Studies in health technology and informatics最新文献

{"title":"Enhancing Longitudinal Data Analysis with Unstructured EHRs: A Case Study of Renal Function Evaluation in Rare Disease.","authors":"Xiaomeng Wang, Carole Faviez, Maxime Douillet, Bertrand Knebelmann, Nicolas Garcelon, Anita Burgun, Xiaoyi Chen","doi":"10.3233/SHTI250602","DOIUrl":"https://doi.org/10.3233/SHTI250602","url":null,"abstract":"<p><p>Electronic Health Records (EHRs) provide valuable longitudinal data for tracking disease progression, especially in rare diseases like ciliopathies which often involve chronic renal decline. While important biomarkers are available in structured databases, crucial information such as external lab tests and detailed disease history may only be found in clinical narratives. This study aims to enrich structured datasets with unstructured clinical text and assess its impact on estimating chronic kidney disease progression in ciliopathy patients. Our results demonstrate that data enrichment increased the number of eligible patients for longitudinal analysis by 73.5%, expanded available measurements by 189%, and significantly extended the median follow-up duration from 3.2 to 6.6 years. Using linear mixed regression to model individual estimated glomerular filtration (eGFR) rate trajectories over age, we found that data enrichment reduced standard errors by 30%, indicating a substantial increase in precision and reliability. These findings underscore the value of EHR data enrichment for longitudinal analysis in rare disease research.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"1270-1274"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087253","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":"Chain of Thought Strategy for Smaller LLMs for Medical Reasoning.","authors":"Hurmat Ali Shah, Mowafa Househ","doi":"10.3233/SHTI250466","DOIUrl":"https://doi.org/10.3233/SHTI250466","url":null,"abstract":"<p><p>This paper investigates the application of Chain of Thought (CoT) reasoning to enhance the performance of smaller language models in medical question-answering tasks. By leveraging CoT prompting strategies, we aim to improve model accuracy and interpretability, especially in resource-constrained settings. Using the PubMedQA dataset, we demonstrate how CoT helps smaller models break down complex medical queries into sequential steps, enabling more structured reasoning. While these models still face challenges in handling highly specialized medical content, CoT significantly improves their viability for healthcare applications. Our findings suggest that further optimization through methods like retrieval-augmented generation could further close the performance gap between smaller and larger models.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"783-787"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087290","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":"Physicians' Experiences of Health Information Exchange in Finland After Ten Years of National Patient Data Repository Services.","authors":"Tinja Lääveri, Jarmo Reponen, Tuulikki Vehko, Johanna Viitanen","doi":"10.3233/SHTI250426","DOIUrl":"https://doi.org/10.3233/SHTI250426","url":null,"abstract":"<p><p>Health information exchange (HIE) is expected to improve cross-organizational collaboration and access to data. In Finland, the first regional health information systems (RHISs) were introduced in 2003, and the electronic prescription and national patient data repository (\"Kanta\") services were implemented in 2010-17. We explored physicians' experiences and use of cross-organizational HIE at four time points: before (2010) and after the implementation of the prescription center (2014), and after the full implementation of Kanta (2017), and during established use (2021). The data were retrieved from four large national cross-sectional usability-focused surveys targeted for physicians and analyzed by physician specialty groups and study years. Across all specialties, RHISs and Kanta Services had largely replaced the need for paper/fax-based HIE. The experiences of medication information, or health information system support for collaboration between physicians working in different organizations improved only slightly during the study period suggesting that availability of medication information and patient documentation are not sufficient for adequate HIE services when most HIE is of \"pull\" type.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"637-641"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087310","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":"Integrating Patient-Generated Health Data from a Smartphone App Across Multiple Healthcare Providers: A Case Study.","authors":"Sabine N van der Veer, Sarah Knowles, Dawn Dowding, Charlotte A Sharp, Susan Moschogianis, Deb Griffiths-Jones, William G Dixon","doi":"10.3233/SHTI250436","DOIUrl":"https://doi.org/10.3233/SHTI250436","url":null,"abstract":"<p><p>Many smartphone apps enable people to collect data about their own health but -unless tethered to an electronic health record system-rarely allow sharing of this patient-generated health data with healthcare providers. The Remote Monitoring of Rheumatoid Arthritis (REMORA) programme successfully integrated a university-provided symptom tracking app into England's National Health Service across 16 rheumatology departments in two regions, each with their own IT set-up. Informed by meetings and initial interviews with the REMORA project team, our paper presents this integration as a case study. We describe the resulting infrastructure, the process and people involved in establishing the integration, and what influencing factors were. Following further interviews, our next step is to translate the case study findings into recommendations for key stakeholders to inform similar cross-provider integrations in the future and expedite the scaling up of integrated patient-generated health data.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"687-692"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087312","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":"Introducing the Database Schema Handling FHIR Data in the INTERPOLAR Project.","authors":"Matthias Reusche, Sebastian Stäubert, Alexander Strübing, Florian Schmidt, Maryam Yahiaoui-Doktor, Marcel von Borzestowski, Daniel Neumann, Markus Loeffler","doi":"10.3233/SHTI250459","DOIUrl":"https://doi.org/10.3233/SHTI250459","url":null,"abstract":"<p><p>The INTERPOLAR project of the German Medical Informatics Initiative investigates medication related problems. A relational database as part of a core data set tool chain was designed to process patient data from routine care represented as FHIR resources. Having the patient data available via SQL makes it easy to perform analyses, reports and connect to existing electronic data capture systems to get feedback from clinical users, like pharmacists.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"767-768"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087327","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":"Using Data-Driven Decision Algorithms and Real-World Data for Updating Clinical Practice Guidelines.","authors":"Thijs van Vegchel, Kees C W J Ebben","doi":"10.3233/SHTI250312","DOIUrl":"https://doi.org/10.3233/SHTI250312","url":null,"abstract":"<p><p>Clinical practice guidelines often struggle to stay updated, especially as cancer care becomes more personalized. We transformed guidelines into data-driven Clinical Decision Algorithms (CDAs) and compared Dutch and US CDAs, enriching the Dutch version with real-world data from the Netherlands Cancer Registry. An interactive dashboard was developed to automate guideline comparisons, adherence analysis, and alternative treatment evaluations, enabling timely updates and more responsive, evidence-based care.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"229-230"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087408","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":"Harnessing Virtual Reality for Training Care Home Staff in Remote Telehealth Assessments: A Digital Health Innovation.","authors":"Sheiladen Aquino","doi":"10.3233/SHTI250549","DOIUrl":"https://doi.org/10.3233/SHTI250549","url":null,"abstract":"<p><p>The rise of digital health technologies offers innovative solutions to address the growing demands in healthcare. Within long-term care settings, the shortage of trained staff in essential areas such as swallowing, nutrition, and medication management has been exacerbated by the increasing complexity of care needs. Virtual Reality (VR) is an emerging technology that provides immersive, interactive environments that can enhance training in remote telehealth assessments, reducing gaps in care delivery while meeting the requirements of health professionals.</p><p><strong>Objectives: </strong>This study investigates the requirements for implementing a Virtual Reality training program tailored for care home staff. The focus is on using VR to improve competencies in remote telehealth assessments in key areas such as swallowing, nutrition, and medication management.</p><p><strong>Methods: </strong>A mixed-methods approach was used, combining surveys and focus groups with care home staff, Generic Therapy Associate Practitioners (GTAPs), and Allied Health Professionals (AHPs). The Technology Acceptance Model (TAM) framework was employed to understand factors influencing the adoption of VR in telehealth training, focusing on perceived usefulness, ease of use, and the integration of digital technologies into clinical workflows.</p><p><strong>Results: </strong>The findings revealed three key areas: (1) the need for realistic and clinically relevant content in VR training simulations, (2) the importance of ease of use and accessibility to ensure broader adoption of VR, and (3) the role of organizational support, including technological infrastructure and funding, in successful deployment. Participants indicated that VR could bridge training gaps by providing scalable, risk-free simulations that enhance staff confidence in delivering remote telehealth assessments.</p><p><strong>Conclusion: </strong>Virtual Reality presents a transformative opportunity in digital health education, particularly in equipping care home staff to conduct remote telehealth assessments. By leveraging VR's immersive capabilities, integrated health and social care can advance towards more efficient, scalable, and effective training solutions. The successful integration of this digital tool will depend on addressing both technological and organizational barriers, paving the way for broader implementation across healthcare systems.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"1079-1083"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087115","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":"Graph Neural Networks for Gleason Grading in Prostate Histopathology Images.","authors":"Hafsa Akebli, Kevin Roitero, Vincenzo Della Mea","doi":"10.3233/SHTI250270","DOIUrl":"https://doi.org/10.3233/SHTI250270","url":null,"abstract":"<p><p>Prostate cancer is a leading cause of cancer-related deaths, with Gleason grading being key for assessing tumor aggressiveness. We propose a Graph Neural Network-based approach to automate Gleason grading using the Automated Gleason Grading Challenge 2022 dataset. Patch-level graphs constructed from Hematoxylin and Eosin-stained Whole-Slide Images were classified into Gleason grades. Our results show that Graph Neural Networks, specifically Graph Attention Networks and Graph Convolutional Networks, effectively distinguish between grades despite class imbalance. Focal Loss improves the classification of the minority Gleason Grade 5, which is crucial for detecting aggressive prostate cancer. Our models outperform state-of-the-art methods, achieving higher F1-scores without scanner generalization techniques.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"43-47"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087131","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":"Advancing Usability and Decision Support for Molecular Tumor Boards: Insights from PM4Onco's Visual Analytics Workshop.","authors":"Cosima Strantz, Dominik Boehm, Philipp Unberath","doi":"10.3233/SHTI250390","DOIUrl":"https://doi.org/10.3233/SHTI250390","url":null,"abstract":"<p><p>The PM4Onco project aims to optimize cBioPortal for use in Molecular Tumor Boards (MTBs), enhancing its usability in the clinical setting and integration of clinical and genomic data. A visual analytics workshop at the PM4Onco Symposium 2024, organized in a co-creative and participatory manner, using a user-centered design (UCD) approach, identified key improvements through discussion among involved stakeholders and exchange of perspectives. These improvements included customizable workflows, role-based access controls, and advanced visualization tools like time-series plots and patient similarity metrics. Participants also highlighted the need to address media silos and ensure seamless data integration from external sources like electronic health records (EHRs). Decision support systems, especially those leveraging annotation sources, were emphasized to improve the interpretation of molecular findings and provide therapy recommendations. The workshop ensured that new features would be practical, user-friendly, and aligned with the specific needs of MTB users, facilitating more efficient clinical decision-making and enhancing the platform's functionality in personalized oncology.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"512-516"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087136","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":"Detecting the Potential for Bias in Healthcare Data.","authors":"Emel Seker, Melody Greer","doi":"10.3233/SHTI250582","DOIUrl":"https://doi.org/10.3233/SHTI250582","url":null,"abstract":"<p><p>Bias in healthcare, including systematic errors, prejudice, or assumptions involving patient care, is an important issue which can cause disparities in health outcomes. In this review we focus on information bias, specifically measurement bias. This bias includes systematic errors in collecting, recording, or interpreting healthcare data, hence the crucial role of healthcare professionals, researchers, and policymakers. Measurement bias becomes an issue when sensitive attributes are involved, as these biases can impact public health decisions based on inaccurate data. We used a cross-checking validation process to address these concerns and enhance data quality. We compared patient data from two different sources, from UAMS and a commercial data provider, both relating to the same healthcare event, to verify accuracy and Consistency. Our analysis incorporated essential data quality metrics to ensure the reliability of the findings. These metrics include Completeness, Accuracy, Consistency, and Validity. Cross-checking with these data quality metrics allowed us to detect discrepancies and inconsistencies, as well as the overall reliability and validity of the data. Our study highlights the importance of rigorous validation and data quality measures to minimize bias and ensure accurate, reliable conclusions, and it calls for the active participation of the audience in this endeavor.</p>","PeriodicalId":94357,"journal":{"name":"Studies in health technology and informatics","volume":"327 ","pages":"1210-1214"},"PeriodicalIF":0.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087158","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}