Studies in health technology and informatics最新文献

The German National Medication Plan (GNMP) can be a valuable and interoperable data source for clinical studies, due to its digital specification and mandatory provisioning for chronically ill patients. Digital transfer of a patients current GNMP from the Patient Data Management System (PDMS) into electronic case report forms would avoid error prone manual data capturing. It is also essential for studies in practice-based research networks (PBRN), where data capturing must have as little impact as possible on everyday practice. The following issues are currently preventing seamless digital integration: There is no standardized interoperable export of the GNMP from PDMS. In the current form, pharmaceutical catalogs are needed to decode the contained pharmaceutical registration numbers. As accessibility to the pharmaceutical catalogs is restricted, there is no generic access to the actual information needed for study data evaluation. In order to conduct studies, feasible workarounds for these issues had to be implemented in the standard operating procedures, tools and participating GP practices. To overcome the GNMP's current lack of digital interoperability, the proposed solution combines semi-automated data export from PDMS at the GP practice and manual database search at the study center with a semi-automated processing pipeline to balance workload between GP practices, study management and evaluation.

The paper presents perceptions and feedback from speech therapists and parents embracing the idea of using digital tools in improving the language of the children with speech disorders. The authors investigated the perception of speech therapists and parents and their readiness to use digital tools in speech therapy starting from several digital applications from the domain. The feedback was positive, 88.3% of the parents agree to use digital apps at home, between face-to-face speech therapy sessions coordinated by speech therapists and 75% of parents agree to use them several days a week.

Medication review is a collaborative process between pharmacists and general practitioners (GPs) aimed at optimizing patient care by identifying and eliminating harmful medications. This paper proposes a collaborative platform to enhance pharmacist-GP interactions, assess drug-drug interactions, evaluate adverse effects, and manage dosages. The platform uses the issue mapping function of IBIS to structure dialogues and systematically evaluates proposed actions using the QuAD framework to support decision-making. An ontology based on medical knowledge ensures consistency, while visual enhancements such as varying edge width, color coding, and highlighting preferred actions enable swift, informed decisions. These tools improve collaboration and patient care outcomes.

Precision Forestry is an emerging approach that uses digital technologies for data-driven decision-making in environmental management. Traditional methods for assessing tree risk are often subjective and focus on individual trees using mechanical approaches. The #SecureTree model offers an innovative alternative by deploying sensors to measure biophysical parameters like temperature, humidity, and acceleration. Data from these sensors is processed to create a risk assessment map based on the progression of trees' behaviors. This model is non-invasive and objective, addressing risk more effectively than current methods. Field tests validated the model's accuracy and highlighted its potential to identify long-term risk trends, enabling better planning for disruptive events and the development of digital strategies for emergency management.

Infectious intestinal disease (IID) is a syndrome consisting of diarrhoea and vomiting symptoms linked to a causative pathogen. The Third Study of IID (IID3) will report its incidence in the community within the UK and assess how it has changed since the second IID study (IID2) in 2012. We implemented an automated, online patient recruitment process within a national sentinel surveillance network and compared its performance versus IID2 in terms of: Patient recruitment rates and demographic characteristics of recruited participants. We utilised a text messaging system (TMS) running off a computerised medical record systems (CMR) application programme interface (API). Demographic analysis showed that the majority of those recruited to IID3/IID2 studies were >65 years and female. However, the recruitment of participants of non-white ethnicity was statistically significantly different between IID3/IID2. Further work is required to improve recruitment in the younger patient demographic and in ethnic minority populations.

We present a new methodological approach based on integrating Arden-Syntax-based clinical decision support (CDS) with an upstream ontology service. Incoming linguistic patient data, such as single reports about detected germs or viruses, shall be identified by the applied ontology at a low level. Then, higher-level concepts are activated by ontology-based bottom-up reasoning. Access to these high-level concepts is then provided by Arden-Syntax-based CDS. The results suggest promising directions for future enhancements in knowledge-based artificial intelligence.

The Arden Syntax is a language designed for the encoding of medical knowledge into clinical decision support systems. Its evolution is overseen by Health Level 7. A significant enhancement in its new version 3.0 is the incorporation of FHIR for data retrieval, which addresses the long-standing curly braces problem. We introduce a newly developed compiler for Arden Syntax 3.0, which employs modern tools such as ANTLR for lexical and parsing analysis and GraalVM with the Truffle Language Implementation Framework for semantic processing, optimization, and language execution. Comprehensive testing against a legacy compiler revealed substantial improvements in execution speed, memory efficiency, and code quality. These advancements, coupled with superior maintainability and extensibility, position the Truffle compiler as a robust replacement, supporting future development and enhancing the user experience with Arden-Syntax-based clinical decision support.

Traumatic brain injuries (TBI) significantly impact global health, often resulting in death or long-term disability. We developed a quality dashboard to monitor adherence to severe TBI guidelines, leveraging data from Rennes University Hospital's clinical data warehouse collected between January 2020 and December 2023. We included 193 patients from the surgical ICU who were over 18 years old and excluded those without adequate intracranial pressure (ICP) monitoring data. The study utilized the French Anesthesiology and Intensive Care Society guidelines and the Brain Trauma Foundation's 4th Guidelines Edition to assess guideline adherence over the first seven days of hospitalization. Our dashboard, built using the flexdashboard and Plotly R libraries, presents patient demographics, clinical assessments, and treatment adherence. Despite limitations, such as reduced interoperability and the absence of clinician usability testing, our tool represents a pioneering effort in TBI guideline compliance, with plans for future enhancements including expanded guideline evaluation and improved dashboard sharing capabilities.

The AKTIN Emergency Department Registry, a German health data network, faces operational challenges due to rapid growth. Manual data request processes have become inefficient, hindering timely research and straining personnel. To address these challenges, we undertook a user-centered analysis utilizing Design Thinking principles to identify pain points and functional requirements in current data request creation and management processes. Future work will prioritize iterative implementation of the created concepts with continuous user engagement and rigorous software validation.

Technology in the medical field is continuously advancing due to its numerous subdomains and the ever-growing medical needs of people. Information systems have become integral to doctors' daily routines in patient care, offering flexibility and support in repetitive tasks, thereby allowing more time for critical activities. This paper presents the implementation of a machine learning algorithm, leveraging natural language processing (NLP) and labeling techniques, to analyze medical leaflets from Romania. The aim is to assist pediatricians in determining appropriate treatment doses for children based on various parameters such as age, weight, and other significant factors.