Isabella C. Wiest

Large Language Models in Lehr- und Prüfungsszenarien

Theresa Maria Meißner, Isabella C. Wiest

Hintergrund/Thema/Fragestellung: Digitale Technologien, insbesondere Large Language Models (LLMs), bieten einen vielversprechenden Lösungsansatz, um sowohl Lehrende als auch Lernende in Lern- und Prüfungszenarien zu unterstützen. Die Akzeptanz Medizinstudierender für den [zum vollständigen Text gelangen Sie über die oben angegebene URL]

de (code pays fourni par la source)

Vom Vergessen zum Lernerfolg: KI-gestütztes hybrides Feedback im OSCE

Isabella C. Wiest, Theresa Maria Meißner, Katja Matthes, Miriam Katharina Diek et autres

Problembeschreibung/Zielsetzung: Feedback ist zentral für kompetenzorientierte Bildung, jedoch zeigen Studien, dass Studierende unmittelbar nach OSCE-Prüfungen (Objective Structured Clinical Examinations) nur etwa 16% der Feedbackpunkte erinnern. Ursächlich sind physiologischer [zum vollständigen Text gelangen Sie über die oben angegebene URL]

de (code pays fourni par la source)

EHR perception and momentary well-being in oncology professionals

M.K. Wekenborg, C. Rominger, E.A.M. Michels, Isabella C. Wiest et autres

Background Digital systems increasingly shape oncology workflows, yet their impact on professionals' momentary well-being remains poorly understood. Existing evidence relies on retrospective self-reports and lacks real-time, multimodal data. We examined whether momentary perception of an oncology electronic health record (EHR), differentiated into …

de, at, gb (code pays fourni par la source)

Retrieval-Augmented Large Language Models for Clinically Aligned Adverse Event Coding in Acute Myeloid Leukemia Clinical Trials

Naghme Dashti, Martin M. K Schneider, Jan Niklas Eckardt, Frank Fiebig et autres

ABSTRACT Background Adverse event (AE) coding is essential for safety monitoring in oncology clinical trials, particularly in acute myeloid leukemia (AML), where intensive therapies are associated with frequent and heterogeneous toxicities requiring standardized MedDRA (Medical Dictionary for Regulatory Activities) coding. However, manual …

de (code pays fourni par la source)

Clinician expertise and prompt engineering enhance cancer information extraction in electronic health records by small language models

Federica Corso, Vittoria Peppoloni, Laura Mazzeo, giuseppe leone et autres

Real-world data (RWD) in unstructured electronic health records (EHRs) is crucial for understanding complex diseases like cancer, but extracting structured information is challenging due to linguistic variability, semantic complexity, and privacy concerns. This study evaluates the performance of four small, locally deployable …

it, pt, de, gb (code pays fourni par la source)

How to write a prompt: a short manual on using large language models

Narmin Ghaffari Laleh, Jakob Nikolas Kather, Isabella C. Wiest

de, gb (code pays fourni par la source)

clickBrick prompt engineering: optimizing large language model performance in clinical psychiatry

Falk Gerrik Verhees, Fabian Huth, Fabian Wolf, Michael S. Bauer et autres

Prompt engineering has the potential to enhance large language models' (LLM) ability to solve tasks through improved in-context learning. In clinical research, the use of LLMs has shown expert-level performance for a variety of tasks ranging from pathology slide classification to identifying …

de (code pays fourni par la source)

Large language models as experimental systems in human psychopathology: a modelling study

Magdalena Wekenborg, Elizabeth Anna Mathilde Michels, Georg Kurze, Matti Lasse Kropp et autres

BACKGROUND: Despite advances in biomedical research, human psychopathology remains underserved by experimental model systems, limiting therapeutic innovation. Alternative approaches are needed to investigate the mechanisms underlying mental health conditions. We aimed to assess whether large language models (LLMs) could serve as experimental …

de (code pays fourni par la source)

Blocking the Reflection: Milestones and Hurdles for Digital Twins in Mental Health

Falk Gerrik Verhees, Isabella C. Wiest, Jakob Nikolas Kather, Joseph Kambeitz et autres

Abstract: Artificial intelligence in mental health has emerged as a potent tool to foster precision psychiatry, for example, by stratifying patient populations. A potential step forward would be mental health digital twins-the independent in-silico reconstruction of an individual person within their functional …

de (code pays fourni par la source)

P0257 A standardized assessment of fatigue markedly increases sensitivity in a tertiary IBD center- a single-center experience

L L Knödler, E L Wilke, E K Herrmann, Isabella C. Wiest et autres

Abstract Background Fatigue is a common symptom in people living with inflammatory bowel diseases (IBD) with a prevalence of up to 80% in patients during a flare and in up to half of all patients with IBD even when the disease is …

de (code pays fourni par la source)

Education Research: Can Large Language Models Match MS Specialist Training?

Hernán Inojosa, Ahmadreza Ramezanzadeh, Iva Gasparovic-Curtini, Isabella C. Wiest et autres

Background and Objectives: Artificial intelligence (AI), particularly large language models (LLMs), is increasingly explored for clinical decision support and medical education. While general LLM proficiency on broad medical examinations has been demonstrated, their application of domain-specific knowledge in neurology remains underexplored. This …

de (code pays fourni par la source)

Combining Clinician Expertise with Prompt Engineering enhances Small Language Models Reliability for Cancer Entity Recognition in Electronic Health Records

Federica Corso, Vittoria Peppoloni, Laura Mazzeo, Luana Passos et autres

Real-world data (RWD), largely stored in unstructured electronic health records (EHRs), are critical for understanding complex diseases like cancer. However, extracting structured information from these narratives is challenging due to linguistic variability, semantic complexity, and privacy concerns. This study evaluates the performance …

it, pt, de, gb (code pays fourni par la source)