{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T20:55:11Z","timestamp":1790974511046,"version":"4.1.0"},"reference-count":10,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In a diagnostic study of 104 western blot and subcutaneous xenograft tumor images, a high-fidelity generative model produced forgeries that could alter the conclusions of a study; 24 PhD-level expert reviewers could not reliably distinguish the forgeries from authentic figures (mean accuracy 50.5%, SD 6.9%), while the best-performing commercial AI detector achieved only moderate discrimination (area under the curve 0.790, 95% CI 0.695-0.885), revealing critical vulnerabilities in current research-integrity safeguards.<\/jats:p>","DOI":"10.2196\/100710","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T13:40:05Z","timestamp":1788788405000},"page":"e100710-e100710","source":"Crossref","is-referenced-by-count":0,"title":["Biomedical Research Images Manipulated by Generative AI to Alter Scientific Outcomes: Diagnostic Study of Human and Automated Detection"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9992-0530","authenticated-orcid":false,"given":"Shuhang","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0398-7469","authenticated-orcid":false,"given":"Runhua","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4588-4076","authenticated-orcid":false,"given":"Ziyin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4667-9365","authenticated-orcid":false,"given":"Jianye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4770-4449","authenticated-orcid":false,"given":"Ming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7786-2716","authenticated-orcid":false,"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5665-384X","authenticated-orcid":false,"given":"Li","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.70200","article-title":"Advancing medical research through artificial intelligence: progressive and transformative strategies: a literature review","volume":"8","author":"Al-Qudimat","journal-title":"Health Sci Rep"},{"issue":"8","key":"R2","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1001\/jama.2023.1344","article-title":"Nonhuman \u201cauthors\u201d and implications for the integrity of scientific publication and medical knowledge","volume":"329","author":"Flanagin","journal-title":"JAMA"},{"issue":"7964","key":"R3","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1038\/d41586-023-01780-w","article-title":"AI intensifies fight against \u201cpaper mills\u201d that churn out fake research","volume":"618","author":"Liverpool","journal-title":"Nature"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"401","DOI":"10.4103\/sja.sja_344_23","article-title":"Artificial intelligence in medicine and research - the good, the bad, and the ugly","volume":"17","author":"Grech","journal-title":"Saudi J Anaesth"},{"issue":"27","key":"R5","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000038811","article-title":"Research integrity in the era of artificial intelligence: challenges and responses","volume":"103","author":"Chen","journal-title":"Medicine (Baltimore)"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1644098","article-title":"AI for scientific integrity: detecting ethical breaches, errors, and misconduct in manuscripts","volume":"8","author":"Pellegrina","journal-title":"Front Artif Intell"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.18988","article-title":"AI detectors are poor western blot classifiers: a study of accuracy and predictive values","volume":"13","author":"Gosselin","journal-title":"PeerJ"},{"key":"R8","doi-asserted-by":"crossref","unstructured":"Chen D . AI-generated figures in academic publishing: policies, tools, and practical guidelines. arXiv. Preprint posted online on 2026. [doi: 10.22541\/au.177499033.31149950\/v1]","DOI":"10.22541\/au.177499033.31149950\/v1"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-28572-8","article-title":"Detection of AI generated images using combined uncertainty measures and particle swarm optimised rejection mechanism","volume":"15","author":"Yumlembam","journal-title":"Sci Rep"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1007\/s00701-025-06622-4","article-title":"Can we trust academic AI detective? Accuracy and limitations of AI-output detectors","volume":"167","author":"Erol","journal-title":"Acta Neurochir (Wien)"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T20:44:03Z","timestamp":1790973843000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e100710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":10,"URL":"https:\/\/doi.org\/10.2196\/100710","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]},"article-number":"v28i2e100710"}}