abstract: Blockchain technology enables a distributed and decentralized environment without any central authority. Healthcare is one industry in which blockchain is expected to have significant impacts. In recent years, the Healthcare Information Exchange(HIE) has been shown to benefit the healthcare industry remarkably. It has been shown that blockchain could help to improve multiple aspects of the HIE system. When Blockchain technology meets HIE, there are only a few proposed systems and they all suffer from the following two problems. First, the existing systems are not patient-centric in terms of data governance. Patients do not own their data and have no direct control over it. Second, there is no defined protocol among different systems on how to share sensitive data. To address the issues mentioned above, this paper proposes MedFabric4Me, a blockchain-based platform for HIE. MedFabric4Me is a patient-centric system where patients own their healthcare data and share on a need-to-know basis. First, analyzed the requirements for a patient-centric system which ensures tamper-proof sharing of data among participants. Based on the analysis, a Merkle root based mechanism is created to ensure that data has not tampered. Second, a distributed Proxy re-encryption system is used for secure encryption of data during storage and sharing of records. Third, combining off-chain storage and on-chain access management for both authenticability and privacy. MedFabric4Me is a two-pronged solution platform, composed of on-chain and off-chain components. The on-chain solution is implemented on the secure network of Hyperledger Fabric(HLF) while the off-chain solution uses Interplanetary File System(IPFS) to store data securely. Ethereum based Nucypher, a proxy re-encryption network provides cryptographic access controls to actors for encrypted data sharing. To demonstrate the practicality and scalability, a prototype solution of MedFabric4Me is implemented and evaluated the performance measure of the system against an already implemented HIE. Results show that decentralization technology like blockchain could help to mitigate some issues that HIE faces today, like transparency for patients, slow emergency response, and better access control. Finally, this research concluded with the benefits and shortcomings of MedFabric4Me with some directions and work that could benefit MedFabric4Me in terms of operation and performance. / Dissertation/Thesis / Masters Thesis Computer Engineering 2020

Yes / Interoperability within different healthcare systems (clinics/hospitals/pharmacies) remains an issue of further research due to a barrier in sharing of the patient’s Electronic Health Record (EHR) information. To solve this problem, cross healthcare system collaboration is required. This paper proposes an interoperability framework that enables a pharmacist to access an electronic version of the patient’s prescription from the doctor using a RESTFul API with ease. Semantic technology standards like Web Ontology Language (OWL), RDF (Resource Description Framework) and SPARQL (SPARQL Protocol and RDF Query Language) were used to implement the framework using JENA semantic framework tool to demonstrate how interoperability is achieved between a pharmacy and a clinic JENA was used to generate the ontology models for the pharmacy called pharmacy.rdf and clinic called clinic.rdf. The two models contain all the information from the two isolated systems. The JENA reasoner was used to merge the two ontology models into a single model.rdf file for easy querying with SPARQL. The model.rdf file was uploaded into a triple store database created using FUSEKI server. SPARQL Endpoint generated from FUSEKI was used to query the triple store database using a RESTFul API. The system was able to query the triple store database and output the results containing the prescription name and its details in JSON and XML formats which can be read by both machines and humans. / Supported by a Institutional Links grant, ID 261865161, under the Newton-Ristekdikti Fund partnership. The grant is funded by the UK Department for Business, Energy and Industrial Strategy and Indonesia Ministry of Research, Technology and Higher Education and delivered by the British Council.

Magister Commercii - MCom / Information and communication technologies (ICT) have changed the way healthcare processes are being documented. This results in better quality and ethical vigilance to ensure a more accurate form of data recordkeeping (Stevenson, Nilsson, Petersson & Johansson, 2010). Health care in South Africa, is facing major issues relating to patient care, such as delays in patients receiving medical care. According to the national Department of Health, the improvement of public healthcare facilities is crucial (McIntyre & Ataguba, 2017). Information and communication technology (ICT) has the ability to significantly alter the status of healthcare services in the Western Cape, which can be achieved through the role of an electronic healthcare record (EHR).

No description available.

No description available.

Electronic Health Record (EHR) creates a huge number of databases which are being updated dynamically. Major goal of interoperability in healthcare is to facilitate the seamless exchange of healthcare related data and an environment to supports interoperability and secure transfer of data. The health care organisations face difficulties in exchanging patient’s health care information and laboratory reports etc. due to a lack of semantic interoperability. Hence, there is a need of semantic web technologies for addressing healthcare interoperability problems by enabling various healthcare standards from various healthcare entities (doctors, clinics, hospitals etc.) to exchange data and its semantics which can be understood by both machines and humans. Thus, a framework with a similarity analyser has been proposed in the thesis that dealt with semantic interoperability. While dealing with semantic interoperability, another consideration was the use of word embedding and ontology for knowledge discovery. In medical domain, the main challenge for medical information extraction system is to find the required information by considering explicit and implicit clinical context with high degree of precision and accuracy. For semantic similarity of medical text at different levels (conceptual, sentence and document level), different methods and techniques have been widely presented, but I made sure that the semantic content of a text that is presented includes the correct meaning of words and sentences. A comparative analysis of approaches included ontology followed by word embedding or vice-versa have been applied to explore the methodology to define which approach gives better results for gaining higher semantic similarity. Selecting the Kidney Cancer dataset as a use case, I concluded that both approaches work better in different circumstances. However, the approach in which ontology is followed by word embedding to enrich data first has shown better results. Apart from enriching the EHR, extracting relevant information is also challenging. To solve this challenge, the concept of analogy has been applied to explain similarities between two different contents as analogies play a significant role in understanding new concepts. The concept of analogy helps healthcare professionals to communicate with patients effectively and help them understand their disease and treatment. So, I utilised analogies in this thesis to support the extraction of relevant information from the medical text. Since accessing EHR has been challenging, tweets text is used as an alternative for EHR as social media has appeared as a relevant data source in recent years. An algorithm has been proposed to analyse medical tweets based on analogous words. The results have been used to validate the proposed methods. Two experts from medical domain have given their views on the proposed methods in comparison with the similar method named as SemDeep. The quantitative and qualitative results have shown that the proposed analogy-based method bring diversity and are helpful in analysing the specific disease or in text classification.

Despite a Presidential Order in 2004 that launched national incentives for the use of health information technology, specifically the Electronic Health Record (EHR), adoption of the EHR has been slow. This study attempts to quantify factors associated with adoption of the EHR and Computerized Provider Order Entry (CPOE) by combining multiple organizational theories and empirical studies. The study is conducted in two phases. The primary phase of this study identifies and evaluates the effects of external environmental and internal organizational factors on healthcare organizations to adopt the EHR. From secondary data, twelve IVs (df=19) are chosen based on existing models and literature. Logistic regression is used to determine the association between the environmental factors and EHR adoption. The secondary phase of this study examines the adoption of five variations of CPOE using the same IVs from phase one. This EHR component of CPOE is chosen due to its promotion as a solution to help cross the quality chasm (IOM, 2001). Secondary data are analyzed and logistic regression is used to quantify the association between the factors of EHR adoption and CPOE adoption. Eleven of the twelve IVs are significant between the two phases (p<.1). This study uses data from 2009 because the HITECH Act was passed that year and significant government incentives were offered for those health care organizations (HCOs) that meet the qualifications of meaningful use. This study serves as a baseline for future studies, extends the work of other empirical studies, and fills a gap in the literature concerning factors associated with the adoption of the EHR and specific dimensions of CPOE. The Kruse Theory developed is strongly based in literature and reflects complexity commensurate with the health care industry.

Indiana University-Purdue University Indianapolis (IUPUI) / With the increasing availability of Electronic Health Records (EHRs) and advances in deep learning techniques, developing deep predictive models that use EHR data to solve healthcare problems has gained momentum in recent years. The majority of clinical predictive models benefit from structured data in EHR (e.g., lab measurements and medications). Still, learning clinical outcomes from all possible information sources is one of the main challenges when building predictive models. This work focuses mainly on two sources of information that have been underused by researchers; unstructured data (e.g., clinical notes) and a patient network. We propose a novel hybrid deep learning model, DeepNote-GNN, that integrates clinical notes information and patient network topological structure to improve 30-day hospital readmission prediction. DeepNote-GNN is a robust deep learning framework consisting of two modules: DeepNote and patient network. DeepNote extracts deep representations of clinical notes using a feature aggregation unit on top of a state-of-the-art Natural Language Processing (NLP) technique - BERT. By exploiting these deep representations, a patient network is built, and Graph Neural Network (GNN) is used to train the network for hospital readmission predictions. Performance evaluation on the MIMIC-III dataset demonstrates that DeepNote-GNN achieves superior results compared to the state-of-the-art baselines on the 30-day hospital readmission task. We extensively analyze the DeepNote-GNN model to illustrate the effectiveness and contribution of each component of it. The model analysis shows that patient network has a significant contribution to the overall performance, and DeepNote-GNN is robust and can consistently perform well on the 30-day readmission prediction task. To evaluate the generalization of DeepNote and patient network modules on new prediction tasks, we create a multimodal model and train it on structured and unstructured data of MIMIC-III dataset to predict patient mortality and Length of Stay (LOS). Our proposed multimodal model consists of four components: DeepNote, patient network, DeepTemporal, and score aggregation. While DeepNote keeps its functionality and extracts representations of clinical notes, we build a DeepTemporal module using a fully connected layer stacked on top of a one-layer Gated Recurrent Unit (GRU) to extract the deep representations of temporal signals. Independent to DeepTemporal, we extract feature vectors of temporal signals and use them to build a patient network. Finally, the DeepNote, DeepTemporal, and patient network scores are linearly aggregated to fit the multimodal model on downstream prediction tasks. Our results are very competitive to the baseline model. The multimodal model analysis reveals that unstructured text data better help to estimate predictions than temporal signals. Moreover, there is no limitation in applying a patient network on structured data. In comparison to other modules, the patient network makes a more significant contribution to prediction tasks. We believe that our efforts in this work have opened up a new study area that can be used to enhance the performance of clinical predictive models.

[ES] La interoperabilidad semántica de la información sanitaria es un requisito imprescindible para la sostenibilidad de la atención sanitaria, y es fundamental para afrontar los nuevos retos sanitarios de un mundo globalizado. Esta tesis aporta nuevas metodologías para abordar algunos de los aspectos fundamentales de la interoperabilidad semántica, específicamente aquellos relacionados con la definición y gobernanza de modelos de información clínica expresados en forma de arquetipo. Las aportaciones de la tesis son: - Estudio de las metodologías de modelado existentes de componentes de interoperabilidad semántica que influirán en la definición de una metodología de modelado de arquetipos. - Análisis comparativo de los sistemas e iniciativas existentes para la gobernanza de modelos de información clínica. - Una propuesta de Metodología de Modelado de Arquetipos unificada que formalice las fases de desarrollo del arquetipo, los participantes requeridos y las buenas prácticas a seguir. - Identificación y definición de principios y características de gobernanza de arquetipos. - Diseño y desarrollo de herramientas que brinden soporte al modelado y la gobernanza de arquetipos. Las aportaciones de esta tesis se han puesto en práctica en múltiples proyectos y experiencias de desarrollo. Estas experiencias varían desde un proyecto local dentro de una sola organización que requirió la reutilización de datos clínicos basados en principios de interoperabilidad semántica, hasta el desarrollo de proyectos de historia clínica electrónica de alcance nacional. / [CA] La interoperabilitat semàntica de la informació sanitària és un requisit imprescindible per a la sostenibilitat de l'atenció sanitària, i és fonamental per a afrontar els nous reptes sanitaris d'un món globalitzat. Aquesta tesi aporta noves metodologies per a abordar alguns dels aspectes fonamentals de la interoperabilitat semàntica, específicament aquells relacionats amb la definició i govern de models d'informació clínica expressats en forma d'arquetip. Les aportacions de la tesi són: - Estudi de les metodologies de modelatge existents de components d'interoperabilitat semàntica que influiran en la definició d'una metodologia de modelatge d'arquetips. - Anàlisi comparativa dels sistemes i iniciatives existents per al govern de models d'informació clínica. - Una proposta de Metodologia de Modelatge d'Arquetips unificada que formalitza les fases de desenvolupament de l'arquetip, els participants requerits i les bones pràctiques a seguir. - Identificació i definició de principis i característiques de govern d'arquetips. - Disseny i desenvolupament d'eines que brinden suport al modelatge i al govern d'arquetips. Les aportacions d'aquesta tesi s'han posat en pràctica en múltiples projectes i experiències de desenvolupament. Aquestes experiències varien des d'un projecte local dins d'una sola organització que va requerir la reutilització de dades clíniques basades en principis d'interoperabilitat semàntica, fins al desenvolupament de projectes d'història clínica electrònica d'abast nacional. / [EN] Semantic interoperability of health information is an essential requirement for the sustainability of healthcare, and it is essential to face the new health challenges of a globalized world. This thesis provides new methodologies to tackle some of the fundamental aspects of semantic interoperability, specifically those aspects related to the definition and governance of clinical information models expressed in the form of archetypes. The contributions of the thesis are: - Study of existing modeling methodologies of semantic interoperability components that will influence in the definition of an archetype modeling methodology. - Comparative analysis of existing clinical information model governance systems and initiatives. - A proposal of a unified Archetype Modeling Methodology that formalizes the phases of archetype development, the required participants, and the good practices to be followed. - Identification and definition of archetype governance principles and characteristics. - Design and development of tools that provide support to archetype modeling and governance. The contributions of this thesis have been put into practice in multiple projects and development experiences. These experiences vary from a local project inside a single organization that required a reuse on clinical data based on semantic interoperability principles, to the development of national electronic health record projects. / This thesis was partially funded by the Ministerio de Economía y Competitividad, ayudas para contratos para la formación de doctores en empresas “Doctorados Industriales”, grant DI-14-06564 and by the Agencia Valenciana de la Innovación, ayudas del Programa de Promoción del Talento – Doctorados empresariales (INNODOCTO), grant INNTA3/2020/12. / Moner Cano, D. (2021). Archetype development and governance methodologies for the electronic health record [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/164916

[ES] La consistencia de los datos de la HCE, como dimensión de la calidad, se considera un requisito esencial para la mejora de la prestación de la asistencia sanitaria, los procesos de toma de decisiones clínicas y la promoción de la investigación clínica. En este contexto, la cooperación entre la información y los modelos de dominio se considera esencial en la literatura, pero la comunidad científica no la ha abordado adecuadamente hasta la fecha. La contribución principal de esta tesis es el desarrollo de métodos y herramientas para la inclusión de expresiones de enlaces terminológicos en reglas de consistencia. Las contribuciones específicas son: - Definición de un método para ejecutar ECs sobre una base de datos de SNOMED CT orientada a grafos. - Definición de métodos para simplificar ECs antes y después de su ejecución, y su validación semántica conforme al Machine Readable Concept Model de SNOMED CT (MRCM). - Definición de un método para visualizar, explorar dinámicamente, comprender y validar subconjuntos de SNOMED CT. - Desarrollo de SNQuery, una plataforma que ejecuta, simplifica y valida ECs y visualiza los subconjuntos resultantes. - Definición de EHRules, un lenguaje de expresiones basado en el openEHR Expression Language para la especificación de reglas de consistencia en arquetipos, incluido el enlace terminológico de contenido, con el fin de enriquecer los arquetipos con conocimiento del dominio. - Definición de un método para ejecutar las expresiones de EHRules con el fin de validar la consistencia de los datos de la HCE mediante la ejecución de dichas expresiones sobre instancias de datos de pacientes. Nuestro objetivo es que estas contribuciones ayuden a mejorar la calidad de la HCE, ya que proporcionan métodos y herramientas para la validación y mejora de la consistencia de los datos de la HCE. Pretendemos, además, mediante la definición de enlaces de contenido entre modelos de información y terminologías clínicas, elevar el nivel de interoperabilidad semántica, para lo cual la definición de enlaces terminológicos es crucial. / [CA] La consistència de les dades de la HCE, com a dimensió de la qualitat, es considera un requisit essencial per a la millora de la prestació de l'assistència sanitària, els processos de presa de decisions clíniques i la promoció de la investigació clínica. En aquest context, la cooperació entre la informació i els models de domini es considera essencial en la literatura, però la comunitat científica no l'ha abordada adequadament fins hui. La contribució principal d'aquesta tesi és el desenvolupament de mètodes i ferramentes per a la inclusió d'expressions d'enllaços terminològics en regles de consistència. Les contribucions específiques són: - Definició d'un mètode per a executar ECs sobre una base de dades de SNOMED CT orientada a grafs. - Definició de mètodes per a simplificar ECs abans i després de la seua execució, i la seua validació semàntica conforme al Machine Readable Concept Model de SNOMED CT (MRCM). - Definició d'un mètode per a visualitzar, explorar dinàmicament, comprendre i validar subconjunts de SNOMED CT. - Desenvolupament de SNQuery, una plataforma que executa, simplifica i valida ECs i visualitza els subconjunts resultants. - Definició de EHRules, un llenguatge d'expressions basat en l'openEHR Expression Language per a l'especificació de regles de consistència en arquetips, inclòs l'enllaç terminològic de contingut, amb la finalitat d'enriquir els arquetips amb coneixement del domini. - Definició d'un mètode per a executar les expressions de EHRules amb la finalitat de validar la consistència de les dades de la HCE mitjançant l'execució d'aquestes expressions sobre instàncies de dades de pacients. El nostre objectiu és que aquestes contribucions ajuden a millorar la qualitat de la HCE, ja que proporcionen mètodes i ferramentes per a la validació i millora de la consistència de les dades de la HCE. Pretenem, a més, mitjançant la definició d'enllaços de contingut entre models d'informació i terminologies clíniques, elevar el nivell d'interoperabilitat semàntica, per a la qual cosa la definició d'enllaços terminològics és crucial. / [EN] Consistency of EHR data, as a dimension of quality, is considered an essential requirement to the improvement of healthcare delivery, clinical decision-making processes, and the promotion of clinical research. In this context, cooperation between information and domain models has been considered essential in the literature, but it has not been adequately addressed by the scientific community to date. The main contribution of this thesis is the development of methods and tools for the inclusion of terminology binding expressions in consistency rules. Specific contributions are: - Definition of a method to execute ECs over a SNOMED CT graph-oriented database. - Definition of methods to simplify ECs before and after its execution and semantic validation according to the SNOMED CT Machine Readable Concept Model (MRCM). - Definition of a method to visualize, dynamically explore, understand and validate SNOMED CT subsets. - Development of SNQuery, an execution platform that executes, simplifies and validates ECs, and visualizes the resulting subsets. - Definition of EHRules, an expression language based on the openEHR Expression Language for the specification of consistency expressions in archetypes, including value set bindings, in order to enrich archetypes with domain knowledge. - Definition of a method to execute EHRules expressions in order to validate the consistency of EHR data by executing such rules over patient data instances. Our objective is that these contributions help to enhance the quality of EHR, as they provide methods and tools for the validation and enhancement of the EHR data consistency. We also intend, by defining value set bindings between information models and clinical terminologies, to raise the level of semantic interoperability, for which the definition of terminological bindings is crucial. / This thesis was partially funded by Ministerio de Economía y Competitividad, “Doctorados Industriales”, grant DIN2018-009951, and by Universitat Politècnica de València, “Formación de Personal Investigador” (FPI-UPV). / Giménez Solano, VM. (2021). Enrichment of Archetypes with Domain Knowledge to Enhance the Consistency of Electronic Health Records [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/180082