{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:04:59Z","timestamp":1779807899942,"version":"3.53.1"},"reference-count":23,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"40","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,3]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Follicular thyroid carcinoma (FTC) is the second most common thyroid malignancy but is challenging to preoperatively distinguish from follicular adenoma. Artificial intelligence (AI) has emerged as an auxiliary diagnostic tool, yet published studies show variable performance. This meta-analysis aims to evaluate the overall diagnostic accuracy of AI in differentiating FTC from benign lesions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Literature searches were independently conducted across the PubMed, Embase &amp; Medline (via Embase.com), Web of Science, Cochrane Library, and Ovid English medical databases. The diagnostic accuracy of AI was compared against the reference standard of histopathology. Pooled sensitivity, specificity, diagnostic odds ratio and area under the curve were calculated to assess AI accuracy. Meta-regression analyses were performed to investigate heterogeneity related to test set size, validation strategy, and machine learning model type.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>\n                      We analyzed a total of 7 studies involving 3163 follicular thyroid neoplasms (comprising 1876 follicular thyroid adenomas [FTAs] and 1287 FTCs). The pooled sensitivity and specificity of AI for differentiating FTC from FTA were 0.73 (95% CI: 0.70\u20130.75) and 0.87 (95% CI: 0.86\u20130.89), respectively. The pooled positive and negative likelihood ratios were 6.19 (95% CI: 3.92\u20139.79) and 0.28 (95% CI: 0.17\u20130.46). The diagnostic odds ratio was 22.81 (95% CI: 10.17\u201351.16), and the area under the curve was 0.94. Meta-regression results indicated no significant heterogeneity associated with validation strategy (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2005=\u2005.25). However, test set size (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2005=\u2005.02) and publication year (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2005=\u2005.04) were identified as potential significant sources of heterogeneity. Subgroup analyses revealed that studies with a test set size\u2005&gt;\u20051000 cases demonstrated superior accuracy compared to those with &lt;1000 cases. Regarding validation strategy, studies utilizing cross-validation yielded better performance than those using holdout validation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>Overall, AI demonstrates promising diagnostic utility in differentiating FTC and FTA. Studies employing larger test sets (&gt;1000 cases) achieved higher accuracy than those with smaller test sets (&lt;1000 cases). Furthermore, validation using cross-validation strategies outperformed non-cross-validation (holdout) approaches.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/md.0000000000044745","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T20:06:04Z","timestamp":1759781164000},"page":"e44745","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["The diagnostic value of artificial intelligence in differentiating follicular thyroid cancer from follicular thyroid adenoma: A meta-analysis"],"prefix":"10.1097","volume":"104","author":[{"given":"Di","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Ultrasound, The First Hospital of China Medical University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengfei","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, General Hospital of Fushun Mining Bureau of Liaoning Health Industry Group, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilin","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, The First Hospital of China Medical University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayue","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, The First Hospital of China Medical University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Class 3, Grade 2023, Science High School, Northeast Yucai School, Shenyang, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-3314","authenticated-orcid":false,"given":"Yunfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, The First Hospital of China Medical University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260526","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1089\/thy.2005.15.583","article-title":"Follicular neoplasms of the thyroid: what to recommend.","volume":"15","author":"Carling","year":"2005","journal-title":"Thyroid"},{"key":"R2-20260526","doi-asserted-by":"crossref","first-page":"873","DOI":"10.3892\/ol_00000154","article-title":"Nodal metastasis in well-differentiated follicular carcinoma of the thyroid: Its incidence and clinical significance.","volume":"1","author":"Hirokawa","year":"2010","journal-title":"Oncol Lett"},{"key":"R3-20260526","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1507\/endocrj.EJ12-0454","article-title":"Distant metastasis at diagnosis and large tumor size are significant prognostic factors of widely invasive follicular thyroid carcinoma.","volume":"60","author":"Ito","year":"2013","journal-title":"Endocr J"},{"key":"R4-20260526","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.3390\/jcm9072156","article-title":"Radiomics based on thyroid ultrasound can predict distant metastasis of follicular thyroid carcinoma.","volume":"9","author":"Kwon","year":"2020","journal-title":"J Clin Med"},{"key":"R5-20260526","doi-asserted-by":"crossref","first-page":"687","DOI":"10.2214\/ajr.178.3.1780687","article-title":"New sonographic criteria for recommending fine-needle aspiration biopsy of nonpalpable solid nodules of the thyroid.","volume":"178","author":"Kim","year":"2002","journal-title":"AJR Am J Roentgenol"},{"key":"R6-20260526","doi-asserted-by":"crossref","first-page":"321595","DOI":"10.1155\/2014\/321595","article-title":"Better understanding in the differentiation of thyroid follicular adenoma, follicular carcinoma, and follicular variant of papillary carcinoma: a retrospective study.","volume":"2014","author":"Yoon","year":"2014","journal-title":"Int J Endocrinol"},{"key":"R7-20260526","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1634\/theoncologist.2010-0405","article-title":"Follicular adenoma and carcinoma of the thyroid gland.","volume":"16","author":"Mchenry","year":"2011","journal-title":"Oncologist"},{"key":"R8-20260526","doi-asserted-by":"crossref","first-page":"109717","DOI":"10.1016\/j.ejrad.2021.109717","article-title":"Artificial intelligence in ultrasound.","volume":"139","author":"Shen","year":"2021","journal-title":"Eur J Radiol"},{"key":"R9-20260526","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12880-024-01244-1","article-title":"The value of a neural network based on multi-scale feature fusion to ultrasound images for the differentiation in thyroid follicular neoplasms.","volume":"24","author":"Chen","year":"2024","journal-title":"BMC Med Imaging"},{"key":"R10-20260526","doi-asserted-by":"crossref","first-page":"3098293","DOI":"10.1155\/2017\/3098293","article-title":"Differentiation of the follicular neoplasm on the gray-scale us by image selection subsampling along with the marginal outline using convolutional neural network.","volume":"2017","author":"Seo","year":"2017","journal-title":"Biomed Res Int"},{"key":"R11-20260526","doi-asserted-by":"crossref","first-page":"257","DOI":"10.14366\/usg.19069","article-title":"Application of machine learning to ultrasound images to differentiate follicular neoplasms of the thyroid gland.","volume":"39","author":"Shin","year":"2020","journal-title":"Ultrasonography"},{"key":"R12-20260526","doi-asserted-by":"crossref","first-page":"981403","DOI":"10.3389\/fendo.2022.981403","article-title":"An artificial intelligence ultrasound system\u2019s ability to distinguish benign from malignant follicular-patterned lesions.","volume":"13","author":"Xu","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"R13-20260526","doi-asserted-by":"crossref","first-page":"245040","DOI":"10.1088\/1361-6560\/abc6f2","article-title":"Segmentation and classification of thyroid follicular neoplasm using cascaded convolutional neural network.","volume":"65","author":"Yang","year":"2020","journal-title":"Phys Med Biol"},{"key":"R14-20260526","doi-asserted-by":"crossref","first-page":"2732","DOI":"10.1097\/JS9.0000000000000506","article-title":"Automated diagnosis and management of follicular thyroid nodules based on the devised small-dataset interpretable foreground optimization network deep learning: a multicenter diagnostic study.","volume":"109","author":"Yang","year":"2023","journal-title":"Int J Surg"},{"key":"R15-20260526","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1007\/s10278-022-00639-2","article-title":"Differentiate thyroid follicular adenoma from carcinoma with combined ultrasound radiomics features and clinical ultrasound features.","volume":"35","author":"Yu","year":"2022","journal-title":"J Digit Imaging"},{"key":"R16-20260526","doi-asserted-by":"crossref","first-page":"b2700","DOI":"10.1136\/bmj.b2700","article-title":"The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration.","volume":"339","author":"Liberati","year":"2009","journal-title":"BMJ"},{"key":"R17-20260526","doi-asserted-by":"crossref","first-page":"e1000097","DOI":"10.1371\/journal.pmed.1000097","article-title":"Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement.","volume":"6","author":"Moher","year":"2009","journal-title":"PLoS Med"},{"key":"R18-20260526","first-page":"938","article-title":"[QUADAS-C-A tool for assessing risk of bias regarding quality assessment of diagnostic accuracy studies-comparative].","volume":"43","author":"Yang","year":"2022","journal-title":"Zhonghua Liu Xing Bing Xue Za Zhi"},{"key":"R19-20260526","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1089\/thy.2021.0602","article-title":"Temporal trends in papillary and follicular thyroid cancer incidence from 1995 to 2019 in adults in denmark according to education and income.","volume":"32","author":"S\u00f8rensen","year":"2022","journal-title":"Thyroid"},{"key":"R20-20260526","first-page":"1757","article-title":"Comparison of the diagonostic value of C-TIRADS and ACR-TIRADS for follicular thyroid carcinoma.","volume":"51","author":"Zhang","year":"2023","journal-title":"Modern Med J"},{"key":"R21-20260526","first-page":"398","article-title":"Progress in the application of artificial intelligence inpathologic diagnosis of thyroid needle aspiration cells.","volume":"35","author":"Liu","year":"2023","journal-title":"Carcinogenesis Teratogenesis Mutagenesis"},{"key":"R22-20260526","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1001\/jamainternmed.2022.4969","article-title":"Artificial intelligence in breast cancer screening: evaluation of FDA device regulation and future recommendations.","volume":"182","author":"Potnis","year":"2022","journal-title":"JAMA Intern Med"},{"key":"R23-20260526","first-page":"16","article-title":"Quality analysis of ultrasonic diagnosis of follicular thyroid carcinoma.","volume":"30","author":"Zahng","year":"2023","journal-title":"Chin Health Quality Manage"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:29:06Z","timestamp":1779805746000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":23,"journal-issue":{"issue":"40","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000044745","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"2025-06-18","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-29","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}