Dario Antweiler

Dario Antweiler

Auto-generated profile, based on publicly available information

Dario Antweiler

Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), Sankt Augustin, Germany

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2024 in International Journal of Medical Informatics
Verified
Journal Article
Open access
ALAssaf Landschaft
Assaf Landschaft
DADario Antweiler
Dario Antweiler
SMSina Mackay
Sina Mackay
SKSabine Kugler
Sabine Kugler
SRStefan Rüping
Stefan Rüping
HAHector Allende-Cid
Hector Allende-Cid
PRISMA-based literature reviews require meticulous scrutiny of extensive textual data by multiple reviewers, which is associated with considerable human effort. To evaluate feasibility and reliability of using GPT-4 API as a complementary reviewer in systematic literature reviews based on the PRISMA framework. A systematic literature review on the role of natural language processing and Large Language Models (LLMs) in automatic patient-trial matching was conducted using human reviewers and an AI-based reviewer (GPT-4 API). A RAG methodology with LangChain integration was used to process full-text articles. Agreement levels between two human reviewers and GPT-4 API for abstract screening and between a single reviewer and GPT-4 API for full-text parameter extraction were evaluated. An almost perfect GPT-human reviewer agreement in the abstract screening process (Cohen's kappa > 0.9) and a lower agreement in the full-text parameter extraction were observed. As GPT-4 has performed on a par with human reviewers in abstract screening, we conclude that GPT-4 has an exciting potential of being used as a main screening tool for systematic literature reviews, replacing at least one of the human reviewers.

23 June 2025 in Computers in Biology and Medicine
Verified
Journal Article
Open access
KAKamyar Arzideh
Kamyar Arzideh
HSHenning Schäfer
Henning Schäfer
HAHéctor Allende-Cid
Héctor Allende-Cid
GBGiulia Baldini
Giulia Baldini
THThomas Hilser
Thomas Hilser
RHRené Hosch
René Hosch
Extracting clinical entities from unstructured medical documents is critical for improving clinical decision support and documentation workflows. This study examines the performance of various encoder and decoder models trained for Named Entity Recognition (NER) of clinical parameters in pathology and radiology reports, highlighting the applicability of Large Language Models (LLMs) for this task. Three NER methods were evaluated: (1) flat NER using transformer-based models, (2) nested NER with a multi-task learning setup, and (3) instruction-based NER utilizing LLMs. A dataset of 2013 pathology reports and 413 radiology reports, annotated by medical students, was used for training and testing. The performance of encoder-based NER models (flat and nested) was superior to that of LLM-based approaches. The best-performing flat NER models achieved F1-scores of 0.87-0.88 on pathology reports and up to 0.78 on radiology reports, while nested NER models performed slightly lower. In contrast, multiple LLMs, despite achieving high precision, yielded significantly lower F1-scores (ranging from 0.18 to 0.30) due to poor recall. A contributing factor appears to be that these LLMs produce fewer but more accurate entities, suggesting they become overly conservative when generating outputs. LLMs in their current form are unsuitable for comprehensive entity extraction tasks in clinical domains, particularly when faced with a high number of entity types per document, though instructing them to return more entities in subsequent refinements may improve recall. Additionally, their computational overhead does not provide proportional performance gains. Encoder-based NER models, particularly those pre-trained on biomedical data, remain the preferred choice for extracting information from unstructured medical documents.

23 September 2024 in Multiple Sclerosis Journal
Verified
Journal Article
Open access
HIHernan Inojosa
Hernan Inojosa
IVIsabel Voigt
Isabel Voigt
JWJudith Wenk
Judith Wenk
DFDyke Ferber
Dyke Ferber
IWIsabella Wiest
Isabella Wiest
Tjalf ZiemssenTjalf Ziemssen
Tjalf Ziemssen
Use of techniques derived from generative artificial intelligence (AI), specifically large language models (LLMs), offer a transformative potential on the management of multiple sclerosis (MS). Recent LLMs have exhibited remarkable skills in producing and understanding human-like texts. The integration of AI in imaging applications and the deployment of foundation models for the classification and prognosis of disease course, including disability progression and even therapy response, have received considerable attention. However, the use of LLMs within the context of MS remains relatively underexplored. LLMs have the potential to support several activities related to MS management. Clinical decision support systems could help selecting proper disease-modifying therapies; AI-based tools could leverage unstructured real-world data for research or virtual tutors may provide adaptive education materials for neurologists and people with MS in the foreseeable future. In this focused review, we explore practical applications of LLMs across the continuum of MS management as an initial scope for future analyses, reflecting on regulatory hurdles and the indispensable role of human supervision.

26 May 2022 in Computers & Graphics
Verified
Journal Article
Closed access
DADario Antweiler
Dario Antweiler
DSDavid Sessler
David Sessler
MRMaxim Rossknecht
Maxim Rossknecht
BABenjamin Abb
Benjamin Abb
SGSebastian Ginzel
Sebastian Ginzel
JKJörn Kohlhammer
Jörn Kohlhammer

30 November 2023 in Bundesgesundheitsblatt - Gesundheitsforschung - Gesundheitsschutz
Verified
Journal Article
Open access
PDF file
DADario Antweiler
Dario Antweiler
DADaniela Albiez
Daniela Albiez
DBDominik Bures
Dominik Bures
BHBernadette Hosters
Bernadette Hosters
FJFlorian Jovy-Klein
Florian Jovy-Klein
ADAnke Diehl
Anke Diehl
Zusammenfassung: Hintergrund: Künstliche Intelligenz (KI) hat für Krankenhäuser wesentlich an Bedeutung gewonnen. Um die umfangreichen Potenziale der Technologie tatsächlich nutzen zu können, sind Anpassungen bei Aufgabenprofilen sowie zielgerichtete Qualifizierungsmaßnahmen für das Krankenhauspersonal heute und in Zukunft unabdingbar. Davon sind sowohl medizinische als auch nichtmedizinische Prozesse entlang der gesamten Wertschöpfungskette im Krankenhaus betroffen. Ziel der Arbeit ist es, einen Überblick über die notwendigen Fähigkeiten im Umgang mit intelligenten Technologien im klinischen Kontext zu geben und Maßnahmen zur Qualifizierung von Mitarbeiter*innen vorzustellen. Methoden: Im Rahmen des Projekts „SmartHospital.NRW“ wurden im Jahr 2022 eine Literaturrecherche sowie Interviews und Workshops mit Expert*innen durchgeführt. KI-Technologien und Anwendungsfelder wurden identifiziert. Ergebnisse: Zentrale Ergebnisse umfassen veränderte und neue Aufgabenprofile, identifizierte Synergien und Abhängigkeiten zwischen den einzelnen Aufgabenprofilen sowie die Notwendigkeit eines umfassenden interdisziplinären und interprofessionellen Austauschs beim Einsatz von KI-basierten Anwendungen im Krankenhaus. Diskussion: Unser Beitrag zeigt, dass Krankenhäuser frühzeitig Kompetenzen im Bereich Digital Health Literacy in der Belegschaft fördern und gleichzeitig technikaffines Personal anwerben müssen. Interprofessionelle Austauschformate sowie ein begleitendes Changemanagement sind essenziell für die Nutzung von KI im Krankenhaus.

29 June 2021 in Medizinrecht
Verified
Journal Article
Closed access
PDF file
SHStefanie Hänold
Stefanie Hänold
NSNelli Schlee
Nelli Schlee
DADario Antweiler
Dario Antweiler
KBKatharina Beckh
Katharina Beckh