Studies in health technology and informatics最新文献

{"title":"From Broad Consent to Patient Engagement: A Framework for Consent Management and Study Oversight.","authors":"Anne Pelz, Philipp Heinrich, Gabriele Mueller, Anne Seim, Peter Penndorf, Martin Bialke, Martin Sedlmayr, Ines Reinecke, Markus Wolfien, Katja Hoffmann","doi":"10.3233/SHTI251405","DOIUrl":"10.3233/SHTI251405","url":null,"abstract":"<p><strong>Introduction: </strong>The German Medical Informatics Initiative (MII) promotes the use of routine clinical data for research, supported by the broad consent framework to ensure patient engagement. This work proposes a data management process and reference infrastructure to improve transparency by enabling patients to track their consent history and data use in research.</p><p><strong>Methods: </strong>We analyzed the data provision process at the University Hospital Dresden (UKD) to identify roles and data flows relevant to secondary data use under broad consent. Established MII tools in use at UKD were evaluated for their suitability in enabling secure data access.</p><p><strong>Results: </strong>We developed a structured data access process and implemented a reference infrastructure that lays the groundwork for a potential patient-facing application providing secure access to consent and study details.</p><p><strong>Conclusion: </strong>The reference infrastructure demonstrates how existing MII tools can be repurposed to offer patient-centric transparency in secondary data use. Future work will address scalability, access control, and ethical considerations, such as patient expectations and the clarity of information.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"265-273"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classifying the AMi-Br Mitotic Figure Dataset with AUCMEDI.","authors":"Daniel Hieber, Friederike Lische-Starnecker, Johannes Schobel, Rüdiger Pryss, Frank Kramer, Dominik Müller","doi":"10.3233/SHTI251413","DOIUrl":"10.3233/SHTI251413","url":null,"abstract":"<p><strong>Introduction: </strong>Mitotic figure (MF) density has been established as a key biomarker for certain tumors. Recently, the differentiation between atypical MFs (AMF) and normal MFs (NMFs) has gained increased interest in research, as AMFs density could be an independent biomarker. This results in the challenge of finding an automated, deterministic way to differentiate between AMFs and NMFs.</p><p><strong>Methods: </strong>In this study, the AUCMEDI deep learning framework is applied to the recently published AMi-Br dataset to get a first bearing on the complexity of the task at hand. The dataset includes eight mitotic subclasses derived from breast cancer samples, four for NMFs and four for AMF. Using a patient-level cross- validation strategy and a ConvNeXt-based ensemble, we trained and evaluated an eight-class subtype classification model.</p><p><strong>Results: </strong>Our results show high specificity across all classes (≥ 90%), but sensitivity varies significantly between mitotic subclasses (0-82%), reflecting the dataset's inherent challenges. The mean AUC of 85.90% outperforms the binary classification baseline (69.8%).</p><p><strong>Conclusion: </strong>The results highlight the promise of progress in subclass-level mitotic analysis while pointing to areas for further model refinement.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"339-345"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conception and Development of a Metadata Search Portal Based on the Data Dictionary Minimal Information Model (DDMIM) Specification.","authors":"Leslie Diana Wamba Makem, Abishaa Vengadeswaran, Dupleix Achille Takoulegha, Dennis Kadioglu","doi":"10.3233/SHTI251400","DOIUrl":"10.3233/SHTI251400","url":null,"abstract":"<p><strong>Introduction: </strong>The heterogeneity of metadata continues to be a key challenge in the healthcare sector. The Data Dictionary Minimal Information Model (DDMIM) aims to meet the need for interoperability between different standards and data dictionaries to facilitate the exchange of metadata.</p><p><strong>Objective: </strong>This paper presents the conception, and the development of a metadata search portal based on the DDMIM specification, designed to improve the discoverability and accessibility of health datasets and enhance interoperability.</p><p><strong>Methods: </strong>We conducted a literature review of existing metadata repositories to select potentially relevant ones for further work. A mapping was created to transform metadata from different MDRs into the DDMIM format. In parallel, the requirements for a prototype search portal are being evaluated, which integrates metadata from various public repositories.</p><p><strong>Results: </strong>The results show that a DDMIM-based search portal can effectively integrate heterogeneous metadata sources and improve the finding of health datasets.</p><p><strong>Discussion: </strong>Such a portal supports the integration of heterogeneous metadata sources and ensures compliance with FAIR principles to optimize the use of health data for research and clinical applications. It is therefore of great importance to address the existing challenges in the field of medical data integration and utilization.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"228-234"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PED-DATA: A Privacy-Preserving Framework for Data-Driven, Pediatric Multi-Center Studies.","authors":"Gorkem Yilmaz, Jonathan M Mang, Markus Metzler, Hans-Ulrich Prokosch, Manfred Rauh, Jakob Zierk","doi":"10.3233/SHTI251409","DOIUrl":"10.3233/SHTI251409","url":null,"abstract":"<p><strong>Introduction: </strong>Data-driven analysis of clinical databases is an efficient method for clinical knowledge generation, which is especially suitable when exceptional ethical and practical restrictions apply, such as in pediatrics. In the multi-center PEDREF 2.0 study, we are analyzing children's laboratory test results, diagnoses, and procedures from more than 20 German tertiary care centers to establish pediatric reference intervals. The PEDREF 2.0 study uses the framework of the German Medical Informatics Initiative, but the specific study needs require the development of a customized module for distributed pediatric analyses.</p><p><strong>Methods: </strong>We developed the Pediatric Distributed Analysis, Anonymization, and Aggregation Module (PED-DATA), which is a containerized application that we deployed to all participating centers. PED-DATA transforms the input datasets to a harmonized internal representation and enables their decentralized analysis in compliance with data protection rules, resulting in an anonymous output dataset that is transferred for central analysis.</p><p><strong>Results: </strong>In a preliminary analysis of data from 15 centers, we analyzed 52,807,236 laboratory test results from 753,774 different patients (323,943 to 4,338,317 test results per laboratory test), enabling us to establish pediatric reference intervals with previously unmatched precision.</p><p><strong>Conclusion: </strong>PED-DATA facilitates the implementation of pediatric data-driven multicenter studies in a decentralized and privacy-respecting manner, and its use throughout German University Hospitals in the PEDREF 2.0 study demonstrates its usefulness in a real-world use case.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"307-317"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prompting Is All You Need - Until It Isn't: Exploring the Limits of LLMs for Negation Detection in German Clinical Text.","authors":"Richard Zowalla, Martin Wiesner","doi":"10.3233/SHTI251374","DOIUrl":"10.3233/SHTI251374","url":null,"abstract":"<p><strong>Introduction: </strong>Detecting negations in clinical text is crucial for accurate documentation and decision-making.</p><p><strong>Methods: </strong>This study assesses open-source Large Language Models (LLMs) for detecting negations in German clinical discharge letters, comparing them to the rule-based approach (GeNeg) and human annotations.</p><p><strong>Results: </strong>While Llama 3.3 and Deepseek-R1 (70B) showed slight accuracy improvements, their high computational costs limit practicality compared to GeNeg. Llama 3.3 achieved the highest accuracy (.9670) and F1-score (.9620), outperforming all other models and slightly exceeding GeNeg in accuracy and F1-score. However, it required significantly more computational time (5.9 sec/sent) when compared to GeNeg's processing time (.005 sec/sent).</p><p><strong>Conclusion: </strong>The study results suggest hybrid approaches combining rule-based efficiency paired with LLMs' linguistic capabilities. In addition, future work should therefore optimize prompts and integrate LLMs with traditional methods to balance accuracy and efficiency.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"5-12"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144984935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Numbers to Insights: Developing a Visual Cohort Explorer for Feasibility Requests.","authors":"Ahmad Albenny, Dennis Hübner, Franziska Bathelt","doi":"10.3233/SHTI251416","DOIUrl":"10.3233/SHTI251416","url":null,"abstract":"<p><strong>Introduction: </strong>The FDPG (German Portal for Medical Research Data) feasibility portal provides the number of patients who meet the inclusion and exclusion criteria at a national level. In addition, it is possible to perform local installation of the Feasibility Portal, with a view to addressing queries relating to local feasibility. In order to facilitate the accurate interpretation of the cohort count and enhance the comprehensibility of the data at a local level, efforts have been undertaken to develop a visual representation of the local FDPG feasibility portal cohort. This paper aims to address the challenge of providing insights into the cohort while preserving the anonymity of the data for the local version.</p><p><strong>Method: </strong>In order to be able to visualize the cohort, it was necessary to ascertain a method for extracting the patient data from the cohort definition established in the FDPG. The present study employed the available Medical Informatics Initiative (MII) tools in conjunction with the local feasibility portal to achieve the objective of visualizing the cohort. Subsequently, an investigation was conducted to determine the most efficient approach within the context of the local environment. An interactive R Shiny dashboard was implemented using fhircrackr, echarts4r, and plotly to visualize gender, diagnoses (ICD-10-GM), labs (LOINC), procedures (OPS), and medication (ATC).</p><p><strong>Results: </strong>Two variants have been developed for the extraction of patient data from our database. The first variant is based on FHIR, while the second is based on SQL. Both pipelines successfully visualized cohort data. The developed Shiny app delivered interactive visualizations validated by clinical experts.</p><p><strong>Conclusion: </strong>The SQL approach outperformed FHIR in processing time, especially at large scale, while FHIR allows flexible deployment across sites. The implementation is suitable for local deployment. However, implementation on a national scale would require considerable additional effort, data protection and significant improvements to the infrastructure.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"358-368"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Open Source Registry System for Rare Diseases (OSSE): Development and Usability Evaluation of an Initial Audit Trail Prototype.","authors":"Tim Vincent Knecht, Jens Göbel, Axel Zieschank, Holger Storf, Jessica Vasseur","doi":"10.3233/SHTI251386","DOIUrl":"10.3233/SHTI251386","url":null,"abstract":"<p><strong>Introduction: </strong>An audit trail is of critical importance for patient registries and electronic data capture (EDC) systems, as it ensures transparency, integrity, traceability and security of the collected data. This work demonstrates the development and usability evaluation of an initial prototype of an accessible audit trail for the Open Source Registry System for Rare Diseases (OSSE), an open source software tool for building patient registries.</p><p><strong>Methods: </strong>The prototype comprises a new user interface with list views and detailed views to make the information stored in the audit trail of the OSSE EDC database available for users. A standardized questionnaire, including the System Usability Scale (SUS) as well as task-based section, was used to gather feedback from 15 participants with varying levels of experience in working with OSSE and patient registries.</p><p><strong>Results: </strong>The resulting SUS score of 66 (on a scale of 0 to 100) falls within the marginal range, suggesting room for improvement in the initial prototype's usability. The survey also highlighted critical features necessary for the audit trail's functionality.</p><p><strong>Conclusion: </strong>Several respondents noted that the lack of these functionalities led to their negative responses, emphasizing the importance of implementing these features to improve the user experience. These insights form the basis for refining the audit trail's structure and adding essential functionalities in the future to improve the overall usability and quality of OSSE.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"112-121"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality of Machine Translations in Medical Texts: An Analysis Based on Standardised Evaluation Metrics.","authors":"Pascal Block, Johanna Schaefer, Felix Maurer, Holger Storf","doi":"10.3233/SHTI251380","DOIUrl":"10.3233/SHTI251380","url":null,"abstract":"<p><strong>Introduction: </strong>The medical care of patients with rare diseases is a cross-border concern across the EU. This is also reflected in the usage statistics of the SE-ATLAS, where most access occurs via browser languages set to German, English, French, or Polish. The SE-ATLAS website provides information on healthcare services and patient organisations for rare diseases in Germany. As SE-ATLAS currently offers its content almost exclusively in German, non-German-speaking users may encounter language barriers. Against this background, this paper explores whether common machine translation systems can translate medical texts into other languages at a reasonable level of quality.</p><p><strong>Methods: </strong>For this purpose, the translation systems DeepL, ChatGPT, and Google Translate were analysed. Translation quality was assessed using the standardised metrics BLEU, METEOR, and COMET. In contrast to subjective human assessments, these automated metrics allow for objective and reproducible evaluation. The analysis focused on machine-generated translations of German-language texts from the OPUS corpus into English, French, and Polish, each compared against existing reference translations.</p><p><strong>Results: </strong>BLEU scores were generally lower than those of the other metrics, whereas METEOR and COMET indicated moderate to high translation quality. Translations into English were consistently rated higher than those into French and Polish.</p><p><strong>Conclusion: </strong>As the three analysed translation systems showed hardly any statistically significant differences in translation quality and all delivered acceptable results, further criteria should be taken into account when choosing an appropriate system. These include factors such as data protection, cost-efficiency, and ease of integration.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"63-72"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144984975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Covhisto: A Web Application for Cross-Version Visualization and Analysis of ICD-10-GM and OPS.","authors":"Tessa Ohlsen, Simon Müller, Josef Ingenerf","doi":"10.3233/SHTI251394","DOIUrl":"10.3233/SHTI251394","url":null,"abstract":"<p><strong>Introduction: </strong>The ongoing development of medical coding systems such as ICD-10-GM and OPS presents challenges in ensuring compatibility across versions. This paper introduces Covhisto, a web application for visualizing and analysing changes across multiple versions.</p><p><strong>Methods: </strong>Covhisto uses crosswalk tables published by the German Federal Institute for Drugs and Medical Devices (BfArM) and data processing pipeline to track changes between ICD-10-GM and OPS versions. Key features include methods for following individual code histories and analyzing structural changes in the coding systems.</p><p><strong>Results: </strong>Covhisto allows users to trace code evolution and identify changes not automatically captured. Unlike existing solutions, Covhisto creates a ConceptMap across all versions, offering a comprehensive view of changes over time.</p><p><strong>Conclusion: </strong>Finally, Covhisto complements existing solutions by making complex code changes more transparent and easier to understand, supporting healthcare professionals and researchers in their analyses and promoting interoperability of healthcare data.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"177-185"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concept for a Framework for Integrating Registry and Routine Healthcare Data in Germany.","authors":"Jessica Vasseur, Dennis Kadioglu, Holger Storf","doi":"10.3233/SHTI251387","DOIUrl":"10.3233/SHTI251387","url":null,"abstract":"<p><strong>Introduction: </strong>In Germany, there is growing interest in linking clinical data from routine care available in data integration centres (DIC) with external data, such as medical registries. However, a suitable technical and organisational infrastructure is required for the secondary use and linkage of registry data. This paper presents the concept of a framework for the integration of routine data and registry data using the structures of a DIC.</p><p><strong>Methods: </strong>The development of the framework followed a step-by-step approach: (1) literature research, (2) derivation of the theoretical foundations of the framework, and (3) design and modelling of the framework.</p><p><strong>Results: </strong>Challenges for data linkage and matching solutions from initiatives such as the Medical Informatics Initiative (MII) or Network of University Medicine (NUM) were identified to create the theoretical basis of the framework. The initial design of the framework on increasingly detailed hierarchical levels includes functional components, processes and support units of a DIC to fulfil specific use cases from registry setup to data linkage.</p><p><strong>Discussion: </strong>The framework was developed to serve as a blueprint for the setup of a DIC as a bidirectional link between registries and routine care. At this stage it represents a theoretical concept as the result of formative research which remains to be systematically evaluated, further specified and tested in pilot projects. Despite the challenges, both registries and DIC could benefit from a future practical implementation of the framework.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"331 ","pages":"122-131"},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}