{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T01:19:46Z","timestamp":1793582386274,"version":"4.5.0"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-026-74501-2","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:03:18Z","timestamp":1783414998000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Empowering clinical trial design with agentic intelligence and real-world data"],"prefix":"10.1038","volume":"17","author":[{"given":"Haoyang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weishen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8149-0157","authenticated-orcid":false,"given":"Suraj","family":"Rajendran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8244-9551","authenticated-orcid":false,"given":"Chengxi","family":"Zang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-9461","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"74501_CR1","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1093\/aje\/kwv254","volume":"183","author":"MA Hern\u00e1n","year":"2016","unstructured":"Hern\u00e1n, M. A. & Robins, J. M. Using big data to emulate a target trial when a randomized trial is not available. Am. J. Epidemiol. 183, 758\u2013764 (2016).","journal-title":"Am. J. Epidemiol."},{"key":"74501_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32310-3","volume":"13","author":"SV Wang","year":"2022","unstructured":"Wang, S. V., Sreedhara, S. K. & Schneeweiss, S. Reproducibility of real-world evidence studies using clinical practice data to inform regulatory and coverage decisions. Nat. Commun. 13, 5126 (2022).","journal-title":"Nat. Commun."},{"key":"74501_CR3","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1080\/00273171.2011.568786","volume":"46","author":"PC Austin","year":"2011","unstructured":"Austin, P. C. An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivar. Behav. Res. 46, 399\u2013424 (2011).","journal-title":"Multivar. Behav. Res."},{"key":"74501_CR4","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1038\/s41591-024-03352-5","volume":"31","author":"X Orcutt","year":"2025","unstructured":"Orcutt, X., Chen, K., Mamtani, R., Long, Q. & Parikh, R. B. Evaluating generalizability of oncology trial results to real-world patients using machine learning-based trial emulations. Nat. Med. 31, 457\u2013465 (2025).","journal-title":"Nat. Med."},{"key":"74501_CR5","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1038\/s41591-024-02902-1","volume":"30","author":"S Feuerriegel","year":"2024","unstructured":"Feuerriegel, S. et al. Causal machine learning for predicting treatment outcomes. Nat. Med. 30, 958\u2013968 (2024).","journal-title":"Nat. Med."},{"key":"74501_CR6","doi-asserted-by":"publisher","first-page":"2446","DOI":"10.1001\/jama.2022.21383","volume":"328","author":"MA Hern\u00e1n","year":"2022","unstructured":"Hern\u00e1n, M. A., Wang, W. & Leaf, D. E. Target trial emulation: a framework for causal inference from observational data. JAMA 328, 2446\u20132447 (2022).","journal-title":"JAMA"},{"key":"74501_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43929-1","volume":"14","author":"C Zang","year":"2023","unstructured":"Zang, C. et al. High-throughput target trial emulation for Alzheimer\u2019s disease drug repurposing with real-world data. Nat. Commun. 14, 8180 (2023).","journal-title":"Nat. Commun."},{"key":"74501_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-59643-z","volume":"16","author":"S Rajendran","year":"2025","unstructured":"Rajendran, S. et al. Multicenter target trial emulation to evaluate corticosteroids for sepsis stratified by predicted organ dysfunction trajectory. Nat. Commun. 16, 4450 (2025).","journal-title":"Nat. Commun."},{"key":"74501_CR9","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1038\/s41746-025-01803-y","volume":"8","author":"H Li","year":"2025","unstructured":"Li, H. et al. Federated target trial emulation using distributed observational data for treatment effect estimation. Npj Digit. Med. 8, 387 (2025).","journal-title":"Npj Digit. Med."},{"key":"74501_CR10","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1016\/S2352-4642(25)00131-2","volume":"9","author":"CH Robinson","year":"2025","unstructured":"Robinson, C. H., Fan, E., Grandi, S. M., Urner, M. & Parekh, R. S. Target trial emulation in paediatric research: how can causal effects be estimated from observational data?. Lancet Child Adolesc. Health 9, 663\u2013672 (2025).","journal-title":"Lancet Child Adolesc. Health"},{"key":"74501_CR11","unstructured":"Data Standardization \u2013 OHDSI. https:\/\/www.ohdsi.org\/data-standardization\/"},{"key":"74501_CR12","doi-asserted-by":"publisher","first-page":"104335","DOI":"10.1016\/j.jbi.2023.104335","volume":"140","author":"T He","year":"2023","unstructured":"He, T. et al. Trends and opportunities in computable clinical phenotyping: A scoping review. J. Biomed. Inform. 140, 104335 (2023).","journal-title":"J. Biomed. Inform."},{"key":"74501_CR13","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1038\/s41586-021-03430-5","volume":"592","author":"R Liu","year":"2021","unstructured":"Liu, R. et al. Evaluating eligibility criteria of oncology trials using real-world data and AI. Nature 592, 629\u2013633 (2021).","journal-title":"Nature"},{"key":"74501_CR14","doi-asserted-by":"publisher","unstructured":"Rajendran, S. et al. Corticosteroids for infectious critical illness: a multicenter target trial emulation stratified by predicted organ dysfunction trajectory. MedRxiv Prepr. Serv. Health Sci. 2024.03.07.24303926 https:\/\/doi.org\/10.1101\/2024.03.07.24303926 (2024).","DOI":"10.1101\/2024.03.07.24303926"},{"key":"74501_CR15","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s44336-024-00009-2","volume":"1","author":"X Li","year":"2024","unstructured":"Li, X., Wang, S., Zeng, S., Wu, Y. & Yang, Y. A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1, 9 (2024).","journal-title":"Vicinagearth"},{"key":"74501_CR16","doi-asserted-by":"crossref","unstructured":"Swanson, K., Wu, W., Bulaong, N. L., Pak, J. E. & Zou, J. The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies. Nature 646, 716\u2013723 (2025).","DOI":"10.1038\/s41586-025-09442-9"},{"key":"74501_CR17","doi-asserted-by":"publisher","unstructured":"Li, J. et al. Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2405.02957 (2025).","DOI":"10.48550\/arXiv.2405.02957"},{"key":"74501_CR18","doi-asserted-by":"publisher","unstructured":"Yue, L., Xing, S., Chen, J. & Fu, T. ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning. In Proc. 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 1\u201310 (Association for Computing Machinery, New York, NY, USA, 2024). https:\/\/doi.org\/10.1145\/3698587.3701359.","DOI":"10.1145\/3698587.3701359"},{"key":"74501_CR19","unstructured":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making. https:\/\/arxiv.org\/abs\/2404.15155."},{"key":"74501_CR20","doi-asserted-by":"crossref","unstructured":"Shi, W. et al. EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records. In Proc. 2024 Conference on Empirical Methods in Natural Language Processing, Vol. 2024, 22315\u201322339 (ACL, 2024).","DOI":"10.18653\/v1\/2024.emnlp-main.1245"},{"key":"74501_CR21","unstructured":"Cui, H. et al. LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction. AMIA. Annu. Symp. Proc. 2024, 319\u2013328 (2025)."},{"key":"74501_CR22","unstructured":"Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models. https:\/\/arxiv.org\/abs\/2401.02851."},{"key":"74501_CR23","unstructured":"Kaufmann, T., Weng, P., Bengs, V. & H\u00fcllermeier, E. A Survey of Reinforcement Learning from Human Feedback. arXiv.org https:\/\/arxiv.org\/abs\/2312.14925v2 (2023)."},{"key":"74501_CR24","doi-asserted-by":"crossref","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","DOI":"10.1038\/s41597-022-01899-x"},{"key":"74501_CR25","unstructured":"INSIGHT Clinical Research Network. INSIGHT Clinical Research Network https:\/\/insightcrn.org\/."},{"key":"74501_CR26","unstructured":"Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"74501_CR27","doi-asserted-by":"publisher","unstructured":"Abdin, M. et al. Phi-4 Technical Report. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2412.08905 (2024).","DOI":"10.48550\/arXiv.2412.08905"},{"key":"74501_CR28","doi-asserted-by":"crossref","unstructured":"Guo, D. et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645, 633\u2013638 (2025).","DOI":"10.1038\/s41586-025-09422-z"},{"key":"74501_CR29","unstructured":"Introducing Gemma 3: The most capable model you can run on a single GPU or TPU. Google https:\/\/blog.google\/technology\/developers\/gemma-3\/ (2025)."},{"key":"74501_CR30","doi-asserted-by":"publisher","first-page":"1964","DOI":"10.1093\/jamia\/ocab078","volume":"28","author":"J Du","year":"2021","unstructured":"Du, J. et al. COVID-19 trial graph: a linked graph for COVID-19 clinical trials. J. Am. Med. Inform. Assoc. JAMIA 28, 1964\u20131969 (2021).","journal-title":"J. Am. Med. Inform. Assoc. JAMIA"},{"key":"74501_CR31","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh, M. L. Interrater reliability: the kappa statistic. Biochem. Med. 22, 276\u2013282 (2012).","journal-title":"Biochem. Med."},{"key":"74501_CR32","doi-asserted-by":"publisher","first-page":"104649","DOI":"10.1016\/j.jbi.2024.104649","volume":"154","author":"J Park","year":"2024","unstructured":"Park, J. et al. Criteria2Query 3.0: Leveraging generative large language models for clinical trial eligibility query generation. J. Biomed. Inform. 154, 104649 (2024).","journal-title":"J. Biomed. Inform."},{"key":"74501_CR33","first-page":"46","volume":"2010","author":"J Ross","year":"2010","unstructured":"Ross, J., Tu, S., Carini, S. & Sim, I. Analysis of eligibility criteria complexity in clinical trials. Summit Transl. Bioinforma. 2010, 46\u201350 (2010).","journal-title":"Summit Transl. Bioinforma."},{"key":"74501_CR34","first-page":"87","volume":"30","author":"J Hauke","year":"2011","unstructured":"Hauke, J. & Kossowski, T. Comparison of values of Pearson\u2019s and Spearman\u2019s correlation coefficients on the same sets of data. Quaest. Geogr. 30, 87\u201393 (2011).","journal-title":"Quaest. Geogr."},{"key":"74501_CR35","doi-asserted-by":"publisher","first-page":"20f13681","DOI":"10.4088\/JCP.20f13681","volume":"81","author":"C Andrade","year":"2020","unstructured":"Andrade, C. Mean difference, standardized mean difference (SMD), and their use in meta-analysis: as simple as it gets. J. Clin. Psychiatry 81, 20f13681 (2020).","journal-title":"J. Clin. Psychiatry"},{"key":"74501_CR36","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1097\/CCM.0b013e31819def97","volume":"37","author":"AE Jones","year":"2009","unstructured":"Jones, A. E., Trzeciak, S. & Kline, J. A. The Sequential Organ Failure Assessment score for predicting outcome in patients with severe sepsis and evidence of hypoperfusion at the time of emergency department presentation*. Crit. Care Med. 37, 1649 (2009).","journal-title":"Crit. Care Med."},{"key":"74501_CR37","first-page":"55","volume":"22","author":"R Likert","year":"1932","unstructured":"Likert, R. A technique for the measurement of attitudes. Arch. Psychol. 22, 55\u201355 (1932).","journal-title":"Arch. Psychol."},{"key":"74501_CR38","first-page":"1","volume":"43","author":"L Huang","year":"2025","unstructured":"Huang, L. et al. A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. 43, 1\u201355 (2025).","journal-title":"ACM Trans. Inf. Syst."},{"key":"74501_CR39","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1001\/jama.2024.28047","volume":"333","author":"O Unlu","year":"2025","unstructured":"Unlu, O. et al. Manual vs AI-assisted prescreening for trial eligibility using large language models\u2014a randomized clinical trial. JAMA 333, 1084\u20131087 (2025).","journal-title":"JAMA"},{"key":"74501_CR40","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02177-7","volume":"24","author":"LR Kalankesh","year":"2024","unstructured":"Kalankesh, L. R. & Monaghesh, E. Utilization of EHRs for clinical trials: a systematic review. BMC Med. Res. Methodol. 24, 70 (2024).","journal-title":"BMC Med. Res. Methodol."},{"key":"74501_CR41","doi-asserted-by":"crossref","unstructured":"Wornow, M. et al. Zero-Shot Clinical Trial Patient Matching with LLMs. NEJM AI 2, AIcs2400360 (2025).","DOI":"10.1056\/AIcs2400360"},{"key":"74501_CR42","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1097\/PEC.0000000000001592","volume":"35","author":"JW Dexheimer","year":"2019","unstructured":"Dexheimer, J. W. et al. A time-and-motion study of clinical trial eligibility screening in a pediatric emergency department. Pediatr. Emerg. Care 35, 868\u2013873 (2019).","journal-title":"Pediatr. Emerg. Care"},{"key":"74501_CR43","doi-asserted-by":"publisher","unstructured":"Liu, F., Wang, H., Cho, J., Roth, D. & Lo, A. W. AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents. In Proc. 2025 Conference on Empirical Methods in Natural Language Processing (eds Christodoulopoulos, C., Chakraborty, T., Rose, C. & Peng, V.) 30945\u201330970 (Association for Computational Linguistics, Suzhou, China, 2025). https:\/\/doi.org\/10.18653\/v1\/2025.emnlp-main.1575.","DOI":"10.18653\/v1\/2025.emnlp-main.1575"},{"key":"74501_CR44","doi-asserted-by":"publisher","first-page":"e70188","DOI":"10.1111\/cts.70188","volume":"18","author":"MH Shahin","year":"2025","unstructured":"Shahin, M. H., Goswami, S., Lobentanzer, S. & Corrigan, B. W. Agents for change: artificial intelligent workflows for quantitative clinical pharmacology and translational sciences. Clin. Transl. Sci. 18, e70188 (2025).","journal-title":"Clin. Transl. Sci."},{"key":"74501_CR45","first-page":"641","volume":"290","author":"J Kim","year":"2022","unstructured":"Kim, J. & Quintana, Y. Review of the performance metrics for natural language systems for clinical trials matching. Stud. Health Technol. Inform. 290, 641\u2013644 (2022).","journal-title":"Stud. Health Technol. Inform."},{"key":"74501_CR46","doi-asserted-by":"publisher","first-page":"104139","DOI":"10.1016\/j.drudis.2024.104139","volume":"29","author":"K Kantor","year":"2024","unstructured":"Kantor, K. & Morzy, M. Machine learning and natural language processing in clinical trial eligibility criteria parsing: a scoping review. Drug Discov. Today 29, 104139 (2024).","journal-title":"Drug Discov. Today"},{"key":"74501_CR47","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00620-0","volume":"7","author":"F Kury","year":"2020","unstructured":"Kury, F. et al. Chia, a large annotated corpus of clinical trial eligibility criteria. Sci. Data 7, 281 (2020).","journal-title":"Sci. Data"},{"key":"74501_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2023.106460","volume":"26","author":"C Su","year":"2023","unstructured":"Su, C. et al. Biomedical discovery through the integrative biomedical knowledge hub (iBKH). iScience 26, 106460 (2023).","journal-title":"iScience"},{"key":"74501_CR49","first-page":"173","volume":"2015","author":"CL Crowe","year":"2015","unstructured":"Crowe, C. L. & Tao, C. Designing ontology-based patterns for the representation of the time-relevant eligibility criteria of clinical protocols. AMIA Summits Transl. Sci. Proc. 2015, 173\u2013177 (2015).","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"74501_CR50","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1093\/jamia\/ocaa058","volume":"27","author":"F Li","year":"2020","unstructured":"Li, F. et al. Time event ontology (TEO): to support semantic representation and reasoning of complex temporal relations of clinical events. J. Am. Med. Inform. Assoc. JAMIA 27, 1046\u20131056 (2020).","journal-title":"J. Am. Med. Inform. Assoc. JAMIA"},{"key":"74501_CR51","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","volume":"32","author":"O Bodenreider","year":"2004","unstructured":"Bodenreider, O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32, D267\u2013D270 (2004).","journal-title":"Nucleic Acids Res."},{"key":"74501_CR52","unstructured":"OHDSI \u2013 Observational Health Data Sciences and Informatics. https:\/\/www.ohdsi.org\/."},{"key":"74501_CR53","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1109\/JBHI.2013.2292591","volume":"18","author":"DR Harris","year":"2014","unstructured":"Harris, D. R., Henderson, D. W., Kavuluru, R., Stromberg, A. J. & Johnson, T. R. Using common table expressions to build a scalable Boolean query generator for clinical data warehouses. IEEE J. Biomed. Health Inform. 18, 1607\u20131613 (2014).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"74501_CR54","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1145\/319732.319745","volume":"7","author":"W Kim","year":"1982","unstructured":"Kim, W. On optimizing an SQL-like nested query. ACM Trans. Database Syst. 7, 443\u2013469 (1982).","journal-title":"ACM Trans. Database Syst."},{"key":"74501_CR55","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1093\/jamia\/ocad218","volume":"31","author":"S Datta","year":"2023","unstructured":"Datta, S. et al. AutoCriteria: a generalizable clinical trial eligibility criteria extraction system powered by large language models. J. Am. Med. Inform. Assoc. JAMIA 31, 375\u2013385 (2023).","journal-title":"J. Am. Med. Inform. Assoc. JAMIA"},{"key":"74501_CR56","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.jbi.2009.12.004","volume":"43","author":"C Weng","year":"2010","unstructured":"Weng, C., Tu, S. W., Sim, I. & Richesson, R. Formal representation of eligibility criteria: a literature review. J. Biomed. Inform. 43, 451\u2013467 (2010).","journal-title":"J. Biomed. Inform."},{"key":"74501_CR57","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1038\/nrg3208","volume":"13","author":"PB Jensen","year":"2012","unstructured":"Jensen, P. B., Jensen, L. J. & Brunak, S. Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13, 395\u2013405 (2012).","journal-title":"Nat. Rev. Genet."},{"key":"74501_CR58","unstructured":"Meystre, S. M., Savova, G. K., Kipper-Schuler, K. C. & Hurdle, J. F. Extracting information from textual documents in the electronic health record: a review of recent research. Yearb. Med. Inform. 17, 128\u2013144 (2008)."},{"key":"74501_CR59","doi-asserted-by":"publisher","first-page":"474","DOI":"10.26421\/JDI3.4-5","volume":"3","author":"P Deka","year":"2022","unstructured":"Deka, P., Jurek-Loughrey, A. & Padmanabhan, D. Improved methods to aid unsupervised evidence-based fact checking for online health news. J. Data Intell. 3, 474\u2013505 (2022).","journal-title":"J. Data Intell."},{"key":"74501_CR60","first-page":"1080","volume":"2017","author":"K Lee","year":"2018","unstructured":"Lee, K., Weiskopf, N. & Pathak, J. A framework for data quality assessment in clinical research datasets. Amia. Annu. Symp. Proc. 2017, 1080\u20131089 (2018).","journal-title":"Amia. Annu. Symp. Proc."},{"key":"74501_CR61","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-021-01252-7","volume":"21","author":"CO Schmidt","year":"2021","unstructured":"Schmidt, C. O. et al. Facilitating harmonized data quality assessments. A data quality framework for observational health research data collections with software implementations in R. BMC Med. Res. Methodol. 21, 63 (2021).","journal-title":"BMC Med. Res. Methodol."},{"key":"74501_CR62","doi-asserted-by":"publisher","DOI":"10.2196\/41446","volume":"25","author":"FA Bernardi","year":"2023","unstructured":"Bernardi, F. A. et al. Data quality in health research: integrative literature review. J. Med. Internet Res. 25, e41446 (2023).","journal-title":"J. Med. Internet Res."},{"key":"74501_CR63","doi-asserted-by":"publisher","first-page":"9","DOI":"10.18590\/mjm.2018.vol4.iss2.9","volume":"4","author":"TW Gress","year":"2018","unstructured":"Gress, T. W., Denvir, J. & Shapiro, J. I. Effect of removing outliers on statistical inference: implications to interpretation of experimental data in medical research. Marshal. J. Med. 4, 9 (2018).","journal-title":"Marshal. J. Med."},{"key":"74501_CR64","doi-asserted-by":"publisher","first-page":"104440","DOI":"10.1016\/j.jbi.2023.104440","volume":"144","author":"M Kazijevs","year":"2023","unstructured":"Kazijevs, M. & Samad, M. D. Deep imputation of missing values in time series health data: a review with benchmarking. J. Biomed. Inform. 144, 104440 (2023).","journal-title":"J. Biomed. Inform."},{"key":"74501_CR65","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1097\/BSD.0000000000000932","volume":"33","author":"LT Kane","year":"2020","unstructured":"Kane, L. T. et al. Propensity score matching: a statistical method. Clin. Spine Surg. 33, 120\u2013122 (2020).","journal-title":"Clin. Spine Surg."},{"key":"74501_CR66","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1111\/j.1467-6419.2007.00527.x","volume":"22","author":"M Caliendo","year":"2008","unstructured":"Caliendo, M. & Kopeinig, S. Some practical guidance for the implementation of propensity score matching. J. Econ. Surv. 22, 31\u201372 (2008).","journal-title":"J. Econ. Surv."},{"key":"74501_CR67","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","volume":"70","author":"PR ROSENBAUM","year":"1983","unstructured":"ROSENBAUM, P. R. & RUBIN, D. B. The central role of the propensity score in observational studies for causal effects. Biometrika 70, 41\u201355 (1983).","journal-title":"Biometrika"},{"key":"74501_CR68","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1093\/ckj\/sfab158","volume":"15","author":"NC Chesnaye","year":"2022","unstructured":"Chesnaye, N. C. et al. An introduction to inverse probability of treatment weighting in observational research. Clin. Kidney J. 15, 14\u201320 (2022).","journal-title":"Clin. Kidney J."},{"key":"74501_CR69","doi-asserted-by":"publisher","first-page":"111338","DOI":"10.1016\/j.jclinepi.2024.111338","volume":"170","author":"F Bettega","year":"2024","unstructured":"Bettega, F., Mendelson, M., Leyrat, C. & Bailly, S. Use and reporting of inverse-probability-of-treatment weighting for multicategory treatments in medical research: a systematic review. J. Clin. Epidemiol. 170, 111338 (2024).","journal-title":"J. Clin. Epidemiol."},{"key":"74501_CR70","doi-asserted-by":"publisher","first-page":"5642","DOI":"10.1002\/sim.7084","volume":"35","author":"PC Austin","year":"2016","unstructured":"Austin, P. C. Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis. Stat. Med. 35, 5642\u20135655 (2016).","journal-title":"Stat. Med."},{"key":"74501_CR71","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.jclinepi.2016.04.014","volume":"79","author":"MA Hern\u00e1n","year":"2016","unstructured":"Hern\u00e1n, M. A., Sauer, B. C., Hern\u00e1ndez-D\u00edaz, S., Platt, R. & Shrier, I. Specifying a target trial prevents immortal time bias and other self-inflicted injuries in observational analyses. J. Clin. Epidemiol. 79, 70\u201375 (2016).","journal-title":"J. Clin. Epidemiol."},{"key":"74501_CR72","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1093\/aje\/kwv445","volume":"184","author":"ME Karim","year":"2016","unstructured":"Karim, M. E., Gustafson, P., Petkau, J. & Tremlett, H. Comparison of statistical approaches for dealing with immortal time bias in drug effectiveness studies. Am. J. Epidemiol. 184, 325\u2013335 (2016).","journal-title":"Am. J. Epidemiol."},{"key":"74501_CR73","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/0951-8320(94)90010-8","volume":"44","author":"D Kumar","year":"1994","unstructured":"Kumar, D. & Klefsj\u00f6, B. Proportional hazards model: a review. Reliab. Eng. Syst. Saf. 44, 177\u2013188 (1994).","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"74501_CR74","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1002\/sim.1203","volume":"21","author":"P Royston","year":"2002","unstructured":"Royston, P. & Parmar, M. K. B. Flexible parametric proportional-hazards and proportional-odds models for censored survival data, with application to prognostic modelling and estimation of treatment effects. Stat. Med. 21, 2175\u20132197 (2002).","journal-title":"Stat. Med."},{"key":"74501_CR75","doi-asserted-by":"publisher","first-page":"105","DOI":"10.7326\/M22-0844","volume":"176","author":"DJ McLernon","year":"2023","unstructured":"McLernon, D. J. et al. Assessing performance and clinical usefulness in prediction models with survival outcomes: practical guidance for Cox proportional hazards models. Ann. Intern. Med. 176, 105\u2013114 (2023).","journal-title":"Ann. Intern. Med."},{"key":"74501_CR76","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/j.otohns.2010.05.007","volume":"143","author":"JT RICH","year":"2010","unstructured":"RICH, J. T. et al. A practical guide to understanding Kaplan\u2013Meier curves. Otolaryngol. Head. Neck Surg. 143, 331\u2013336 (2010).","journal-title":"Otolaryngol. Head. Neck Surg."},{"key":"74501_CR77","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-021-01375-x","volume":"21","author":"KL Pickett","year":"2021","unstructured":"Pickett, K. L., Suresh, K., Campbell, K. R., Davis, S. & Juarez-Colunga, E. Random survival forests for dynamic predictions of a time-to-event outcome using a longitudinal biomarker. BMC Med. Res. Methodol. 21, 216 (2021).","journal-title":"BMC Med. Res. Methodol."},{"key":"74501_CR78","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1093\/aje\/kwq439","volume":"173","author":"MJ Funk","year":"2011","unstructured":"Funk, M. J. et al. Doubly robust estimation of causal effects. Am. J. Epidemiol. 173, 761\u2013767 (2011).","journal-title":"Am. J. Epidemiol."},{"key":"74501_CR79","doi-asserted-by":"publisher","unstructured":"Gao, Y. et al. Retrieval-Augmented Generation for Large Language Models: A Survey. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2312.10997 (2024).","DOI":"10.48550\/arXiv.2312.10997"},{"key":"74501_CR80","doi-asserted-by":"crossref","unstructured":"Douze, M. et al. The Faiss library. IEEE Trans. Big Data 12, 346\u2013361 (2026).","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"74501_CR81","doi-asserted-by":"publisher","unstructured":"Bai, Y. et al. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2204.05862 (2022).","DOI":"10.48550\/arXiv.2204.05862"},{"key":"74501_CR82","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal Policy Optim. Algorithms. https:\/\/doi.org\/10.48550\/arXiv.1707.06347 (2017).","DOI":"10.48550\/arXiv.1707.06347"},{"key":"74501_CR83","doi-asserted-by":"publisher","unstructured":"Rafailov, R. et al. Direct preference optimization: your language model is secretly a reward model. Adv. Neural Inform. Process. Syst. https:\/\/doi.org\/10.48550\/arXiv.2305.18290 (2024).","DOI":"10.48550\/arXiv.2305.18290"},{"key":"74501_CR84","doi-asserted-by":"publisher","unstructured":"Li, H., Pan, W. & Rajendran, S. TrialLab\/EmulatRx: Public Code for EmulatRx: Empowering Clinical Trial Design with Agentic Intelligence and Real World Data. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.20016649 (2026).","DOI":"10.5281\/zenodo.20016649"},{"key":"74501_CR85","doi-asserted-by":"publisher","unstructured":"McKight, P. E. & Najab, J. Kruskal-Wallis Test. In The Corsini Encyclopedia of Psychology 1\u20131 (John Wiley & Sons, Ltd, 2010). https:\/\/doi.org\/10.1002\/9780470479216.corpsy0491.","DOI":"10.1002\/9780470479216.corpsy0491"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74501-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74501-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74501-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:03:57Z","timestamp":1783415037000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74501-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":85,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["74501"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-74501-2","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"assertion":[{"value":"24 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5501"}}