{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T00:10:59Z","timestamp":1791591059554,"version":"4.3.4"},"reference-count":21,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Clin. Med.","JCM"],"abstract":"<jats:p>Background\/Objectives: Postoperative free flap monitoring relies on clinical assessment of colour, turgor, and capillary refill time (CRT). The high frequency of required assessments renders this process labour-intensive and inherently subjective, with sensitivity dependent on observer experience and fatigue. This study evaluated the feasibility of a large multimodal AI (Artificial Intelligence) model (Gemini 3 Flash, Google AI Studio) applied without any task-specific training or fine-tuning, with each video analysed in an independent session, to establish whether meaningful diagnostic agreement is achievable before any domain-specific training is introduced, with the ultimate goal of supporting the development of a machine-based secondary safety net that augments, rather than replaces, the primary clinical assessment of the responsible surgeon in postoperative free flap surveillance. Methods: One hundred and forty-three postoperative video recordings from 143 different patients who underwent fasciocutaneous free flap reconstruction for extraoral defects were analysed. The cohort was deliberately enriched for pathological cases to ensure adequate representation of each vascular compromise category. Assessment was based on intrapatient comparison between flap and adjacent native tissue, without task-specific training or prior clinical information. AI outputs were compared against consensus assessments of three senior plastic surgeons (two associate professors, one full professor) for four parameters: flap colour, turgor, CRT interpretation, and clinical diagnosis. Agreement was evaluated using Cohen\u2019s kappa (\u03ba). Receiver operating characteristic (ROC) analysis assessed the discriminative performance of the AI confidence score. Results: Statistically significant agreement was demonstrated across all four parameters (p &lt; 0.001 for all): flap colour (\u03ba = 0.613, 95% CI: 0.489\u20130.737, 80.4%), turgor (\u03ba = 0.676, 95% CI: 0.558\u20130.794, 83.9%; assessed from visual surrogates rather than direct palpation), CRT interpretation (\u03ba = 0.487, 95% CI: 0.360\u20130.614, 74.1%), and clinical diagnosis (\u03ba = 0.524, 95% CI: 0.399\u20130.649, 74.1%). Normal flaps were correctly identified in 81.0% of cases and venous compromise in 69.4%. ROC analysis identified a confidence score percentile cutoff of 89 as the optimal threshold for discriminating compromised from normal flaps, with scores below 89 indicating a compromised (pathological) result (AUC = 0.667, 95% CI: 0.579\u20130.755; sensitivity 77.0%, specificity 52.4%; overall accuracy 62.9%). Conclusions: A structured-prompted multimodal LLM (Large Language Model) demonstrated statistically significant agreement with the consensus judgement of senior plastic surgeons in postoperative free flap assessment without task-specific training, relying solely on intrapatient visual comparison. These findings constitute a proof-of-concept for AI-based video analysis as a potential adjunctive approach in free flap surveillance, warranting prospective validation with independent clinical outcome data before any claim of clinical utility, with possible broader applicability across clinical domains pending such validation. Key limitations include the absence of independent clinical outcome or confirmation of diagnostic categories, deliberately enriched sampling, a small arterial insufficiency subgroup, and the current absence of a formal data processing agreement for the cloud-based AI platform used.<\/jats:p>","DOI":"10.3390\/jcm15156114","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T08:08:02Z","timestamp":1786003682000},"page":"6114","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Gemini Eye in Microsurgery: Video-Based Capillary Refill and Chromatic Assessment for Free Flap Monitoring"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3201-9610","authenticated-orcid":false,"given":"Ebru","family":"A\u015firet","sequence":"first","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Burak","family":"Ya\u015far","sequence":"additional","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3703-3559","authenticated-orcid":false,"given":"B\u00fc\u015fra Ta\u015f","family":"Efe","sequence":"additional","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7999-8960","authenticated-orcid":false,"given":"S\u00fcleyman Ege","family":"Tozan","sequence":"additional","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0305-7032","authenticated-orcid":false,"given":"Hasan Murat","family":"Ergani","sequence":"additional","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramazan Erkin","family":"\u00dcnl\u00fc","sequence":"additional","affiliation":[{"name":"Department of Plastic, Reconstructive and Aesthetic Surgery, Ankara Bilkent City Hospital, Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1055\/s-0039-1677880","article-title":"Postoperative free-flap monitoring techniques","volume":"33","author":"Kohlert","year":"2019","journal-title":"Semin. Plast. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e2424299","DOI":"10.1001\/jamanetworkopen.2024.24299","article-title":"Development of an automated free flap monitoring system based on artificial intelligence","volume":"7","author":"Kim","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"133","DOI":"10.20517\/ais.2024.89","article-title":"Artificial intelligence applications in free flap microvascular reconstruction: Preoperative planning, intraoperative assessment, and postoperative monitoring","volume":"5","author":"Villavisanis","year":"2025","journal-title":"Art. Int. Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1584","DOI":"10.1097\/JS9.0000000000000626","article-title":"Quantization of extraoral free flap monitoring for venous congestion with deep learning integrated iOS applications on smartphones","volume":"109","author":"Li","year":"2023","journal-title":"Int. J. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1097\/SCS.0000000000011150","article-title":"An Artificial Intelligence Model for Vascularity Monitoring of Postoperative Flap","volume":"36","author":"Lu","year":"2025","journal-title":"J. Craniofac. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106214","DOI":"10.1016\/j.ijsu.2021.106214","article-title":"Breaking the technical barrier of microvascular anastomosis with high-speed videography: A prospective cohort study","volume":"98","author":"Bao","year":"2022","journal-title":"Int. J. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1097\/PRS.0b013e3181c49580","article-title":"Advancements in free flap monitoring in the last decade: A critical review","volume":"125","author":"Smit","year":"2010","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e295","DOI":"10.1097\/PRS.0b013e3181bcf07b","article-title":"Flap monitoring and patient management","volume":"124","author":"Salgado","year":"2009","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4308","DOI":"10.1111\/iwj.14333","article-title":"The application of infrared thermography technology in flap: A perspective from bibliometric and visual analysis","volume":"20","author":"Lu","year":"2023","journal-title":"Int. Wound J."},{"key":"ref_10","first-page":"415","article-title":"Pocket predictors: Are smartphones the future of artificial intelligence in plastic surgery","volume":"31","author":"Watt","year":"2022","journal-title":"Plast. Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2204","DOI":"10.1007\/s00266-024-03932-3","article-title":"Ethics for AI in plastic surgery: Guidelines and review","volume":"48","author":"Kenig","year":"2024","journal-title":"Aesthet. Plast. Surg."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1042\/ETLS20210246","article-title":"Artificial intelligence, machine learning, and deep learning for clinical outcome prediction","volume":"5","author":"Pettit","year":"2021","journal-title":"Emerg. Top. Life Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Shadid, O., Seth, I., Cuomo, R., Rozen, W.M., and Marcaccini, G. (2025). Artificial Intelligence in Microsurgical Planning: A Five-Year Leap in Clinical Translation. J. Clin. Med., 14.","DOI":"10.3390\/jcm14134574"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3466","DOI":"10.1245\/s10434-020-08307-x","article-title":"Development and evaluation of a machine learning prediction model for flap failure in microvascular breast reconstruction","volume":"27","author":"Yang","year":"2020","journal-title":"Ann. Surg. Oncol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2343","DOI":"10.1245\/s10434-022-13053-3","article-title":"The use of machine learning for predicting complications of free-flap head and neck reconstruction","volume":"30","author":"Asaad","year":"2023","journal-title":"Ann. Surg. Oncol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.jpra.2024.07.014","article-title":"Artificial intelligence for optimum tissue excision with indocyanine green fluorescence angiography for flap reconstructions: Proof of concept","volume":"41","author":"Singaravelu","year":"2024","journal-title":"JPRAS Open"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Atkinson, C.J., Seth, I., Xie, Y., Ross, R.J., Hunter-Smith, D.J., Rozen, W.M., and Cuomo, R. (2024). Artificial intelligence language model performance for rapid intraoperative queries in plastic surgery: ChatGPT and the deep inferior epigastric perforator flap. J. Clin. Med., 13.","DOI":"10.3390\/jcm13030900"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1097\/PRS.0b013e318254b1b9","article-title":"The survival curve: Factors impacting the outcome of free flap take-backs","volume":"130","author":"Selber","year":"2012","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bagheri, M., Tietz, K., von Kohout, M., Fuchs, P.C., Lefering, R., and Schiefer, J.L. (2024). Is It Possible to Monitor the Safest Time to Perform Secondary Surgery on Free Flaps? A Clinical Evaluation of the Tewameter\u00ae. Medicina, 60.","DOI":"10.3390\/medicina60081327"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.bjps.2026.01.032","article-title":"Can ChatGPT-4o handle the heat? Benchmarking AI against clinicians in initial burn care: A single-blinded comparative analysis","volume":"116","author":"Lim","year":"2026","journal-title":"J. Plast. Reconstr. Aesthet. Surg."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/15\/6114\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T08:37:37Z","timestamp":1786005457000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/15\/6114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":21,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["jcm15156114"],"URL":"https:\/\/doi.org\/10.3390\/jcm15156114","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,6]]}}}