JMIR Medical Informatics

In medical imaging, 3D visualization is vital for displaying volumetric organs, enhancing diagnosis and analysis. Multiplanar reconstruction (MPR) improves visual and diagnostic capabilities by transforming 2D images from computed tomography (CT) and magnetic resonance imaging into 3D representations. Web-based Digital Imaging and Communications in Medicine (DICOM) viewers integrated into picture archiving and communication systems facilitate access to pictures and interaction with remote data. However, the adoption of progressive web applications (PWAs) for web-based DICOM and MPR visualization remains limited. This paper addresses this gap by leveraging PWAs for their offline access and enhanced performance.

The EyeMatics project, embedded as a clinical use case in Germany's Medical Informatics Initiative, is a large digital health initiative in ophthalmology. The objective is to improve understanding of treatment effects regarding intravitreal injections, the most frequent procedure to treat eye diseases. To achieve this, valuable patient data will be meaningfully integrated and visualized from different IT-systems and different hospital sites. EyeMatics emphasizes a governance framework that actively involves patient representatives, strictly implements interoperability standards and employs Artificial Intelligence methods to extract biomarkers from both tabular clinical and raw retinal scans. In this perspective paper, we delineate the strategies for user-centered implementation and healthcare-based evaluation in a multi-site observational technology study.

Social media platforms allow individuals to openly gather, communicate, and share information about their interactions with healthcare services, becoming an essential supplemental means of understanding patient experience.

With great interest we read the article entitled “Development of a Trusted Third Party at a Large University Hospital: Design and Implementation Study” by Wündisch et al. (1). The objective of the article was to introduce a “comprehensive architecture for a Trusted Third Party (TTP) that aims to support a wide range of different research projects” incorporating “a fine-grained authentication and authorization model [and] a modern REST-API” in order to “support cross-service workflows”. Their work is based on well-established software components of the University Medicine Greifswald for record linkage (E PIX®), pseudonymisation (gPAS®) and consent management (gICS®) (2). With this letter, we aim to place the authors’ statement that “the literature lacks insights into the design of more comprehensive architectures that support complex research workflows that are actually in production use” into a state-of-the-art perspective to prevent any misleading impressions. While the authors concede that “research exists on the components mentioned above”, their article contains several inaccuracies that we would like to highlight in the following. The functional scope of the existing solutions (E-PIX, gPAS, gICS) is presented in Table 1. However, the existing workflow management solution of the University Medicine Greifswald (TTP Dispatcher) was not displayed (2). The authors only reference this highly relevant component later in text of their article. Furthermore, the content and designation of Table 2 “additional functional requirements” misleadingly suggests that the listed requirements are not covered by the solutions mentioned in Table 1. In published work (2) (3) and available materials (4), many of the checkmarks listed in Table 2 have been successfully validated, and moreover, the compliance of the tools with the pertinent TMF guidelines (3) has been demonstrated. Unlike the authors’ indication, the TTP dispatcher solution from the University Medicine Greifswald provides a common REST-API across all TTP services (based on E-PIX, gPAS and gICS) and enables cross-service workflows (2). Contrary to the description by Wündisch et. al., the dispatcher architecture allows the implementation of complex research workflows. We published a list of available workflows together with a corresponding example (“automatic creation of pseudonyms linked to the primary identifier when registering a patient or study participant”)(2). Since 2018, the existing TTP dispatcher solution has been made available in various project collaborations (3). In 2024, the TTP dispatcher is used in projects throughout Germany and the comprehensive documentation for the latest software version is publicly available (4). With regard to the relevance of the secure authentication mechanisms, we fully agree with the authors that OAuth 2.0 support based on OIDC and a fine-grained authorisation model are essential for securing TTP-Services. Therefore, Keycloak-support for E-PIX, gPAS and gICS is operational since 2022 (5). We can also only encourage the interoperability endeavours of the authors with regard to HL7 FHIR. For this reason, the University Medicine Greifswald has actively contributed to the HL7 FHIR standard and has fully implemented it (5). We hope that our additions have clarified any remaining uncertainties and welcome further opportunities to exchange and share our practical experience with the authors.

-

The paper reviews digital solutions for health services management in Brazil, focusing on certified software features. It reveals the integration of various functionalities in operational, financial, and clinical needs simultaneously, which are critical for enhancing operational efficiency and patient care. This study highlights the integration of critical features like interoperability, compliance management, and data-driven decision support, though advancing innovation and integration remains essential for broader impact.

The enzymatic system of cytochrome P450 (CYP450) is a group of enzymes involved in the metabolism of drugs present in the liver. Literature records instances of underdosing of drugs due to the concurrent administration of another drug that strongly induces the same cytochrome for which the first drug is a substrate, and overdosing due to strong inhibition. Information technology solutions have been proposed to raise awareness among prescribers to mitigate these interactions.

Atrial fibrillation (AF) is a progressive disease, and its clinical type is classified according to the AF duration: paroxysmal AF, persistent AF (PeAF; AF duration of less than 1 year), and long-standing persistent AF (AF duration of more than 1 year). When considering the indication for catheter ablation, having a long AF duration is considered a risk factor for recurrence, and therefore, the duration of AF is an important factor in determining the treatment strategy for PeAF.

Mild cognitive impairment (MCI) poses significant challenges in early diagnosis and timely intervention. Underdiagnosis, coupled with the economic and social burden of dementia, necessitates more precise detection methods. Machine learning (ML) algorithms show promise in managing complex data for MCI and dementia prediction.

Clinical named entity recognition (CNER) is a fundamental task in natural language processing used to extract named entities from electronic medical record texts. In recent years, with the continuous development of machine learning, deep learning models have replaced traditional machine learning and template-based methods, becoming widely applied in the CNER field. However, due to the complexity of clinical texts, the diversity and large quantity of named entity types, and the unclear boundaries between different entities, existing advanced methods rely to some extent on annotated databases and the scale of embedded dictionaries.

The integration of information systems in healthcare and social welfare organizations has brought significant changes in patient and client care. This integration is expected to offer numerous benefits, but simultaneously the implementation of health information systems and client information systems can also introduce added stress due to the increased time and effort required by professionals.

Social networking services (SNS) closely reflect the lives of individuals in modern society and generate large amounts of data. Previous studies have extracted drug information using relevant SNS data. In particular, it is important to detect adverse drug reactions (ADRs) early using drug surveillance systems. To this end, various deep learning methods have been employed, which have studied multiple languages in addition to English.