{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T04:23:49Z","timestamp":1792038229624,"version":"4.4.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["16KISA100k"],"award-info":[{"award-number":["16KISA100k"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["454245598"],"award-info":[{"award-number":["454245598"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["521379614"],"award-info":[{"award-number":["521379614"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003107","name":"Bundesministerium f\u00fcr Gesundheit","doi-asserted-by":"publisher","award":["ZMVI1-2520DAT111"],"award-info":[{"award-number":["ZMVI1-2520DAT111"]}],"id":[{"id":"10.13039\/501100003107","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Mental Health Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Prompt engineering has the potential to enhance large language models\u2019 (LLM) ability to solve tasks through improved in-context learning. In clinical research, the use of LLMs has shown expert-level performance for a variety of tasks ranging from pathology slide classification to identifying suicidality. We introduce clickBrick, a modular prompt-engineering framework, and rigorously test its effectiveness. Here, we explore the effects of increasingly structuring prompts with the clickBrick framework for a comprehensive psychopathological assessment of 100 index patients from psychiatric electronic health records. We compare the performance of two locally-run LLMs against an expert-labeled ground truth for a variety of successively built-up prompts for the extraction of 12 transdiagnostic psychopathological criteria. Potential clinical value was explored by training linear support vector machines on outputs from the strongest and weakest prompts to predict discharge ICD-10 main diagnoses for a historical sample of 1692 patients. We could reliably extract information across 12 distinct psychopathological classification tasks from unstructured clinical text with balanced accuracies spanning 71% to 94%. Across tasks, we observed a substantially improved extraction accuracy (between +19% and +36%) using clickBrick for the most reactive model. The comparison unveiled great variations between prompts with a reasoning prompt performing best in 7 out of 12 domains. Clinical value and internal validity were approximated by downstream classification of eventual psychiatric diagnoses for 1,692 patients. Here, clickBrick led to an improvement in overall classification accuracy from 71% to 76%. ClickBrick prompt engineering, i.e., iterative, expert-led design and testing, is critical for unlocking LLMs\u2019 clinical potential. The framework offers a reproducible, explainable pathway for deploying trustworthy generative AI across mental health and other clinical fields.<\/jats:p>","DOI":"10.1038\/s44184-026-00224-3","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T18:38:09Z","timestamp":1782412689000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["clickBrick prompt engineering: optimizing large language model performance in clinical psychiatry"],"prefix":"10.1038","volume":"5","author":[{"given":"Falk Gerrik","family":"Verhees","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Huth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Pfennig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Ritter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob Nikolas","family":"Kather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabella Catharina","family":"Wiest","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavol","family":"Mikolas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"224_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51465-9","volume":"15","author":"D Ferber","year":"2024","unstructured":"Ferber, D. et al. In-context learning enables multimodal large language models to classify cancer pathology images. Nat. Commun. 15, 10104 (2024).","journal-title":"Nat. Commun."},{"key":"224_CR2","doi-asserted-by":"crossref","unstructured":"Wiest, I. C. et al. Detection of suicidality from medical text using privacy-preserving large language models. Br. J. Psychiatry 1\u20136 (2024).","DOI":"10.1101\/2024.03.06.24303763"},{"key":"224_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-024-01029-4","volume":"7","author":"L Wang","year":"2024","unstructured":"Wang, L. et al. Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. Npj Digit. Med. 7, 1\u20139 (2024).","journal-title":"Npj Digit. Med."},{"key":"224_CR4","first-page":"478","volume":"2024","author":"X Zhang","year":"2024","unstructured":"Zhang, X. et al. Comparison of prompt engineering and fine-tuning strategies in large language models in the classification of clinical notes. AMIA Summits Transl. Sci. Proc. 2024, 478\u2013487 (2024).","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"224_CR5","doi-asserted-by":"crossref","unstructured":"Meincke, L., Mollick, E. R., Mollick, L. & Shapiro, D. Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting. 2025; published online June 8. https:\/\/papers.ssrn.com\/abstract=5285532 (accessed June 8, 2025).","DOI":"10.2139\/ssrn.5285532"},{"key":"224_CR6","unstructured":"Prompt engineering overview. Anthropic. https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/prompt-engineering\/overview (accessed June 2, 2025)."},{"key":"224_CR7","unstructured":"Boonstra L. Prompt Engineering. 2025; published online Feb. https:\/\/www.kaggle.com\/whitepaper-prompt-engineering."},{"key":"224_CR8","doi-asserted-by":"crossref","unstructured":"Hein, D. et al. Iterative refinement and goal articulation to optimize large language models for clinical information extraction. NPJ Digit. Med. 8, 301 (2025).","DOI":"10.1038\/s41746-025-01686-z"},{"key":"224_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01618-7","volume":"15","author":"M Ganzinger","year":"2025","unstructured":"Ganzinger, M. et al. Automated generation of discharge summaries: leveraging large language models with clinical data. Sci. Rep. 15, 16466 (2025).","journal-title":"Sci. Rep."},{"key":"224_CR10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.euroneuro.2024.07.012","volume":"88","author":"CU Correll","year":"2024","unstructured":"Correll, C. U. et al. The Transdiagnostic Global Impression - Psychopathology scale (TGI-P): initial development of a novel transdiagnostic tool for assessing, tracking, and visualising psychiatric symptom severity in everyday practice. Eur. Neuropsychopharmacol. J. Eur. Coll. Neuropsychopharmacol. 88, 31\u201339 (2024).","journal-title":"Eur. Neuropsychopharmacol. J. Eur. Coll. Neuropsychopharmacol."},{"key":"224_CR11","doi-asserted-by":"publisher","unstructured":"McCluskey, R., Enshaei, A. & Hasan, B. A. S. Finding the Ground-Truth from Multiple Labellers: Why Parameters of the Task Matter. 2021; published online Feb 16. https:\/\/doi.org\/10.48550\/arXiv.2102.08482.","DOI":"10.48550\/arXiv.2102.08482"},{"key":"224_CR12","unstructured":"meta-llama\/Llama-3.1-70B-Instruct \u00b7 Hugging Face. 2024; published online Dec 6. https:\/\/huggingface.co\/meta-llama\/Llama-3.1-70B-Instruct (accessed June 26, 2025)."},{"key":"224_CR13","unstructured":"openai\/gpt-oss-120b \u00b7 Hugging Face. 2025; published online Aug 7. https:\/\/huggingface.co\/openai\/gpt-oss-120b (accessed March 11, 2026)."},{"key":"224_CR14","unstructured":"ggml-org\/llama.cpp. 2025; published online June 26. https:\/\/github.com\/ggml-org\/llama.cpp (accessed June 26, 2025)."},{"key":"224_CR15","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant, J. et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat. Med 31, 60\u201369 (2025).","journal-title":"Nat. Med"},{"key":"224_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2024.105699","volume":"162","author":"D Oliver","year":"2024","unstructured":"Oliver, D. et al. Exploring causal mechanisms of psychosis risk. Neurosci. Biobehav Rev. 162, 105699 (2024).","journal-title":"Neurosci. Biobehav Rev."},{"key":"224_CR17","unstructured":"KatherLab\/LLMAIx. 2025; published online April 10. https:\/\/github.com\/KatherLab\/LLMAIx (accessed April 12, 2025)."},{"key":"224_CR18","doi-asserted-by":"publisher","unstructured":"The pandas development. pandas-dev\/pandas: Pandas team. 2020; published online Feb. https:\/\/doi.org\/10.5281\/zenodo.3509134.","DOI":"10.5281\/zenodo.3509134"},{"key":"224_CR19","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C. R. et al. Array programming with NumPy. Nature 585, 357\u2013362 (2020).","journal-title":"Nature"},{"key":"224_CR20","doi-asserted-by":"crossref","unstructured":"Seabold, S. & Perktold, J. statsmodels: Econometric and statistical modeling with Python. In: 9th Python in Science Conference. (2010).","DOI":"10.25080\/Majora-92bf1922-011"},{"key":"224_CR21","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn Res 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn Res"},{"key":"224_CR22","unstructured":"Python 3.12 documentation. Python Doc. https:\/\/docs.python.org\/3\/ (accessed June 20, 2025)."},{"key":"224_CR23","doi-asserted-by":"publisher","first-page":"AIdbp2400537","DOI":"10.1056\/AIdbp2400537","volume":"2","author":"IC Wiest","year":"2025","unstructured":"Wiest, I. C. et al. Deidentifying medical documents with local, privacy-preserving large language models: the LLM-anonymizer. NEJM AI 2, AIdbp2400537 (2025).","journal-title":"NEJM AI"},{"key":"224_CR24","doi-asserted-by":"crossref","unstructured":"Wiest, I. C. et al. A software pipeline for medical information extraction with large language models, open source and suitable for oncology. NPJ Precis. Oncol. 9, 313 (2025).","DOI":"10.1038\/s41698-025-01103-4"},{"key":"224_CR25","doi-asserted-by":"publisher","first-page":"1156","DOI":"10.1001\/jamapsychiatry.2018.2165","volume":"75","author":"N Koutsouleris","year":"2018","unstructured":"Koutsouleris, N. et al. Prediction models of functional outcomes for individuals in the clinical high-risk state for psychosis or with recent-onset depression: a multimodal, multisite machine learning analysis. JAMA Psychiatry 75, 1156\u20131172 (2018).","journal-title":"JAMA Psychiatry"},{"key":"224_CR26","unstructured":"The MathWorks Inc. MATLAB version: 9.14.0.2206163 (R2023a). https:\/\/www.mathworks.com (2023)."},{"key":"224_CR27","doi-asserted-by":"publisher","DOI":"10.1002\/sim.10320","volume":"44","author":"A Carriero","year":"2025","unstructured":"Carriero, A. et al. The harms of class imbalance corrections for machine learning based prediction models: a simulation study. Stat. Med 44, e10320 (2025).","journal-title":"Stat. Med"},{"key":"224_CR28","doi-asserted-by":"publisher","unstructured":"Hughes, J. et al. Best-of-N Jailbreaking. published online Dec 19. https:\/\/doi.org\/10.48550\/arXiv.2412.03556 (2024).","DOI":"10.48550\/arXiv.2412.03556"},{"key":"224_CR29","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis, J. R. & Koch, G. G. The measurement of observer agreement for categorical data. Biometrics 33, 159\u2013174 (1977).","journal-title":"Biometrics"},{"key":"224_CR30","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/S2215-0366(20)30147-4","volume":"7","author":"RJ Drake","year":"2020","unstructured":"Drake, R. J. et al. Effect of delaying treatment of first-episode psychosis on symptoms and social outcomes: a longitudinal analysis and modelling study. Lancet Psychiatry 7, 602\u2013610 (2020).","journal-title":"Lancet Psychiatry"},{"key":"224_CR31","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1111\/acps.13490","volume":"146","author":"J Scott","year":"2022","unstructured":"Scott, J. et al. A systematic review and meta-analysis of delayed help-seeking, delayed diagnosis and duration of untreated illness in bipolar disorders. Acta Psychiatr. Scand. 146, 389\u2013405 (2022).","journal-title":"Acta Psychiatr. Scand."},{"key":"224_CR32","doi-asserted-by":"publisher","DOI":"10.1038\/srep26094","volume":"6","author":"R Miotto","year":"2016","unstructured":"Miotto, R., Li, L., Kidd, B. A. & Dudley, J. T. Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci. Rep. 6, 26094 (2016).","journal-title":"Sci. Rep."},{"key":"224_CR33","doi-asserted-by":"crossref","unstructured":"Zhuo, J. et al. ProSA: assessing and Understanding the Prompt Sensitivity of LLMs. in Findings of the Association for Computational Linguistics: EMNLP 2024. (Al-Onaizan Y., Bansal M., Chen Y.-N., eds) 1950\u20131976 (Miami, Florida, USA: Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.108"},{"key":"224_CR34","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1038\/s41591-026-04252-6","volume":"32","author":"L Luo","year":"2026","unstructured":"Luo, L. et al. A clinical environment simulator for dynamic AI evaluation. Nat. Med 32, 820\u2013827 (2026).","journal-title":"Nat. Med"},{"key":"224_CR35","doi-asserted-by":"publisher","unstructured":"Belcak, P. et al. Small Language Models are the Future of Agentic AI. 2025; published online Sept 15. https:\/\/doi.org\/10.48550\/arXiv.2506.02153.","DOI":"10.48550\/arXiv.2506.02153"},{"key":"224_CR36","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s42256-024-00944-1","volume":"6","author":"J Qiu","year":"2024","unstructured":"Qiu, J. et al. LLM-based agentic systems in medicine and healthcare. Nat. Mach. Intell. 6, 1418\u20131420 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"224_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-023-00970-0","volume":"7","author":"M Guevara","year":"2024","unstructured":"Guevara, M. et al. Large language models to identify social determinants of health in electronic health records. Npj Digit Med 7, 1\u201314 (2024).","journal-title":"Npj Digit Med"},{"key":"224_CR38","doi-asserted-by":"publisher","first-page":"e012012","DOI":"10.1136\/bmjopen-2016-012012","volume":"7","author":"RG Jackson","year":"2017","unstructured":"Jackson, R. G. et al. Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) project. BMJ Open 7, e012012 (2017).","journal-title":"BMJ Open"},{"key":"224_CR39","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Zhao, Y., Shumailov, I., Mullins, R. & Gal, Y. Revisiting Automated Prompting: Are We Actually Doing Better? published online June 22. https:\/\/doi.org\/10.48550\/arXiv.2304.03609 (2023).","DOI":"10.48550\/arXiv.2304.03609"},{"key":"224_CR40","doi-asserted-by":"publisher","unstructured":"Yang, C. et al. Large Language Models as Optimizers. published online April 15. https:\/\/doi.org\/10.48550\/arXiv.2309.03409 (2024).","DOI":"10.48550\/arXiv.2309.03409"},{"key":"224_CR41","doi-asserted-by":"publisher","unstructured":"Chen, B., Zhang, Z., Langren\u00e9, N. & Zhu, S. Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review. published online Oct 27. https:\/\/doi.org\/10.48550\/arXiv.2310.14735 (2023).","DOI":"10.48550\/arXiv.2310.14735"},{"key":"224_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Zhang, A., Li, M. & Smola, A. Automatic Chain of Thought Prompting in Large Language Models. published online Oct 7. https:\/\/doi.org\/10.48550\/arXiv.2210.03493 (2022).","DOI":"10.48550\/arXiv.2210.03493"},{"key":"224_CR43","doi-asserted-by":"publisher","unstructured":"Yao, Z., Jaafar, A., Wang, B., Yang, Z. & Yu, H. Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation. published online July 5. https:\/\/doi.org\/10.48550\/arXiv.2311.09684 (2024).","DOI":"10.48550\/arXiv.2311.09684"},{"key":"224_CR44","doi-asserted-by":"crossref","unstructured":"Liu, X. et al. P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks. in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (Muresan S., Nakov P., Villavicencio A., eds.) 61\u201368 (Dublin, Ireland: Association for Computational Linguistics, 2022).","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"224_CR45","doi-asserted-by":"publisher","unstructured":"Wu, S., Koo, M., Scalzo, F. & Kurtz, I. AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradients. published online Feb 21. https:\/\/doi.org\/10.48550\/arXiv.2502.15944 (2025).","DOI":"10.48550\/arXiv.2502.15944"},{"key":"224_CR46","doi-asserted-by":"crossref","unstructured":"Fesl, S., Lang, C., Verhees, F. G., Schmitt, J. & Scheibe, M. Perspectives on Health Data Sharing Among Patients With Somatic and Mental Health Diseases: Focus Group Study. J. Med. Internet Res. 28, e79990 (2026).","DOI":"10.2196\/79990"},{"key":"224_CR47","doi-asserted-by":"publisher","first-page":"e12","DOI":"10.1016\/S2589-7500(23)00225-X","volume":"6","author":"T Zack","year":"2024","unstructured":"Zack, T. et al. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. Lancet Digit Health 6, e12\u2013e22 (2024).","journal-title":"Lancet Digit Health"},{"key":"224_CR48","doi-asserted-by":"crossref","unstructured":"Duffourc, M. N., Verhees, F. G. & Gilbert, S. Artificial intelligence characters are dangerous without legal guardrails. Nat. HumBehav. 10, 218\u2013221 (2026).","DOI":"10.1038\/s41562-025-02375-3"},{"key":"224_CR49","doi-asserted-by":"publisher","unstructured":"Dohn\u00e1ny, S. et al. Technological folie \u00e0 deux: Feedback Loops Between AI Chatbots and Mental Illness. published online July 28. https:\/\/doi.org\/10.48550\/arXiv.2507.19218 (2025).","DOI":"10.48550\/arXiv.2507.19218"}],"container-title":["npj Mental Health Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44184-026-00224-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44184-026-00224-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44184-026-00224-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T18:59:21Z","timestamp":1782413961000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44184-026-00224-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["224"],"URL":"https:\/\/doi.org\/10.1038\/s44184-026-00224-3","relation":{},"ISSN":["2731-4251"],"issn-type":[{"value":"2731-4251","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"25 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.N.K. declares consulting services for Owkin, France, DoMore Diagnostics, Norway, Panakeia, UK, Scailyte, Switzerland, Cancilico, Germany, Mindpeak, Germany, MultiplexDx, Slovakia, and Histofy, UK; furthermore he holds shares in StratifAI GmbH, Germany, has received a research grant by GSK, and has received honoraria by AstraZeneca, Bayer, Eisai, Janssen, MSD, BMS, Roche, Pfizer and Fresenius. ICW received honoraria from AstraZeneca. M.B. has served as an advisor to Alfred E. Tiefenbacher GmbH Co. KG, COMPASS Pathfinder Ltd., GH Research, MedEd-Link Inc., Janssen Global Services, LLC, Livanova, Mindforce Game Lab AB, and Novartis. He has received lecture fees from MedTrix GmbH and Streamedup GmbH. He has received honoraria for editor-in-chief positions by Thieme Verlag and Springer Nature. The other authors do not have a competing interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Artificial intelligence in the form of large language models (ChatGPT plus, o3 and others; local instances of Llama, 3.1_instruct and others) have been used to supplement the systematic literature research that this work is based on. Analytic code and feedback on the analysis plan was supported by AI, as was proof-reading for more clarity and brevity. All output was scrutinized by the authors and used only if deemed accurate.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"AI Use Statement"}}],"article-number":"30"}}