-
Sullivan Barnes posted an update 9 months, 2 weeks ago
Proper algorithms can be used to identify patients with HF.This paper presents an application of deep neural networks (DNN) to identify patients with Alcohol Use Disorder based on historical electronic health records. Our methodology consists of four stages including data collection, preprocessing, predictive model development, and validation. Data are collected from two sources and labeled into three classes including Normal, Hazardous, and Harmful drinkers. Moreover, problems such as imbalanced classes, noise, and categorical variables were handled. A four-layer fully-connected feedforward DNN architecture was designed and developed to predict Normal, Hazardous, and Harmful drinkers. Results show that our proposed method could successfully classify about 96%, 82%, and 89% of Normal, Hazardous, and Harmful drinkers, respectively, which is better than classical machine learning approaches.Pseudonymization plays a vital role in medical research. In Germany, the Technologie- und Methodenplattform für die vernetzte medizinische Forschung e.V. (TMF) has developed guidelines on how to create pseudonyms and how to handle personally identifiable information (PII) during this process. An open-source implementation of a pseudonymization service following these guidelines and therefore recommended by the TMF is the so-called “Mainzelliste”. This web application supports a REST-API for (de-) pseudonymization. For security reasons, a complex session and tokening mechanism for each (de-) pseudonymization is required and a careful interaction between front- and backend to ensure a correct handling of PII. The objective of this work is the development of a library to simplify the integration and usage of the Mainzelliste’s API in a TMF conform way. The frontend library uses JavaScript while the backend component is based on Java with an optional Spring Boot extension. The library is available under MIT open-source license from https//github.com/DanielPreciado-Marquez/MainzelHandler.With advances in Digital Health (DH) tools, it has become much easier to collect, use, and share patient-generated health data (PGHD). Entinostat This wealth of data could be efficiently used in monitoring and controlling chronic illnesses as well as predicting health outcome. Although integrating PGHD into clinical practice is currently in a promising stage, there are several technical challenges and usage barriers that hinder the full utilization of the PGHD potential in clinical care and research. This paper aims to address PGHD opportunities and challenges while developing the DH-Convener project to integrate PGHD into the Electronic Health Record in Austria (ELGA). Accordingly, it provides an integrative technical-clinical-user approach for developing a fully functional health ecosystem for exchanging integrated data among patients, healthcare providers, and researchers.Blood products and their derivatives are perishable commodities that require an efficient inventory management to ensure both a low wastage rate and a high product availability rate. To optimize blood product inventory, blood transfusion services need to reduce wastage by avoiding outdates and improve availability of different blood products. We used advance visualization techniques to design and develop a highly interactive real-time web-based dashboard to monitor the blood product inventory and the on-going blood unit transactions in near-real-time based on analysis of transactional data. Blood transfusion staff use the dashboard to locate units with specific characteristics, investigate the lifecycle of the units, and efficiently transfer units between facilities to minimize outdates.
Clinical pathways represents the sequence of interventions from which the patients benefit during their encounters with health care structures. There are several complex issues which make it difficult to represent these pathways (e.g. high numbers of patients, heterogeneity of variables).
We developed a tool to automate the representation of clinical pathways, from an individual and population points of view, and based on the OMOP CDM. The tool implemented the Sankey diagram in three stages (i) data extraction, (ii) generation of individual sequence of steps and (iii) aggregation of sequence to obtain the population-level diagram. We tested the tool with three surgery procedures the total hip replacement, the coronary bypass and the transcatheter aortic valve implantation.
The tool provided different ways of visualizing pathways depending on the question asked a pathway before a surgery, the pathway of deceased patients or the complete pathway with different steps of interest.
We proposed a tool automating the representation of the clinical pathways, and reducing complexity of visualization. Representations are detailed from an individual and population points of view. It has been tested with three surgical procedures. The tool functionalities will be extended to cover a greater number of use cases.
We proposed a tool automating the representation of the clinical pathways, and reducing complexity of visualization. Representations are detailed from an individual and population points of view. It has been tested with three surgical procedures. The tool functionalities will be extended to cover a greater number of use cases.The terminology services, defined as part of the emerging FHIR standard, yield a promising approach to finally achieve a common handling of coding systems needed for semantic interoperability. As a precondition, legacy terminology data must be transformed into FHIR-compatible resources whereby varying source formats make a manual case-by-case solution impracticable. In this work, the practicability of using CSIRO’s Ontoserver and the related Snapper tool as support of the transformation process were evaluated by applying them to the German Alpha-ID terminology.To facilitate personalised healthcare provision across Europe, we envision solutions that enable the secure integration and sharing of medical health records. These solutions should address privacy concerns, such as granular access control to personal data, establishing what should be accessible when and by whom, whilst complying with collective regulatory frameworks such as the European General Data Protection Regulation (GDPR) and adhering to international standards on how to manage information security. The proposed healthcare system design integrates technologies such as blockchain and scalable data lakes with adequate system routines to guarantee the secure access of confidential data. In this paper, we present the essential architectural components for the secure integration of medical records in a blockchain-based platform. We present a patient-centric data retrieval approach which incorporates a structured format to compose access rules.