Felix Meyer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Felix Meyer has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Blanka Pophof
Federal Office for Radiation Protection
2 shared publications - Dan Baaken
Federal Office for Radiation Protection
2 shared publications - Dimitri Belenki
Federal Office for Radiation Protection
2 shared publications - Evelyn Weiser
Federal Office for Radiation Protection
2 shared publications - Heinrich A. M. Leymann
Federal Office for Radiation Protection
2 shared publications Alexander Astanin
Federal Office for Radiation Protection
1 shared publication
Latest Publications
- Open Access
- 4 September 2026
- Published by Springer Nature in Research Square
Cost-Efficient Large Language Model-Assisted Title and Abstract Screening for Systematic Reviews: Method Evaluation and Validation
Background The yearly number of publications in many fields, including research on potential health effects of electromagnetic fields (EMF), has steadily risen, making systematic reviews (SRs) increasingly laborious. Automating the title and abstract screening phase using large language models (LLMs) is a promising solution. However, prior studies have underexplored structured LLM workflows, including explicit reasoning outputs, few-shot prompting, and task-decomposition. Methods We systematically devised and evaluated multiple LLM-based workflows using both open-source and proprietary models. The most promising workflows were validated on eight independent SR datasets, focusing on EMF and non-EMF research domains. Workflows were designed to elicit PECOS-wise decisions with explicit reasoning, and record-level verdicts were derived using deterministic decision rules. Results Three workflows, one based on an open-source (llama3.3:70b) and two based on proprietary LLMs, achieved high sensitivity while substantially reducing manual screening effort. The proprietary LLM gpt-4.1-mini embedded in a few-shot workflow with PECOS-wise reasoning, reached a pooled sensitivity of 96.4% (95% CI: 94.8%–97.6%) with a workload reduction of 80.4% (95% CI: 63.7%–90.5%) at an approximate batch API cost of $1.0 per 1,000 records. Overall, small “mini” models performed competitively, demonstrating cost-efficient and resource-friendly applicability. Conclusions Carefully selected LLM workflows implementing few-shot prompting and explicit PECOS-wise reasoning can achieve near-human sensitivity while substantially reducing manual screening effort. These findings provide a transparent and versatile framework for AI-assisted literature screening in systematic reviews, although further optimisation is needed to improve specificity, with executable code for the best workflows available at https://github.com/openbfs/ai-sr-litscreen.
- 4 September 2026
- Published by Springer Nature in Research Square
Open AccessCost-Efficient Large Language Model-Assisted Title and Abstract Screening for Systematic Reviews: Method Evaluation and Validation
Background The yearly number of publications in many fields, including research on potential health effects of electromagnetic fields (EMF), has steadily risen, making systematic reviews (SRs) increasingly laborious. Automating the title and abstract screening phase using large language models (LLMs) is a promising solution. However, prior studies have underexplored structured LLM workflows, including explicit reasoning outputs, few-shot prompting, and task-decomposition. Methods We systematically devised and evaluated multiple LLM-based workflows using both open-source and proprietary models. The most promising workflows were validated on eight independent SR datasets, focusing on EMF and non-EMF research domains. Workflows were designed to elicit PECOS-wise decisions with explicit reasoning, and record-level verdicts were derived using deterministic decision rules. Results Three workflows, one based on an open-source (llama3.3:70b) and two based on proprietary LLMs, achieved high sensitivity while substantially reducing manual screening effort. The proprietary LLM gpt-4.1-mini embedded in a few-shot workflow with PECOS-wise reasoning, reached a pooled sensitivity of 96.4% (95% CI: 94.8%–97.6%) with a workload reduction of 80.4% (95% CI: 63.7%–90.5%) at an approximate batch API cost of $1.0 per 1,000 records. Overall, small “mini” models performed competitively, demonstrating cost-efficient and resource-friendly applicability. Conclusions Carefully selected LLM workflows implementing few-shot prompting and explicit PECOS-wise reasoning can achieve near-human sensitivity while substantially reducing manual screening effort. These findings provide a transparent and versatile framework for AI-assisted literature screening in systematic reviews, although further optimisation is needed to improve specificity, with executable code for the best workflows available at https://github.com/openbfs/ai-sr-litscreen.
- Open Access
- 28 July 2026
- Published by IOP Publishing in Journal of Radiological Protection
- Vol. 46 (3) , 031520
Spotlight on EMF research: a literature review service by the German federal office for radiation protection
In the area of research on electromagnetic fields (EMFs) and health, decision makers and practitioners face an increasingly complex information landscape, characterised by high publication volumes, heterogeneous methods and the occasional spread of oversimplified claims. ‘ Spotlight on EMF Research ’, offered by the German Federal Office for Radiation Protection (BfS), wants to support the EMF-interested community by providing regular, structured assessments of selected scientific publications. Spotlight on EMF Research offers concise summaries and critical commentaries, brief Literature Suggestions, comprehensive literature lists, and a quarterly newsletter aimed at regulators, advisory bodies, scientists, and other expert users. This article describes the underlying rationale and workflow, including regular database searches, AI-assisted categorisation, and an interdisciplinary editorial and review process. It also presents descriptive data on the screened and featured literature and summarises early user feedback. We discuss the systematic limitations and potential selection biases of the format, its implications for risk communication in a changing media landscape, and how Spotlight on EMF Research complements existing scientific EMF literature information services.
- 28 July 2026
- Published by IOP Publishing in Journal of Radiological Protection
- Vol. 46 (3) , 031520
Open AccessSpotlight on EMF research: a literature review service by the German federal office for radiation protection
In the area of research on electromagnetic fields (EMFs) and health, decision makers and practitioners face an increasingly complex information landscape, characterised by high publication volumes, heterogeneous methods and the occasional spread of oversimplified claims. ‘ Spotlight on EMF Research ’, offered by the German Federal Office for Radiation Protection (BfS), wants to support the EMF-interested community by providing regular, structured assessments of selected scientific publications. Spotlight on EMF Research offers concise summaries and critical commentaries, brief Literature Suggestions, comprehensive literature lists, and a quarterly newsletter aimed at regulators, advisory bodies, scientists, and other expert users. This article describes the underlying rationale and workflow, including regular database searches, AI-assisted categorisation, and an interdisciplinary editorial and review process. It also presents descriptive data on the screened and featured literature and summarises early user feedback. We discuss the systematic limitations and potential selection biases of the format, its implications for risk communication in a changing media landscape, and how Spotlight on EMF Research complements existing scientific EMF literature information services.