FMFlorian Meer

Florian Meer

*This is an algorithmically generated author record based on publicly available information.

Florian Meer has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Analysis of eligibility criteria clusters based on large language models for clinical trial design

    by Alban Bornet, Philipp Khlebnikov, Florian Meer, Quentin Haas, Anthony Yazdani, Boya Zhang, Poorya Amini, Douglas Teodoro

    Objectives: Clinical trials (CTs) are essential for improving patient care by evaluating new treatments’ safety and efficacy. A key component in CT protocols is the study population defined by the eligibility criteria. This study aims to evaluate the effectiveness of large language models (LLMs) in encoding eligibility criterion information to support CT-protocol design. Materials and Methods: We extracted eligibility criterion sections, phases, conditions, and interventions from CT protocols available in the ClinicalTrials.gov registry. Eligibility sections were split into individual rules using a criterion tokenizer and embedded using LLMs. The obtained representations were clustered. The quality and relevance of the clusters for protocol design was evaluated through 3 experiments: intrinsic alignment with protocol information and human expert cluster coherence assessment, extrinsic evaluation through CT-level classification tasks, and eligibility section generation. Results: Sentence embeddings fine-tuned using biomedical corpora produce clusters with the highest alignment to CT-level information. Human expert evaluation confirms that clusters are well structured and coherent. Despite the high information compression, clusters retain significant CT information, up to 97% of the classification performance obtained with raw embeddings. Finally, eligibility sections automatically generated using clusters achieve 95% of the ROUGE scores obtained with a generative LLM prompted with CT-protocol details, suggesting that clusters encapsulate information useful to CT-protocol design. Discussion: Clusters derived from sentence-level LLM embeddings effectively summarize complex eligibility criterion data while retaining relevant CT-protocol details. Clustering-based approaches provide a scalable enhancement in CT design that balances information compression with accuracy. Conclusions: Clustering eligibility criteria using LLM embeddings provides a practical and efficient method to summarize critical protocol information. We provide an interactive visualization of the pipeline here.


  • Open Access

    Analysis of Eligibility Criteria Clusters Based on Large Language Models for Clinical Trial Design

    by Alban Bornet, Philipp Khlebnikov, Florian Meer, Quentin Haas, Anthony Yazdani, Boya Zhang, Poorya Amini, Douglas Teodoro

    Objectives Clinical trials (CTs) are essential for improving patient care by evaluating new treatments’ safety and efficacy. A key component in CT protocols is the study population defined by the eligibility criteria. This study aims to evaluate the effectiveness of large language models (LLMs) in encoding eligibility criterion information to support CT protocol design. Materials and Methods We extracted eligibility criterion sections, phases, conditions, and interventions from CT protocols available in the ClinicalTrials.gov registry. Eligibility sections were split into individual rules using a criterion tokenizer and embedded using LLMs. The obtained representations were clustered. The quality and relevance of the clusters for protocol design was evaluated through 3 experiments: intrinsic alignment with protocol information and human expert cluster coherence assessment, extrinsic evaluation through CT-level classification tasks, and eligibility section generation. Results Sentence embeddings fine-tuned using biomedical corpora produce clusters with the highest alignment to CT-level information. Human expert evaluation confirms that clusters are well-structured and coherent. Despite the high information compression, clusters retain significant CT information, up to 97% of the classification performance obtained with raw embeddings. Finally, eligibility sections automatically generated using clusters achieve 95% of the ROUGE scores obtained with a generative LLM. Conclusions We show that clusters derived from sentence-level LLM embeddings are effective in summarizing complex eligibility criterion data while retaining relevant CT protocol details. Clustering-based approaches provide a scalable enhancement in CT design that balances information compression with accuracy.

  • Open Access

    Morphometry and mechanical instability at the onset of epithelial bladder cancer

    by Franziska L. Lampart, Roman Vetter, Yifan Wang, Kevin A. Yamauchi, Nico Strohmeyer, Florian Meer, Marie-Didiée Hussherr, Gieri Camenisch, Hans-Helge Seifert, Cyrill A. Rentsch, et al.

    Malignancies of epithelial tissues, called carcinomas, account for the majority of cancer cases. Much cancer research has focused on genetic alterations and their relation to different carcinoma phenotypes. Besides a rewiring in the signalling networks, carcinoma progression is accompanied by mechanical changes in the epithelial cells and the extracellular matrix. Here, we reveal intricate morphologies in the basement membrane at the onset of bladder cancer, and propose that they emerge from a mechanical buckling instability upon epithelial overgrowth. Using a combination of microscopy imaging of the mouse and human bladder tissue, elasticity theory, and numerical simulations of differential growth in the bladder mucosa, we find that aberrant tissue morphologies can emerge through stiffness changes in the different mucosa layers. The resulting thickening, wrinkles and folds exhibit qualitative and quantitative similarity with imaged early papillary tumors and carcinomas in situ . Atomic force microscopy indeed reveals local stiffness changes in the pathological basement membrane. Our findings suggest a mechanical origin of the different carcinoma subtypes in the bladder, which have vastly different clinical prognosis. They might provide the basis for a new line of attack in medical carcinoma treatment and prophylaxis.