recommendations and used the profiles to implement an exemplary clinical guideline recommendation.

CONCLUSIONS

The FHIR implementation guide presented here can be used to directly link the evidence assessment process of evidence-based guideline recommendation development, i.e. systematic reviews and evidence grading, and the underlying evidence from primary studies to the resulting guideline recommendations. This not only allows the evidence on which recommendations are based on to be evaluated transparently and critically, but also enables guideline developers to leverage computable evidence in a more direct way to facilitate the generation of computer-interpretable guideline recommendations.

An Ostensive Information Architecture to Enhance Semantic Interoperability for Healthcare Information Systems

Semantic interoperability establishes intercommunications and enables data sharing across disparate systems. In this study, we propose an ostensive information architecture for healthcare information systems to decrease ambiguity caused by using signs in different contexts for different purposes. The ostensive information architecture adopts a consensus-based approach initiated from the perspective of information systems re-design and can be applied to other domains where information exchange is required between heterogeneous systems. Driven by the issues in FHIR (Fast Health Interoperability Resources) implementation, an ostensive approach that supplements the current lexical approach in semantic exchange is proposed. A Semantic Engine with an FHIR knowledge graph as the core is constructed using Neo4j to provide semantic interpretation and examples. The MIMIC III (Medical Information Mart for Intensive Care) datasets and diabetes datasets have been employed to demonstrate the effectiveness of the proposed information architecture. We further discuss the benefits of the separation of semantic interpretation and data storage from the perspective of information system design, and the semantic reasoning towards patient-centric care underpinned by the Semantic Engine.