Studies in Health Technology and Informatics

INTRODUCTION: Glioblastoma (GB) is one of the most aggressive tumors of the brain. Despite intensive treatment, the average overall survival (OS) is 15-18 months. Therefore, it is helpful to be able to assess a patient's OS to tailor treatment more specifically to the course of the disease. Automated analysis of routinely generated MRI sequences (FLAIR, T1, T1CE, and T2) using deep learning-based image classification has the potential to enable accurate OS predictions. METHODS: In this work, a method was developed and evaluated that classifies the OS into three classes - "short", "medium" and "long"...

This study aims to advance the field of digital wound care by developing and evaluating convolutional neural network (CNN) architectures for the automatic classification of maceration, a significant wound healing complication, in 458 annotated wound images. Detection and classification of maceration can improve patient outcomes. Several CNN models were compared and MobileNetV2 emerged as the top-performing model, achieving the highest accuracy despite having fewer parameters. This finding underscores the importance of considering model complexity relative to dataset size...

INTRODUCTION: Existing research agrees that a well-thought design of the user interface is a key point for an mHealth application for animal owners, supporting them obtain information and make decisions regarding their pet's specific situation. However, there is currently a lack of specific advice on the design of such an application. METHODS: As part of a user-centered design (UCD) process, a formative, explorative usability test with n = 5 users was conducted for collecting design ideas...

Inclusive Design Thinking (IDT) is an approach that specifically addresses disadvantaged user groups and involves them in the innovation process. In recent years, IDT has emerged as a particularly promising approach for increasing citizen and patient engagement in the development of digital health applications. Although IDT is based on existing frameworks of design thinking and human-centered design approaches, there is still no overview of its methods for digital health solutions. Our aim was to develop such a systematic overview of the methods used, aligned with the design process, and thereby facilitate the practical application of IDT...

INTRODUCTION: User-centered data visualizations can reduce physician cognitive load and support clinical decision making. To facilitate the selection of appropriate visualizations for single patient health data summaries, this scoping review provides a literature overview of possible visualization techniques and the corresponding reported user-centered design phases. METHODS: The publication databases PubMed, Web of Science, IEEE Xplore and ACM Digital Library were searched for relevant articles from 2017 to 2022...

INTRODUCTION: The integration of Patient-Reported Experience Measures (PREM) alongside traditional clinical outcomes is crucial for improving quality of care. Although PREMs are frequently measured in inpatient treatment settings, they are rarely employed in digitally supported care processes or longitudinal assessment of care pathways. METHODS: To gain an overview of PREMs used to cover patients' experiences with digitally supported care processes in heart failure (HF), a scoping review was conducted in Medline...

INTRODUCTION: Automation bias poses a significant challenge to the effectiveness of Clinical Decision Support Systems (CDSS), potentially compromising diagnostic accuracy. Previous research highlights trust, self-confidence, and task difficulty as key determinants. With the increasing availability of AI-enabled CDSS, automation bias attains new attention. This study therefore aims to identify factors influencing automation bias in a diagnostic task. METHODS: A quantitative intervention study with participants from different backgrounds (n = 210) was conducted, employing regression analysis to analyze potential factors...

INTRODUCTION: Parkinson's disease represents a burdensome condition with complex manifestations. A licensed, standardized paper-based questionnaire is completed by both patients and physicians to monitor the progression and state of the disease. However, integrating the obtained scores into digital systems still poses a challenge. METHODS: Paper-based handwriting is intuitive and an efficient mode of human-computer interaction. Accordingly, we transformed a consumer-grade tablet into a device where an exact digital copy of the disease-specific questionnaire can be filled with the supplied pen...

INTRODUCTION: In nursing, professionals are expected to base their practice on evidence-based knowledge, however the successful implementation of this knowledge into nursing practice is not always assured. Clinical Decision Support Systems (CDSS) are considered to bridge this evidence-practice gap. METHODS: This study examines the extent to which evidence-based nursing (EBN) practices influence the use of CDSS and identifies what additional factors from acceptance theories such as UTAUT play a role...

INTRODUCTION: A modern approach to ensuring privacy when sharing datasets is the use of synthetic data generation methods, which often claim to outperform classic anonymization techniques in the trade-off between data utility and privacy. Recently, it was demonstrated that various deep learning-based approaches are able to generate useful synthesized datasets, often based on domain-specific analyses. However, evaluating the privacy implications of releasing synthetic data remains a challenging problem, especially when the goal is to conform with data protection guidelines...

INTRODUCTION: Retrieving comprehensible rule-based knowledge from medical data by machine learning is a beneficial task, e.g., for automating the process of creating a decision support system. While this has recently been studied by means of exception-tolerant hierarchical knowledge bases (i.e., knowledge bases, where rule-based knowledge is represented on several levels of abstraction), privacy concerns have not been addressed extensively in this context yet. However, privacy plays an important role, especially for medical applications...

INTRODUCTION: Drawing tasks are an elementary component of psychological assessment in the evaluation of mental health. With the rise of digitalization not only in psychology but healthcare in general, digital drawing tools (dDTs) have also been developed for this purpose. This scoping review aims at summarizing the state of the art of dDTs available to assess mental health conditions in people above preschool age. METHODS: PubMed, PsycInfo, PsycArticles, CINAHL, and Psychology and Behavioral Sciences Collection were searched for dDTs from 2000 onwards...

INTRODUCTION: Secure Multi-Party Computation (SMPC) offers a powerful tool for collaborative healthcare research while preserving patient data privacy. STATE OF THE ART: However, existing SMPC frameworks often require separate executions for each desired computation and measurement period, limiting user flexibility. CONCEPT: This research explores the potential of a client-driven metaprotocol for the Federated Secure Computing (FSC) framework and its SImple Multiparty ComputatiON (SIMON) protocol as a step towards more flexible SMPC solutions...

Pancreatic cancer, renowned for its aggressive nature and poor prognosis, necessitates the optimization of treatment strategies. The sequence of procedures in clinical trials is critical, such as evaluating the potential benefits of preoperative chemo-radio-therapy for pancreatic cancer. Nevertheless, we might not be aware of other temporal sequences which have an effect on therapy response or the general outcome. Extracting transitive sequential patterns from patients' medical trajectories allows researchers to identify temporal characteristics for complex diseases...

INTRODUCTION: Large Language Models (LLMs) like ChatGPT have become increasingly prevalent. In medicine, many potential areas arise where LLMs may offer added value. Our research focuses on the use of open-source LLM alternatives like Llama 3, Gemma, Mistral, and Mixtral to extract medical parameters from German clinical texts. We concentrate on German due to an observed gap in research for non-English tasks. OBJECTIVE: To evaluate the effectiveness of open-source LLMs in extracting medical parameters from German clinical texts, specially focusing on cardiovascular function indicators from cardiac MRI reports...

INTRODUCTION: Cardiovascular diseases are a leading cause of mortality worldwide, highlighting the urgent need for accurate and efficient diagnostic tools. Echocardiography, a non-invasive imaging technique, plays a central role in the diagnosis of heart diseases, yet the potential impact of artificial intelligence (AI) on its accuracy and speed has not yet been reviewed and summarized. This scoping review aims to address this research gap by synthesizing existing evidence on AI-assisted echocardiography's...

INTRODUCTION: Human and veterinary medicine are practiced separately, but literature databases such as Pubmed include articles from both fields. This impedes supporting clinical decisions with automated information retrieval, because treatment considerations would not ignore the discipline of mixed sources. Here we investigate data-driven methods from computational linguistics for automatically distinguishing between human and veterinary medical texts. METHODS: For our experiments, we selected language models after a literature review of benchmark datasets and reported performances...

INTRODUCTION: The secondary use of data in clinical environments offers significant opportunities to enhance medical research and practices. However, extracting data from generic data structures, particularly the Entity-Attribute-Value (EAV) model, remains challenging. This study addresses these challenges by developing a methodological approach to convert EAV-based data into a format more suitable for analysis. BACKGROUND: The EAV model is widely used in clinical information systems due to its adaptability, but it often complicates data retrieval for research purposes due to its vertical data structure and dynamic schema...

INTRODUCTION: Medical terminologies and code systems, which play a vital role in the health domain, are rarely static but undergo changes as knowledge and terminology evolves. This includes addition, deletion and relabeling of terms, and, if terms are organized hierarchically, changing their position. Tracking these changes may become important if one uses multiple versions of the same terminology and interoperability is desired. METHOD: We propose a new method for automatic change tracking between terminology versions...

INTRODUCTION: Constructing search queries that deal with complex concepts is a challenging task without proficiency in the underlying query language - which holds true for either structured or unstructured data. Medical data might encompass both types, with valuable information present in one type but not the other. METHOD: The TOP Framework provides clinical practitioners as well as researchers with a unified framework for querying diverse data types and, furthermore, facilitates an easier and intuitive approach...