Peter May

Peter May

Auto-generated profile, based on publicly available information

Peter May

Department of Medicine III, TUM School of Medicine and Health, Technical University of Munich, Ismaninger Str. 22, Munich, Bavaria, 81675, Germany, +49 8941408753

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
10 January 2023 in Immunity
Verified
Journal Article
Open access
DBDaria Briukhovetska
Daria Briukhovetska
JSJavier Suarez-Gosalvez
Javier Suarez-Gosalvez
CVCornelia Voigt
Cornelia Voigt
AMAnamarija Markota
Anamarija Markota
AGAnastasios D. Giannou
Anastasios D. Giannou
SKSebastian Kobold
Sebastian Kobold
Although T cells can exert potent anti-tumor immunity, a subset of T helper (Th) cells producing interleukin-22 (IL-22) in breast and lung tumors is linked to dismal patient outcome. Here, we examined the mechanisms whereby these T cells contribute to disease. In murine models of lung and breast cancer, constitutional and T cell-specific deletion of Il22 reduced metastases without affecting primary tumor growth. Deletion of the IL-22 receptor on cancer cells decreases metastasis to a degree similar to that seen in IL-22-deficient mice. IL-22 induced high expression of CD155, which bound to the activating receptor CD226 on NK cells. Excessive activation led to decreased amounts of CD226 and functionally impaired NK cells, which elevated the metastatic burden. IL-22 signaling was also associated with CD155 expression in human datasets and with poor patient outcomes. Taken together, our findings reveal an immunosuppressive circuit activated by T cell-derived IL-22 that promotes lung metastasis.

10 January 2023 in Immunity
Verified
Journal Article
Open access
AGAnastasios D. Giannou
Anastasios D. Giannou
JKJan Kempski
Jan Kempski
ASAhmad Mustafa Shiri
Ahmad Mustafa Shiri
JLJöran Lücke
Jöran Lücke
TZTao Zhang
Tao Zhang
Samuel HuberSamuel Huber
Samuel Huber
During metastasis, cancer cells invade, intravasate, enter the circulation, extravasate, and colonize target organs. Here, we examined the role of interleukin (IL)-22 in metastasis. Immune cell-derived IL-22 acts on epithelial tissues, promoting regeneration and healing upon tissue damage, but it is also associated with malignancy. Il22-deficient mice and mice treated with an IL-22 antibody were protected from colon-cancer-derived liver and lung metastasis formation, while overexpression of IL-22 promoted metastasis. Mechanistically, IL-22 acted on endothelial cells, promoting endothelial permeability and cancer cell transmigration via induction of endothelial aminopeptidase N. Multi-parameter flow cytometry and single-cell sequencing of immune cells isolated during cancer cell extravasation into the liver revealed iNKT17 cells as source of IL-22. iNKT-cell-deficient mice exhibited reduced metastases, which was reversed by injection of wild type, but not Il22-deficient, invariant natural killer T (iNKT) cells. IL-22-producing iNKT cells promoting metastasis were tissue resident, as demonstrated by parabiosis. Thus, IL-22 may present a therapeutic target for prevention of metastasis.

1 January 2026 in JCO Clinical Cancer Informatics
Verified
Journal Article
Open access
PMPeter May
Peter May
SNSina Nokodian
Sina Nokodian
CNChristoph Nuernbergk
Christoph Nuernbergk
MKManuel Knauer
Manuel Knauer
MHMaike Hefter
Maike Hefter
JJJohannes Jung
Johannes Jung
PURPOSE: In high-risk specialties such as oncology, errors in clinical documentation can have severe consequences, highlighting a need for enhanced safety checks. We therefore aimed to evaluate the capability of frontier large language models (LLMs) to identify and correct errors in complex clinical documentation in oncology. METHODS: We conducted a two-phase evaluation. First, we assessed LLMs (GPT o4-mini and Gemini 2.5 Pro) on 1,000 synthetic clinical hematology/oncology vignettes with controlled errors, benchmarking against human expert data for error flag detection and sentence localization. Second, we evaluated advanced LLMs and a local LLM (Gemma 3 27B) against six clinicians in detecting single, predefined, and clinically relevant errors, such as wrong risk classifications or omission of critical medication within 90 synthetic discharge summaries from oncologic patients. RESULTS: LLMs outperformed human benchmark in error flag and sentence localization tasks, with Gemini 2.5 Pro achieving top accuracies of 0.928 and 0.915, respectively. Results were robust across subgroups and scalable, with simultaneous processing of up to 50 vignettes. Within complex discharge summaries, Gemini 2.5 Pro and GPT o4-mini-high identified 97.8% and 87.8% of injected errors, respectively, substantially exceeding the 47.8% average detection rate of human specialists. Gemma 3 27B detected 35.6% of errors. Analysis of error detection overlap revealed a synergistic potential for hybrid human-artificial intelligence (AI) systems. CONCLUSION: Frontier LLMs exhibit superior error‐detection capabilities and speed compared with both local models and human specialists, who are inherently time-constrained. Although synthetic data provide a controlled testbed, real-world evaluation across diverse errors and documentation styles remains critical. Advanced LLMs can serve as powerful assistants for clinical documentation reviews, substantially reducing the risk of oversight and clinician workload. Integrating LLM‐driven error flagging into electronic health record workflows offers a promising strategy for enhancing documentation accuracy, treatment quality, and patient safety in oncology.

1 December 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
PMPeter May
Peter May
JGJulian Greß
Julian Greß
CSChristoph Seidel
Christoph Seidel
SSSebastian Sommer
Sebastian Sommer
MSMarkus K. Schuler
Markus K. Schuler
JJJohannes Jung
Johannes Jung
Background: Traditional cancer registries, limited by labor-intensive manual data abstraction and rigid, predefined schemas, often hinder timely and comprehensive oncology research. While large language models (LLMs) have shown promise in automating data extraction, their potential to perform direct, just-in-time (JIT) analysis on unstructured clinical narratives—potentially bypassing intermediate structured databases for many analytical tasks—remains largely unexplored. Objective: This study aimed to evaluate whether a state-of-the-art LLM (Gemini 2.5 Pro) can enable a JIT clinical oncology analysis paradigm by assessing its ability to (1) perform high-fidelity multiparameter data extraction, (2) answer complex clinical queries directly from raw text, (3) automate multistep survival analyses including executable code generation, and (4) generate novel, clinically plausible hypotheses from free-text documentation. Methods: A synthetic dataset of 240 unstructured clinical letters from patients with stage IV non–small cell lung cancer (NSCLC), embedding 14 predefined variables, was used. Gemini 2.5 Pro was evaluated on four core JIT capabilities. Performance was measured by using the following metrics: extraction accuracy (compared to human extraction of n=40 letters and across the full n=240 dataset); numerical deviation for direct question answering (n=40 to 240 letters, 5 questions); log-rank P value and Harrell concordance index for LLM-generated versus ground-truth Kaplan-Meier survival analyses (n=160 letters, overall survival and progression-free survival); and correct justification, novelty, and a qualitative evaluation of LLM-generated hypotheses (n=80 and n=160 letters). Results: For multiparameter extraction from 40 letters, the LLM achieved >99% average accuracy, comparable to human extraction, but in significantly less time (LLM: 3.7 min vs human: 133.8 min). Across the full 240-letter dataset, LLM multiparameter extraction maintained >98% accuracy for most variables. The LLM answered multiconditional clinical queries directly from raw text with a relative deviation rarely exceeding 1.5%, even with up to 240 letters. Crucially, it autonomously performed end-to-end survival analysis, generating text-to-R-code that produced Kaplan-Meier curves statistically indistinguishable from ground truth. Consistent performance was demonstrated on a small validation cohort of 80 synthetic acute myeloid leukemia reports. Stress testing on data with simulated imperfections revealed a key role of a human-in-the-loop to resolve AI-flagged ambiguities. Furthermore, the LLM generated several correctly justified, biologically plausible, and potentially novel hypotheses from datasets up to 80 letters. Conclusions: This feasibility study demonstrated that a frontier LLM (Gemini 2.5 Pro) can successfully perform high-fidelity data extraction, multiconditional querying, and automated survival analysis directly from unstructured text. These results provide a foundational proof of concept for the JIT clinical analysis approach. However, these findings are confined to synthetic patients, and rigorous validation on real-world clinical data is an essential next step before clinical implementation can be considered.

1 September 2025 in Translational Lung Cancer Research
Verified
Journal Article
Open access
PDF file
PMPeter May
Peter May
CWChristof Winter
Christof Winter
IHInga Hubrecht
Inga Hubrecht
EOEva Ortner
Eva Ortner
SSSelina Strathmeyer
Selina Strathmeyer
ARAaron Becker von Rose
Aaron Becker von Rose
Background: Small cell lung cancer (SCLC) is characterized by an aggressive clinical course and poor survival rates. The introduction of immune checkpoint blockade (ICB) into the frontline treatment of extensive-stage (ES)-SCLC with programmed death-ligand 1 (PD-L1) inhibitors such as atezolizumab and durvalumab has improved outcomes. However, median overall survival (OS) is still limited to approximately 12 months, underscoring the need for predictive biomarkers to optimize treatment selection. Notably, recent subgroup analyses suggest potential sex-specific differences in response to ICB, with improved outcomes observed in female patients. However, the biological mechanisms underlying these differences remain unclear. Additionally, metabolic factors may influence response to immunotherapy, yet their roles in ES-SCLC remain underexplored. This study aims to evaluate the impact of sex and metabolic phenotypes on treatment outcomes in ES-SCLC patients receiving atezolizumab and to identify potential metabolic biomarkers of response. Methods: This retrospective single-center study evaluated the impact of sex and metabolic phenotypes on treatment outcomes in ES-SCLC patients receiving atezolizumab. Seventy patients were analyzed: 33 treated with atezolizumab plus chemotherapy (September 2019 to May 2024) and 37 historical controls who received chemotherapy alone (January 2014 to September 2019). Primary endpoints were OS and progression-free survival (PFS). Additionally, targeted metabolomic profiling was performed using nuclear magnetic resonance (NMR) spectroscopy on serum samples from 12 patients receiving atezolizumab, yielding 55 serum samples for analysis. Results: Our study replicated the OS benefit of atezolizumab, with the greatest advantage observed in female patients (median OS: 20.2 vs. 11.7 months). Body mass index (BMI) and uric acid levels exhibited an inverse U-shaped relationship with OS, suggesting a possible metabolic influence on immunotherapy efficacy. Multivariate analysis confirmed female sex and lower lactate dehydrogenase levels as independent prognostic factors for improved survival. Additionally, preliminary metabolome analysis identified distinct metabolite profiles in responders (PFS >6 months), including elevated cystine, histidine, and creatine, and reduced phenylalanine levels. Conclusions: These findings support the hypothesis that both sex and metabolic factors modulate responses to ICB in ES-SCLC. Further research is warranted to validate these biomarkers and explore potential interventions to enhance immunotherapy efficacy in this aggressive malignancy.

20 August 2026 in JMIR AI
Verified
Journal Article
Open access
MKManuel Knauer
Manuel Knauer
JGJulian Greß
Julian Greß
JKJakob Nikolas Kather
Jakob Nikolas Kather
PMPeter May
Peter May
Background: Maintenance of oncology clinical practice guidelines (CPGs) is increasingly challenged by the rapid growth of trial data and therapeutic complexity. While large language models (LLMs) have shown promise in information retrieval, their utility in the rigorous, end-to-end workflow of guideline maintenance remains underexplored. Objective: This case study aimed to systematically evaluate the performance of frontier LLMs in supporting oncology guideline maintenance. We sought to determine their reliability in predicting necessary guideline updates based on new evidence, their accuracy in extracting data from clinical trials, and their effectiveness as automated auditors for detecting errors in established guidelines. Methods: Using the Onkopedia peripheral T-cell lymphoma (PTCL) guideline as a prospective case study, we tasked frontier models with deep-research modes and autonomous web-search capabilities (Gemini 2.5 Pro and GPT o4-mini-high) to predict a guideline update in August 2025 based on the 2021 version. Predictions were validated against the official 2025 revision published in October 2025. Next, we benchmarked evidence extraction accuracy across 80 pivotal trials using models of varying scale (27B-671B parameters vs frontier). Finally, we deployed a stacked LLM workflow to audit 28 recently updated Onkopedia guidelines for linguistic and content-related errors. Results: In the predictive task, models captured 36.7% to 40% of substantive updates, often identifying landmark approvals, but frequently overstating evidence. An independent, model-blinded rescoring yielded substantial agreement (weighted Cohen κ=0.75) and confirmed predictive accuracies of 35% to 38.3%. While frontier models demonstrated high accuracy (up to 99.2%) in extracting data from individual studies, substantially outperforming smaller open-source models, this precision declined during multisource synthesis. We observed a position-dependent performance drop in long-form generation, with GPT’s endpoint accuracy dropping from 84.6% in the first half of the drafted guideline to 38.5% in the second half. As automated auditors of existing CPGs, the models successfully identified a median of 16.5 (IQR 13.8-20.3) formal errors per document and detected several clinically relevant inconsistencies (eg, invalid scoring formulas and incorrect staging definitions). Conclusions: LLMs currently lack the reasoning stability for autonomous guideline authoring due to deficits in complex synthesis. However, they are effective tools for high-fidelity evidence extraction and automated quality assurance, supporting a human-led, AI-augmented workflow for efficient guideline maintenance.