A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [¹⁸F]FDG-PET/CT parameters.

"more detailed descriptions of each feature and its categories are provided in the open data repository zenodo (10 5281/zenodo 7094287).; all scripts that were used for the following steps of feature preprocessing and machine learning are provided in the open data repository zenodo (10 5281/zenodo 7094287).; data availability the datasets and scripts generated during and/or analysed during the current study are available in the zenodo repository 10 5281/zenodo 7094287. data availability the datasets and scripts generated during and/or analysed during the current study are available in the zenodo"

"an openly accessible web application was programmed and published at github ( https://baumgagl github io/pet_ln_calculator/ ).; to facilitate the usage of the model a user-friendly online tool can be accessed ( https://baumgagl github io/pet_ln_calculator/ )."

"Declarations Ethics approvalThis is a retrospective, monocentric analysis. Approval was granted by the Ethics Committee of the Charité – Universitätsmedizin Berlin (25.05.2021, No EA2/100/21). Consent to participateInformed consent for data analysis for research purpose was obtained from all individual participants included in the study. Consent for publicationThe authors affirm that human research participants provided informed consent for the publication of the images in Fig. 2 as well as Figures S4.11, S4.12 and S4.13. Competing interestsJulian M.M. Rogasch is a participant in the BIH-Charité Digital Clinician Scientist Program funded by the Charité – Universitätsmedizin Berlin, the Berlin Institute of Health, and the German Research Foundation (DFG). Tobias Penzkofer was supported by Berlin Institute of Health (Clinician Scientist Grant, Platform Grant), Ministry of Education and Research (BMBF, 01KX2021, 68GX21001A), German Research Foundation (DFG, SFB 1340/2), Horizon 2020 (952172) and reports research agreements (no personal payments, outside of submitted work) with AGO, Aprea AB, ARCAGY-GINECO, Astellas Pharma Global Inc. (APGD), Astra Zeneca, Clovis Oncology, Inc., Dohme Corp, Holaira, Incyte Corporation, Karyopharm, Lion Biotechnologies, Inc., MedImmune, Merck Sharp, Millennium Pharmaceuticals, Inc., Morphotec Inc., NovoCure Ltd., PharmaMar S.A. and PharmaMar USA, Inc., Roche, Siemens Healthineers, and TESARO Inc., and fees for a book translation (Elsevier). All other authors have no relevant financial or non-financial interests to disclose. Competing interests Julian M.M. Rogasch is a participant in the BIH-Charité Digital Clinician Scientist Program funded by the Charité – Universitätsmedizin Berlin, the Berlin Institute of Health, and the German Research Foundation (DFG). Tobias Penzkofer was supported by Berlin Institute of Health (Clinician Scientist Grant, Platform Grant), Ministry of Education and Research (BMBF, 01KX2021, 68GX21001A), German Research Foundation (DFG, SFB 1340/2), Horizon 2020 (952172) and reports research agreements (no personal payments, outside of submitted work) with AGO, Aprea AB, ARCAGY-GINECO, Astellas Pharma Global Inc. (APGD), Astra Zeneca, Clovis Oncology, Inc., Dohme Corp, Holaira, Incyte Corporation, Karyopharm, Lion Biotechnologies, Inc., MedImmune, Merck Sharp, Millennium Pharmaceuticals, Inc., Morphotec Inc., NovoCure Ltd., PharmaMar S.A. and PharmaMar USA, Inc., Roche, Siemens Healthineers, and TESARO Inc., and fees for a book translation (Elsevier). All other authors have no relevant financial or non-financial interests to disclose."

"Funding Open Access funding enabled and organized by Projekt DEAL."