RESUMEN
BACKGROUND: Data science offers an unparalleled opportunity to identify new insights into many aspects of human life with recent advances in health care. Using data science in digital health raises significant challenges regarding data privacy, transparency, and trustworthiness. Recent regulations enforce the need for a clear legal basis for collecting, processing, and sharing data, for example, the European Union's General Data Protection Regulation (2016) and the United Kingdom's Data Protection Act (2018). For health care providers, legal use of the electronic health record (EHR) is permitted only in clinical care cases. Any other use of the data requires thoughtful considerations of the legal context and direct patient consent. Identifiable personal and sensitive information must be sufficiently anonymized. Raw data are commonly anonymized to be used for research purposes, with risk assessment for reidentification and utility. Although health care organizations have internal policies defined for information governance, there is a significant lack of practical tools and intuitive guidance about the use of data for research and modeling. Off-the-shelf data anonymization tools are developed frequently, but privacy-related functionalities are often incomparable with regard to use in different problem domains. In addition, tools to support measuring the risk of the anonymized data with regard to reidentification against the usefulness of the data exist, but there are question marks over their efficacy. OBJECTIVE: In this systematic literature mapping study, we aim to alleviate the aforementioned issues by reviewing the landscape of data anonymization for digital health care. METHODS: We used Google Scholar, Web of Science, Elsevier Scopus, and PubMed to retrieve academic studies published in English up to June 2020. Noteworthy gray literature was also used to initialize the search. We focused on review questions covering 5 bottom-up aspects: basic anonymization operations, privacy models, reidentification risk and usability metrics, off-the-shelf anonymization tools, and the lawful basis for EHR data anonymization. RESULTS: We identified 239 eligible studies, of which 60 were chosen for general background information; 16 were selected for 7 basic anonymization operations; 104 covered 72 conventional and machine learning-based privacy models; four and 19 papers included seven and 15 metrics, respectively, for measuring the reidentification risk and degree of usability; and 36 explored 20 data anonymization software tools. In addition, we also evaluated the practical feasibility of performing anonymization on EHR data with reference to their usability in medical decision-making. Furthermore, we summarized the lawful basis for delivering guidance on practical EHR data anonymization. CONCLUSIONS: This systematic literature mapping study indicates that anonymization of EHR data is theoretically achievable; yet, it requires more research efforts in practical implementations to balance privacy preservation and usability to ensure more reliable health care applications.
RESUMEN
BACKGROUND: Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records data for identifying such patients can ultimately help provide better health outcomes. OBJECTIVE: Our study investigated the performance of predictive models to forecast HbA1c elevation levels by employing several machine learning models. We also examined the use of patient electronic health record longitudinal data in the performance of the predictive models. Explainable methods were employed to interpret the decisions made by the black box models. METHODS: This study employed multiple logistic regression, random forest, support vector machine, and logistic regression models, as well as a deep learning model (multilayer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large data set from Saudi Arabia with 18,844 unique patient records. RESULTS: The machine learning models achieved promising results for predicting current HbA1c elevation risk. When coupled with longitudinal data, the machine learning models outperformed the multiple logistic regression model used in the comparative study. The multilayer perceptron model achieved an accuracy of 83.22% for the area under receiver operating characteristic curve when used with historical data. All models showed a close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data. CONCLUSIONS: This study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels (≥5.7% or less). Using patients' longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.
RESUMEN
BACKGROUND: Electronic health record (EHR) systems generate large datasets that can significantly enrich the development of medical predictive models. Several attempts have been made to investigate the effect of glycated hemoglobin (HbA1c) elevation on the prediction of diabetes onset. However, there is still a need for validation of these models using EHR data collected from different populations. OBJECTIVE: The aim of this study is to perform a replication study to validate, evaluate, and identify the strengths and weaknesses of replicating a predictive model that employed multiple logistic regression with EHR data to forecast the levels of HbA1c. The original study used data from a population in the United States and this differentiated replication used a population in Saudi Arabia. METHODS: A total of 3 models were developed and compared with the model created in the original study. The models were trained and tested using a larger dataset from Saudi Arabia with 36,378 records. The 10-fold cross-validation approach was used for measuring the performance of the models. RESULTS: Applying the method employed in the original study achieved an accuracy of 74% to 75% when using the dataset collected from Saudi Arabia, compared with 77% obtained from using the population from the United States. The results also show a different ranking of importance for the predictors between the original study and the replication. The order of importance for the predictors with our population, from the most to the least importance, is age, random blood sugar, estimated glomerular filtration rate, total cholesterol, non-high-density lipoprotein, and body mass index. CONCLUSIONS: This replication study shows that direct use of the models (calculators) created using multiple logistic regression to predict the level of HbA1c may not be appropriate for all populations. This study reveals that the weighting of the predictors needs to be calibrated to the population used. However, the study does confirm that replicating the original study using a different population can help with predicting the levels of HbA1c by using the predictors that are routinely collected and stored in hospital EHR systems.
RESUMEN
We investigated the reasons why the transition from paper to electronically formatted records during patient handover between ambulance crews and emergency department staff in a North East England Emergency Department has not always been viewed positively. Interviews with seven paramedics and three emergency department staff were conducted in addition to observations of 74 ambulance staff during 37 handovers in the emergency department. In just over half of the handovers (20), paramedics found it necessary to provide written information to aid emergency department staff, in addition to that recorded electronically. There were a number of issues that impeded the ready utilisation of electronic records in this context. The major factors identified as contributing to this were the choice of system architecture, the design of user interfaces, and the procurement process used by the National Health Service. We have made some suggestions about how the system could evolve from one focused on providing management information to one that also supports operational needs.
Asunto(s)
Servicios Médicos de Urgencia/normas , Servicio de Urgencia en Hospital/normas , Pase de Guardia/normas , Ambulancias , Actitud del Personal de Salud , Comunicación , Servicios Médicos de Urgencia/métodos , Servicios Médicos de Urgencia/estadística & datos numéricos , Servicio de Urgencia en Hospital/organización & administración , Servicio de Urgencia en Hospital/estadística & datos numéricos , Inglaterra , Humanos , Pase de Guardia/estadística & datos numéricos , Medicina Estatal/organización & administración , Medicina Estatal/estadística & datos numéricosRESUMEN
With the continued expansion of electronic patient record systems ahead of comprehensive evidence, metrics, or future-proofing, health informatics in Europe and beyond is embarking on a faith-driven adventure that also risks data swamping of end-users. An alternative approach is an information broker system, drawing from departmental data sources. A 3-year study in health and social care has produced a first demonstrator which can search for specified information in heterogeneous distributed data stores, with source-specific permission can copy it, and then merge the search results into one integrated picture in a real-time process which is also captured in an audit system. The research project has addressed a number of issues during the study, including updating the concepts of role-based access, semantic interoperability, and harnessing web-based services bound at the time of need. A demonstrator now exists, and provides a platform for further application and development research. This paper summarises how this opens up a viable alternative approach for the next generation of health record systems, enabling record searching and integration as and when it is needed for specific patient-related purposes, whilst being independent of organisations, diagnostic approaches, or service delivery structures, and reducing the risks of data swamping.
Asunto(s)
Gestión de la Información/métodos , Internet , Sistemas de Registros Médicos Computarizados/organización & administración , Programas Informáticos , Acceso a la Información , Eficiencia Organizacional , Humanos , Almacenamiento y Recuperación de la Información , Aplicaciones de la Informática MédicaRESUMEN
Software services offer the opportunity to use a component-based approach for the design of applications. However, this needs a deeper understanding of how to develop service-based applications in a systematic manner, and of the set of properties that need to be included in the 'design model'. We have used a realistic application to explore systematically how service-based designs can be created and described. We first identified the key properties of an SOA (service oriented architecture) and then undertook a single-case case study to explore its use in the development of a design for a large-scale application in energy engineering, modelling this with existing notations wherever possible. We evaluated the resulting design model using two walkthroughs with both domain and application experts. We were able to successfully develop a design model around the ten properties identified, and to describe it by adapting existing design notations. A component-based approach to designing such systems does appear to be feasible. However, it needs the assistance of a more integrated set of notations for describing the resulting design model.
Asunto(s)
Modelos Teóricos , Diseño de Software , Programas Informáticos , Sistemas de ComputaciónRESUMEN
We describe a prototype information broker that has been developed to address typical healthcare information needs, using web services to obtain data from autonomous, heterogeneous sources. Some key features are reviewed: how data sources are turned into data services; how we enforce a distributed access control policy; and how semantic interoperability is achieved between the broker and its data services. Finally, we discuss the role that such a broker might have in a Grid context, as well as the limitations this reveals in current Grid provision.
Asunto(s)
Gestión de la Información/métodos , Servicios de Información , Sistemas de Información/organización & administración , Sistemas de Computación , Humanos , Gestión de la Información/instrumentación , Almacenamiento y Recuperación de la Información , Reino Unido , Interfaz Usuario-Computador , Vocabulario ControladoRESUMEN
With the continued expansion of Electronic Patient Record systems ahead of comprehensive evidence, metrics, or future-proofing, European health informatics is embarking on a faith-driven adventure that also risks data swamping of end-users. An alternative approach is an information broker system, drawing from departmental data sources. A three-year study in health and social care has produced a first demonstrator which can search for specified information in heterogeneous distributed data stores, with source-specific permission can copy it, and then merge the search results in a real-time process.