RESUMEN
Health data are extremely important in today's data-driven world. Through automation, healthcare processes can be optimized, and clinical decisions can be supported. For any reuse of data, the quality, validity, and trustworthiness of data are essential, and it is the only way to guarantee that data can be reused sensibly. Specific requirements for the description and coding of reusable data are defined in the FAIR guiding principles for data stewardship. Various national research associations and infrastructure projects in the German healthcare sector have already clearly positioned themselves on the FAIR principles: both the infrastructures of the Medical Informatics Initiative and the University Medicine Network operate explicitly on the basis of the FAIR principles, as do the National Research Data Infrastructure for Personal Health Data and the German Center for Diabetes Research.To ensure that a resource complies with the FAIR principles, the degree of FAIRness should first be determined (so-called FAIR assessment), followed by the prioritization for improvement steps (so-called FAIRification). Since 2016, a set of tools and guidelines have been developed for both steps, based on the different, domain-specific interpretations of the FAIR principles.Neighboring European countries have also invested in the development of a national framework for semantic interoperability in the context of the FAIR (Findable, Accessible, Interoperable, Reusable) principles. Concepts for comprehensive data enrichment were developed to simplify data analysis, for example, in the European Health Data Space or via the Observational Health Data Sciences and Informatics network. With the support of the European Open Science Cloud, among others, structured FAIRification measures have already been taken for German health datasets.
Asunto(s)
Registros Electrónicos de Salud , Humanos , Alemania , Internacionalidad , Programas Nacionales de SaludRESUMEN
The interoperability Working Group of the Medical Informatics Initiative (MII) is the platform for the coordination of overarching procedures, data structures, and interfaces between the data integration centers (DIC) of the university hospitals and national and international interoperability committees. The goal is the joint content-related and technical design of a distributed infrastructure for the secondary use of healthcare data that can be used via the Research Data Portal for Health. Important general conditions are data privacy and IT security for the use of health data in biomedical research. To this end, suitable methods are used in dedicated task forces to enable procedural, syntactic, and semantic interoperability for data use projects. The MII core dataset was developed as several modules with corresponding information models and implemented using the HL7® FHIR® standard to enable content-related and technical specifications for the interoperable provision of healthcare data through the DIC. International terminologies and consented metadata are used to describe these data in more detail. The overall architecture, including overarching interfaces, implements the methodological and legal requirements for a distributed data use infrastructure, for example, by providing pseudonymized data or by federated analyses. With these results of the Interoperability Working Group, the MII is presenting a future-oriented solution for the exchange and use of healthcare data, the applicability of which goes beyond the purpose of research and can play an essential role in the digital transformation of the healthcare system.
Asunto(s)
Interoperabilidad de la Información en Salud , Humanos , Conjuntos de Datos como Asunto , Registros Electrónicos de Salud , Alemania , Interoperabilidad de la Información en Salud/normas , Informática Médica , Registro Médico Coordinado/métodos , Integración de SistemasRESUMEN
BACKGROUND: Resources are increasingly spent on artificial intelligence (AI) solutions for medical applications aiming to improve diagnosis, treatment, and prevention of diseases. While the need for transparency and reduction of bias in data and algorithm development has been addressed in past studies, little is known about the knowledge and perception of bias among AI developers. OBJECTIVE: This study's objective was to survey AI specialists in health care to investigate developers' perceptions of bias in AI algorithms for health care applications and their awareness and use of preventative measures. METHODS: A web-based survey was provided in both German and English language, comprising a maximum of 41 questions using branching logic within the REDCap web application. Only the results of participants with experience in the field of medical AI applications and complete questionnaires were included for analysis. Demographic data, technical expertise, and perceptions of fairness, as well as knowledge of biases in AI, were analyzed, and variations among gender, age, and work environment were assessed. RESULTS: A total of 151 AI specialists completed the web-based survey. The median age was 30 (IQR 26-39) years, and 67% (101/151) of respondents were male. One-third rated their AI development projects as fair (47/151, 31%) or moderately fair (51/151, 34%), 12% (18/151) reported their AI to be barely fair, and 1% (2/151) not fair at all. One participant identifying as diverse rated AI developments as barely fair, and among the 2 undefined gender participants, AI developments were rated as barely fair or moderately fair, respectively. Reasons for biases selected by respondents were lack of fair data (90/132, 68%), guidelines or recommendations (65/132, 49%), or knowledge (60/132, 45%). Half of the respondents worked with image data (83/151, 55%) from 1 center only (76/151, 50%), and 35% (53/151) worked with national data exclusively. CONCLUSIONS: This study shows that the perception of biases in AI overall is moderately fair. Gender minorities did not once rate their AI development as fair or very fair. Therefore, further studies need to focus on minorities and women and their perceptions of AI. The results highlight the need to strengthen knowledge about bias in AI and provide guidelines on preventing biases in AI health care applications.
Asunto(s)
Algoritmos , Inteligencia Artificial , Humanos , Femenino , Masculino , Adulto , Sesgo , Atención a la Salud , InternetRESUMEN
The COVID-19 pandemic has led to tremendous investment in clinical studies to generate much-needed knowledge on the prevention, diagnosis, treatment and long-term effects of the disease. Case report forms, comprised of questions and answers (variables), are commonly used to collect data in clinical trials. Maximizing the value of study data depends on data quality and on the ability to easily pool and share data from several sources. ISARIC, in collaboration with the WHO, has created a case report form that is available for use by the scientific community to collect COVID-19 trial data. One of such research initiatives collecting and analyzing multi-country and multi-cohort COVID-19 study data is the Horizon 2020 project ORCHESTRA. Following the ISO/TS 21564:2019 standard, a mapping between five ORCHESTRA studies' variables and the ISARIC Freestanding Follow-Up Survey elements was created. Measures of correspondence of shared semantic domain of 0 (perfect match), 1 (fully inclusive match), 2 (partial match), 4 (transformation required) or 4* (not present in ORCHESTRA) as compared to the target code system, ORCHESTRA study variables, were assigned to each of the elements in the ISARIC FUP case report form (CRF) which was considered the source code system. Of the ISARIC FUP CRF's variables, around 34% were found to show an exact match with corresponding variables in ORCHESTRA studies and about 33% showed a non-inclusive overlap. Matching variables provided information on patient demographics, COVID-19 testing, hospital admission and symptoms. More in-depth details are covered in ORCHESTRA variables with regards to treatment and comorbidities. ORCHESTRA's Long-Term Sequelae and Fragile population studies' CRFs include 32 and 27 variables respectively which were evaluated as a perfect match to variables in the ISARIC FUP CRF. Our study serves as an example of the kind of maps between case report form variables from different research projects needed to link ongoing COVID-19 research efforts and facilitate collaboration and data sharing. To enable data aggregation across two data systems, the information they contain needs to be connected through a map to determine compatibility and transformation needs. Combining data from various clinical studies can increase the power of analytical insights.
Asunto(s)
Prueba de COVID-19 , COVID-19 , Humanos , Estudios de Seguimiento , Pandemias , Semántica , COVID-19/epidemiología , FatigaRESUMEN
BACKGROUND: The COVID-19 outbreak has affected the lives of millions of people by causing a dramatic impact on many health care systems and the global economy. This devastating pandemic has brought together communities across the globe to work on this issue in an unprecedented manner. OBJECTIVE: This case study describes the steps and methods employed in the conduction of a remote online health hackathon centered on challenges posed by the COVID-19 pandemic. It aims to deliver a clear implementation road map for other organizations to follow. METHODS: This 4-day hackathon was conducted in April 2020, based on six COVID-19-related challenges defined by frontline clinicians and researchers from various disciplines. An online survey was structured to assess: (1) individual experience satisfaction, (2) level of interprofessional skills exchange, (3) maturity of the projects realized, and (4) overall quality of the event. At the end of the event, participants were invited to take part in an online survey with 17 (+5 optional) items, including multiple-choice and open-ended questions that assessed their experience regarding the remote nature of the event and their individual project, interprofessional skills exchange, and their confidence in working on a digital health project before and after the hackathon. Mentors, who guided the participants through the event, also provided feedback to the organizers through an online survey. RESULTS: A total of 48 participants and 52 mentors based in 8 different countries participated and developed 14 projects. A total of 75 mentorship video sessions were held. Participants reported increased confidence in starting a digital health venture or a research project after successfully participating in the hackathon, and stated that they were likely to continue working on their projects. Of the participants who provided feedback, 60% (n=18) would not have started their project without this particular hackathon and indicated that the hackathon encouraged and enabled them to progress faster, for example, by building interdisciplinary teams, gaining new insights and feedback provided by their mentors, and creating a functional prototype. CONCLUSIONS: This study provides insights into how online hackathons can contribute to solving the challenges and effects of a pandemic in several regions of the world. The online format fosters team diversity, increases cross-regional collaboration, and can be executed much faster and at lower costs compared to in-person events. Results on preparation, organization, and evaluation of this online hackathon are useful for other institutions and initiatives that are willing to introduce similar event formats in the fight against COVID-19.
Asunto(s)
COVID-19/terapia , Atención a la Salud/organización & administración , Internet , Adulto , COVID-19/epidemiología , Humanos , SARS-CoV-2/aislamiento & purificaciónRESUMEN
Public health research and epidemiological and clinical studies are necessary to understand the COVID-19 pandemic and to take appropriate action. Therefore, since early 2020, numerous research projects have also been initiated in Germany. However, due to the large amount of information, it is currently difficult to get an overview of the diverse research activities and their results. Based on the "Federated research data infrastructure for personal health data" (NFDI4Health) initiative, the "COVID-19 task force" is able to create easier access to SARS-CoV-2- and COVID-19-related clinical, epidemiological, and public health research data. Therefore, the so-called FAIR data principles (findable, accessible, interoperable, reusable) are taken into account and should allow an expedited communication of results. The most essential work of the task force includes the generation of a study portal with metadata, selected instruments, other study documents, and study results as well as a search engine for preprint publications. Additional contents include a concept for the linkage between research and routine data, a service for an enhanced practice of image data, and the application of a standardized analysis routine for harmonized quality assessment. This infrastructure, currently being established, will facilitate the findability and handling of German COVID-19 research. The developments initiated in the context of the NFDI4Health COVID-19 task force are reusable for further research topics, as the challenges addressed are generic for the findability of and the handling with research data.
Asunto(s)
Investigación Biomédica/tendencias , COVID-19 , Difusión de la Información , Alemania , Humanos , Metadatos , Pandemias , SARS-CoV-2RESUMEN
BACKGROUND: The current COVID-19 pandemic has led to a surge of research activity. While this research provides important insights, the multitude of studies results in an increasing fragmentation of information. To ensure comparability across projects and institutions, standard datasets are needed. Here, we introduce the "German Corona Consensus Dataset" (GECCO), a uniform dataset that uses international terminologies and health IT standards to improve interoperability of COVID-19 data, in particular for university medicine. METHODS: Based on previous work (e.g., the ISARIC-WHO COVID-19 case report form) and in coordination with experts from university hospitals, professional associations and research initiatives, data elements relevant for COVID-19 research were collected, prioritized and consolidated into a compact core dataset. The dataset was mapped to international terminologies, and the Fast Healthcare Interoperability Resources (FHIR) standard was used to define interoperable, machine-readable data formats. RESULTS: A core dataset consisting of 81 data elements with 281 response options was defined, including information about, for example, demography, medical history, symptoms, therapy, medications or laboratory values of COVID-19 patients. Data elements and response options were mapped to SNOMED CT, LOINC, UCUM, ICD-10-GM and ATC, and FHIR profiles for interoperable data exchange were defined. CONCLUSION: GECCO provides a compact, interoperable dataset that can help to make COVID-19 research data more comparable across studies and institutions. The dataset will be further refined in the future by adding domain-specific extension modules for more specialized use cases.
Asunto(s)
Investigación Biomédica , COVID-19 , Conjuntos de Datos como Asunto , Medicina , Consenso , Humanos , PandemiasRESUMEN
This paper presents an approach to enable interoperability of the research data management system XNAT by the implementation of the HL7 standards framework Fast Healthcare Interoperability Resources (FHIR). The FHIR implementation is realized as an XNAT plugin (Source code: https://github.com/somnonetz/xnat-fhir-plugin ), that allows easy adoption in arbitrary XNAT instances. The approach is demonstrated on patient data exchange between a FHIR reference implementation and XNAT.
Asunto(s)
Estándar HL7/organización & administración , Sistemas de Registros Médicos Computarizados/organización & administración , Neuroimagen/métodos , Manejo de Datos , Registros Electrónicos de Salud , Estándar HL7/normas , Humanos , Sistemas de Registros Médicos Computarizados/normas , Integración de SistemasRESUMEN
The four grand challenges of imaging researchincreasing evidence levels, enhancing global collaboration, improving research reporting quality, and sharing trial datacan be addressed, utilizing the tail wind of digital transformation, by consolidating actions of all stakeholders, with the ultimate goal of evidence-based, reproducible, generalizable, and broadly accepted results that will improve the quality and consistency of patient care.
Asunto(s)
Investigación Biomédica/normas , Diagnóstico por Imagen , Humanos , Difusión de la Información , Cooperación InternacionalRESUMEN
BACKGROUND: Medical documentation is no longer used primarily for administrative processes or healthcare billing, but for the entire electronic health record with accompanying eHealth use cases. OBJECTIVES: It shall be examined to what extent classifications such as the International Statistical Classification of Diseases and Related Health Problems (ICD-11) and the International Classification of Health Interventions (ICHI), in comparison to the international reference terminology SNOMED CT, meet the requirements of current eHealth applications and ensure interoperability. MATERIALS AND METHODS: The strengths and weaknesses of ICD-11 and ICHI are highlighted in terms of literature, contextual mapping within the international patient summary, telemedicine applications and the use in IT standards, such as HL7 in comparison to SNOMED CT. RESULTS: The whole range of medical terminology is not covered by ICHI and ICD-10, but with SNOMED CT, because ICD-11 and ICHI may be used in strict limitations to annotate procedures and diagnosis. A sample value set (nâ¯= 30) shows high mapping equivalence in SNOMED CT. In the literature, ICD-11 to SNOMED CT mappings are described as complex and error-prone. CONCLUSIONS: In terms of content expressivity and international usability, the potential of SNOMED CT in eHealth applications can be considered more favorable than ICD-11 or ICHI, even considering the original scope of these classifications, diagnoses and procedures. ICHI may even be recommended for specific use cases (e.â¯g. statistics).
Asunto(s)
Registros Electrónicos de Salud , Clasificación Internacional de Enfermedades , Systematized Nomenclature of Medicine , Telemedicina , Alemania , HumanosRESUMEN
In the international classifications ICD-10-WHO and ICD-11-WHO, many sex-specific diseases have incomplete coding. It is possible to further enhance semantic interoperability using SNOMED CT additionally to ICD. Part of the analysis of semantic interoperability of diagnoses in the ICD are Sexual Dysfunctions, Postpartum Depression, Sexual Assault, Premenstrual Tension Syndrome and Premenstrual Dysphoric Disorder, Female Genital Mutilation and Cutting, Gender Incongruence and Disorders of Breast. Labeling biases have been identified in all diagnoses, either in SNOMED CT or ICD. For mental disorders associated with pregnancy, gender incongruence and sexual violence the use of the GPS of SNOMED CT can help enhance semantic interoperability additionally to ICD.
Asunto(s)
Clasificación Internacional de Enfermedades , Systematized Nomenclature of Medicine , Humanos , Femenino , Masculino , Sexismo , SemánticaRESUMEN
This paper explores the critical role of Interoperability (IOP) in the integration of Artificial Intelligence (AI) for clinical applications. As AI gains prominence in medical analytics, its application in clinical practice faces challenges due to the lack of standardization in the medical sector. IOP, the ability of systems to exchange information seamlessly, emerges as a fundamental solution. Our paper discusses the indispensable nature of IOP throughout the Data Life Cycle, demonstrating how interoperable data can facilitate AI applications. The benefits of IOP encompass streamlined data entry for healthcare professionals, efficient data processing, enabling the sharing of data and algorithms for replication, and potentially increasing the significance of results obtained by medical data analytics via AI. Despite the challenges of IOP, its successful implementation promises substantial benefits for integrating AI into clinical practice, which could ultimately enhance patient outcomes and healthcare quality.
Asunto(s)
Inteligencia Artificial , Humanos , Interoperabilidad de la Información en Salud , Registros Electrónicos de Salud , Integración de SistemasRESUMEN
This paper explores key success factors for the development and implementation of a Common Data Model (CDM) for Rare Diseases (RDs) focusing on the European context. Several challenges hinder RD care and research in diagnosis, treatment, and research, including data fragmentation, lack of standardisation, and Interoperability (IOP) issues within healthcare information systems. We identify key issues and recommendations for an RD-CDM, drawing on international guidelines and existing infrastructure, to address organisational, consensus, interoperability, usage, and secondary use challenges. Based on these, we analyse the importance of balancing the scope and IOP of a CDM to cater to the unique requirements of RDs while ensuring effective data exchange and usage across systems. In conclusion, a well-designed RD-CDM can bridge gaps in RD care and research, enhance patient care and facilitate international collaborations.
Asunto(s)
Elementos de Datos Comunes , Enfermedades Raras , Humanos , Registros Electrónicos de Salud , Europa (Continente) , Interoperabilidad de la Información en Salud , Enfermedades Raras/terapiaRESUMEN
This work presents the Fast Healthcare Interoperability Resources (FHIR®) specification of the NFDI4Health Metadata schema based on FHIR Version 4: We created 16 profiles to facilitate the integration of clinical, epidemiological, and public health study data. Despite challenges arising from the extensive MDS as well as missing concepts in semantic standards, it marks a significant advance in applying information technology standards to health research.
Asunto(s)
Interoperabilidad de la Información en Salud , Estándar HL7 , Metadatos , Humanos , Registros Electrónicos de Salud , Estudios Epidemiológicos , Salud Pública , Investigación BiomédicaRESUMEN
Congenital heart disease (CHD) represents a significant challenge in prenatal care due to low prenatal detection rates. Artificial Intelligence (AI) offers promising avenues for precise CHD prediction. In this study we conducted a systematic review according to the PRISMA guidelines, investigating the landscape of AI applications in prenatal CHD detection. Through searches on PubMed, Embase, and Web of Science, 621 articles were screened, yielding 28 relevant studies for analysis. Deep Learning (DL) emerged as the predominant AI approach. Data types were limited to ultrasound and MRI sequences mainly. This comprehensive analysis provides valuable insights for future research and clinical practice in CHD detection using AI applications.
Asunto(s)
Inteligencia Artificial , Cardiopatías Congénitas , Cardiopatías Congénitas/diagnóstico por imagen , Humanos , Femenino , Embarazo , Diagnóstico Prenatal , Imagen por Resonancia Magnética , Ultrasonografía Prenatal , Aprendizaje ProfundoRESUMEN
Our novel Intelligent Tutoring System (ITS) architecture integrates HL7 Fast Healthcare Interoperability Resources (FHIR) for data exchange and Unified Medical Language System (UMLS) codes for content mapping.
Asunto(s)
Estándar HL7 , Unified Medical Language System , Interoperabilidad de la Información en Salud , Integración de Sistemas , HumanosRESUMEN
The German initiative "National Research Data Infrastructure for Personal Health Data" (NFDI4Health) focuses on research data management in health research. It aims to foster and develop harmonized informatics standards for public health, epidemiological studies, and clinical trials, facilitating access to relevant data and metadata standards. This publication lists syntactic and semantic data standards of potential use for NFDI4Health and beyond, based on interdisciplinary meetings and workshops, mappings of study questionnaires and the NFDI4Health metadata schema, and literature search. Included are 7 syntactic, 32 semantic and 9 combined syntactic and semantic standards. In addition, 101 ISO Standards from ISO/TC 215 Health Informatics and ISO/TC 276 Biotechnology could be identified as being potentially relevant. The work emphasizes the utilization of standards for epidemiological and health research data ensuring interoperability as well as the compatibility to NFDI4Health, its use cases, and to (inter-)national efforts within these sectors. The goal is to foster collaborative and inter-sectoral work in health research and initiate a debate around the potential of using common standards.
Asunto(s)
Interoperabilidad de la Información en Salud , Humanos , Metadatos , Alemania , Registros de Salud Personal , Manejo de DatosRESUMEN
Adhering to FAIR principles (findability, accessibility, interoperability, reusability) ensures sustainability and reliable exchange of data and metadata. Research communities need common infrastructures and information models to collect, store, manage and work with data and metadata. The German initiative NFDI4Health created a metadata schema and an infrastructure integrating existing platforms based on different information models and standards. To ensure system compatibility and enhance data integration possibilities, we mapped the Investigation-Study-Assay (ISA) model to Fast Healthcare Interoperability Resources (FHIR). We present the mapping in FHIR logical models, a resulting FHIR resources' network and challenges that we encountered. Challenges mainly related to ISA's genericness, and to different structures and datatypes used in ISA and FHIR. Mapping ISA to FHIR is feasible but requires further analyses of example data and adaptations to better specify target FHIR elements, and enable possible automatized conversions from ISA to FHIR.
Asunto(s)
Medicamentos Genéricos , Instituciones de Salud , Humanos , Metadatos , Atención a la SaludRESUMEN
The Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema was released in 2022 and approved by ISO as a standard for sharing clinical and genomic information about an individual, including phenotypic descriptions, numerical measurements, genetic information, diagnoses, and treatments. A phenopacket can be used as an input file for software that supports phenotype-driven genomic diagnostics and for algorithms that facilitate patient classification and stratification for identifying new diseases and treatments. There has been a great need for a collection of phenopackets to test software pipelines and algorithms. Here, we present phenopacket-store. Version 0.1.12 of phenopacket-store includes 4916 phenopackets representing 277 Mendelian and chromosomal diseases associated with 236 genes, and 2872 unique pathogenic alleles curated from 605 different publications. This represents the first large-scale collection of case-level, standardized phenotypic information derived from case reports in the literature with detailed descriptions of the clinical data and will be useful for many purposes, including the development and testing of software for prioritizing genes and diseases in diagnostic genomics, machine learning analysis of clinical phenotype data, patient stratification, and genotype-phenotype correlations. This corpus also provides best-practice examples for curating literature-derived data using the GA4GH Phenopacket Schema.
RESUMEN
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.