A Formal Model for the FAIR4Health Information Architecture.

In the EU project FAIR4Health, a ETL pipeline for the FAIRification of structured health data as well as an agent-based, distributed query platform for the analysis of research hypotheses and the training of machine learning models were developed. The system has been successfully tested in two clinical use cases with patient data from five university hospitals. Currently, the solution is also being considered for use in other hospitals. However, configuring the system and deploying it in the local IT architecture is non-trivial and meets with understandable concerns about security. This paper presents a model for describing the information architecture based on a formal approach, the 3LGM metamodel. The model was evaluated by the developers. As a result, the clear separation of tasks and the software components that implement them as well as the rich description of interactions via interfaces were positively emphasized.

From Raw Data to FAIR Data: The FAIRification Workflow for Health Research.

BACKGROUND: FAIR (findability, accessibility, interoperability, and reusability) guiding principles seek the reuse of data and other digital research input, output, and objects (algorithms, tools, and workflows that led to that data) making them findable, accessible, interoperable, and reusable. GO FAIR - a bottom-up, stakeholder driven and self-governed initiative - defined a seven-step FAIRification process focusing on data, but also indicating the required work for metadata. This FAIRification process aims at addressing the translation of raw datasets into FAIR datasets in a general way, without considering specific requirements and challenges that may arise when dealing with some particular types of data. OBJECTIVES: This scientific contribution addresses the architecture design of an open technological solution built upon the FAIRification process proposed by "GO FAIR" which addresses the identified gaps that such process has when dealing with health datasets. METHODS: A common FAIRification workflow was developed by applying restrictions on existing steps and introducing new steps for specific requirements of health data. These requirements have been elicited after analyzing the FAIRification workflow from different perspectives: technical barriers, ethical implications, and legal framework. This analysis identified gaps when applying the FAIRification process proposed by GO FAIR to health research data management in terms of data curation, validation, deidentification, versioning, and indexing. RESULTS: A technological architecture based on the use of Health Level Seven International (HL7) FHIR (fast health care interoperability resources) resources is proposed to support the revised FAIRification workflow. DISCUSSION: Research funding agencies all over the world increasingly demand the application of the FAIR guiding principles to health research output. Existing tools do not fully address the identified needs for health data management. Therefore, researchers may benefit in the coming years from a common framework that supports the proposed FAIRification workflow applied to health datasets. CONCLUSION: Routine health care datasets or data resulting from health research can be FAIRified, shared and reused within the health research community following the proposed FAIRification workflow and implementing technical architecture.

[A New Paradigm in Health Research: FAIR Data (Findable, Accessible, Interoperable, Reusable)]. / Um Novo Paradigma em Investigação em Saúde: Dados FAIR (Localizáveis, Acessíveis, Interoperáveis, Reutilizáveis).

The digital era, that we are living nowadays, is transforming health, health care models and services, and the role of society in this new reality. We currently have a large amount of stored health data, including clinical, biometric, and scientific research data. Nonetheless, its potential is not being fully exploited. It is essential to foster the sharing and reuse of this data not only in research but also towards the development of health technologies in order to improve health care efficiency, as well as products, services or digital health apps, to promote preventive and individualized medicine and to empower citizens in health literacy and self-management. In this sense, the FAIR concept has emerged, which implies that health data is findable, accessible, shared and reusable, facilitating interoperability between systems, ensuring the protection of personal and sensitive data. In this paper we review the FAIR concept, 'FAIRification' process, FAIR data versus open access data, ethical issues and the general data protection regulation, and digital health and citizen science.

Vivemos uma nova era digital que está a transformar a saúde, os modelos de cuidados e serviços de saúde, e o próprio papel da sociedade nesta realidade. Atualmente dispomos de uma grande quantidade de dados de saúde armazenados, incluindo dados clínicos, biométricos e de investigação científica, cuja potencialidade não está a ser devidamente explorada. É essencial favorecer a partilha e reutilização destes dados não só na investigação, como também para o desenvolvimento de tecnologias para melhorar a eficiência dos cuidados de saúde, de produtos ou serviços de saúde digitais, promover uma medicina preventiva e individualizada, mas também o empoderamento da população em literacia em saúde e na gestão da doença. Recentemente, surgiu o conceito FAIR que implica que os dados de saúde sejam facilmente localizáveis, acessíveis, partilhados e reutilizáveis, facilitando desta forma a interoperacionalidade entre sistemas e assegurando a proteção de dados pessoais e sensíveis. Neste artigo é feita uma revisão do conceito FAIR, processo de 'FAIRificação', dados FAIR versus dados de acesso livre, questões de éticas e o regulamento geral de proteção de dados, e saúde digital e ciência cidadã.

Comparison of Feature Selection Methods for Predicting RT-Induced Toxicity.

This work addresses a scoping review of Feature Selection (FS) methods applied to a Lung Cancer dataset to elucidate parameters' relevance when predicting radiotherapy (RT) induced toxicity. Subsetting-based and Ranking-based FS methods were implemented along with 4 advanced classifiers to predict the onset of RT-induced acute esophagitis, cough, pneumonitis and dyspnea. Their prediction performance was measured in terms of the AUC for each model to find the best FS.

ITCBio, a Clinical and Translational Research Platform.

An informatics platform has been designed, deployed and validated around the ITCBio initiative to provide support to clinical and translational research in Andalusia. To this end, an infrastructure has been developed which, in a scalable manner, incorporates functionalities aimed to facilitate the consistent definition of information models, the data reusability from electronic health records, as well as the analysis and processing of information. All this with the purpose of providing support to the different clinical and translational research processes associated with clinical trials and research projects. This initiative is based on the creation of a suite of applications that, through using standards, incorporates open-software tools intended to support these research processes. It is currently in widespread and growing use in university hospitals in which the platform is deployed.

Autonomous rehabilitation at stroke patients home for balance and gait: safety, usability and compliance of a virtual reality system.

BACKGROUND: New technologies, such as telerehabilitation and gaming devices offer the possibility for patients to train at home. This opens the challenge of safety for the patient as he/she is called to exercise neither with a therapist on the patients' side nor with a therapist linked remotely to supervise the sessions. AIM: To study the safety, usability and patient acceptance of an autonomous telerehabilitation system for balance and gait (the REWIRE platform) in the patients home. DESIGN: Cohort study. SETTING: Community, in the stroke patients' home. POPULATION: Fifteen participants with first-ever stroke, with a mild to moderate residual deficit of the lower extremities. METHODS: Autonomous rehabilitation based on virtual rehabilitation was provided at the participants' home for twelve weeks. The primary outcome was compliance (the ratio between days of actual and scheduled training), analyzed with the two-tailed Wilcoxon Mann-Whitney test. Furthermore safety is defined by adverse events. The secondary endpoint was the acceptance of the system measured with the Technology Acceptance Model (TAM). Additionally, the cumulative duration of weekly training was analyzed. RESULTS: During the study there were no adverse events related to the therapy. Patients performed on average 71% (range 39 to 92%) of the scheduled sessions. The TAM Questionnaire showed excellent values for stroke patients after the training. The average training duration per week was 99±53min. CONCLUSIONS: Autonomous telerehabilitation for balance and gait training with the REWIRE-system is safe, feasible and can help to intensive rehabilitative therapy at home. CLINICAL REHABILITATION IMPACT: Telerehabilitation enables safe training in home environment and supports of the standard rehabilitation therapy.

Validation of a method for retroperitoneal tumor segmentation.

PURPOSE: In 2005, an application for surgical planning called AYRA[Formula: see text] was designed and validated by different surgeons and engineers at the Virgen del Rocío University Hospital, Seville (Spain). However, the segmentation methods included in AYRA and in other surgical planning applications are not able to segment accurately tumors that appear in soft tissue. The aims of this paper are to offer an exhaustive validation of an accurate semiautomatic segmentation tool to delimitate retroperitoneal tumors from CT images and to aid physicians in planning both radiotherapy doses and surgery. METHODS: A panel of 6 experts manually segmented 11 cases of tumors, and the segmentation results were compared exhaustively with: the results provided by a surgical planning tool (AYRA), the segmentations obtained using a radiotherapy treatment planning system (Pinnacle[Formula: see text]), the segmentation results obtained by a group of experts in the delimitation of retroperitoneal tumors and the segmentation results using the algorithm under validation. RESULTS: 11 cases of retroperitoneal tumors were tested. The proposed algorithm provided accurate results regarding the segmentation of the tumor. Moreover, the algorithm requires minimal computational time-an average of 90.5% less than that required when manually contouring the same tumor. CONCLUSION: A method developed for the semiautomatic selection of retroperitoneal tumor has been validated in depth. AYRA, as well as other surgical and radiotherapy planning tools, could be greatly improved by including this algorithm.

Evaluation of clinical information modeling tools.

OBJECTIVE: Clinical information models are formal specifications for representing the structure and semantics of the clinical content within electronic health record systems. This research aims to define, test, and validate evaluation metrics for software tools designed to support the processes associated with the definition, management, and implementation of these models. METHODOLOGY: The proposed framework builds on previous research that focused on obtaining agreement on the essential requirements in this area. A set of 50 conformance criteria were defined based on the 20 functional requirements agreed by that consensus and applied to evaluate the currently available tools. RESULTS: Of the 11 initiative developing tools for clinical information modeling identified, 9 were evaluated according to their performance on the evaluation metrics. Results show that functionalities related to management of data types, specifications, metadata, and terminology or ontology bindings have a good level of adoption. Improvements can be made in other areas focused on information modeling and associated processes. Other criteria related to displaying semantic relationships between concepts and communication with terminology servers had low levels of adoption. CONCLUSIONS: The proposed evaluation metrics were successfully tested and validated against a representative sample of existing tools. The results identify the need to improve tool support for information modeling and software development processes, especially in those areas related to governance, clinician involvement, and optimizing the technical validation of testing processes. This research confirmed the potential of these evaluation metrics to support decision makers in identifying the most appropriate tool for their organization. OBJECTIVO: Los Modelos de Información Clínica son especificaciones para representar la estructura y características semánticas del contenido clínico en los sistemas de Historia Clínica Electrónica. Esta investigación define, prueba y valida un marco para la evaluación de herramientas informáticas diseñadas para dar soporte en la en los procesos de definición, gestión e implementación de estos modelos. METODOLOGIA: El marco de evaluación propuesto se basa en una investigación previa para obtener consenso en la definición de requisitos esenciales en esta área. A partir de los 20 requisitos funcionales acordados, un conjunto de 50 criterios de conformidad fueron definidos y aplicados en la evaluación de las herramientas existentes. RESULTADOS: Un total de 9 de las 11 iniciativas identificadas desarrollando herramientas para el modelado de información clínica fueron evaluadas. Los resultados muestran que las funcionalidades relacionadas con la gestión de tipos de datos, especificaciones, metadatos y mapeo con terminologías u ontologías tienen un buen nivel de adopción. Se identifican posibles mejoras en áreas relacionadas con los procesos de modelado de información. Otros criterios relacionados con presentar las relaciones semánticas entre conceptos y la comunicación con servidores de terminología tienen un bajo nivel de adopción. CONCLUSIONES: El marco de evaluación propuesto fue probado y validado satisfactoriamente contra un conjunto representativo de las herramientas existentes. Los resultados identifican la necesidad de mejorar el soporte de herramientas a los procesos de modelado de información y desarrollo de software, especialmente en las áreas relacionadas con gobernanza, participación de profesionales clínicos y la optimización de la validación técnica en los procesos de pruebas técnicas. Esta investigación ha confirmado el potencial de este marco de evaluación para dar soporte a los usuarios en la toma de decisiones sobre que herramienta es más apropiadas para su organización.

Clinical Decision Support using a Terminology Server to improve Patient Safety.

Clinical Decision Support Systems (CDSS) are software applications that support clinicians in making healthcare decisions providing relevant information for individual patients about their specific conditions. The lack of integration between CDSS and Electronic Health Record (EHR) has been identified as a significant barrier to CDSS development and adoption. Andalusia Healthcare Public System (AHPS) provides an interoperable health information infrastructure based on a Service Oriented Architecture (SOA) that eases CDSS implementation. This paper details the deployment of a CDSS jointly with the deployment of a Terminology Server (TS) within the AHPS infrastructure. It also explains a case study about the application of decision support to thromboembolism patients and its potential impact on improving patient safety. We will apply the inSPECt tool proposal to evaluate the appropriateness of alerts in this scenario.

Improving integrated care in chronic kidney failure patients with a standard-based interoperability framework.

This paper introduces the evaluation report after fostering a Standard-based Interoperability Framework (SIF) between the Virgen del Rocío University Hospital (VRUH) Haemodialysis (HD) Unit and 5 outsourced HD centres in order to improve integrated care by automatically sharing patients' Electronic Health Record (EHR) and lab test reports. A pre-post study was conducted during fourteen months. The number of lab test reports of both emergency and routine nature regarding to 379 outpatients was computed before and after the integration of the SIF. Before fostering SIF, 19.38 lab tests per patient were shared between VRUH and HD centres, 5.52 of them were of emergency nature while 13.85 were routine. After integrating SIF, 17.98 lab tests per patient were shared, 3.82 of them were of emergency nature while 14.16 were routine. The inclusion of a SIF in the HD Integrated Care Process has led to an average reduction of 1.39 (p=0.775) lab test requests per patient, including a reduction of 1.70 (p=0.084) in those of emergency nature, whereas an increase of 0.31 (p=0.062) was observed in routine lab tests. Fostering this strategy has led to the reduction in emergency lab test requests, which implies a potential improvement of the integrated care.