{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:58:47Z","timestamp":1781279927303,"version":"3.54.1"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Cervical cancer remains a major cause of morbidity and mortality among women, particularly in low- and middle-income countries, where delays in screening and diagnostic follow-up limit early detection. Artificial intelligence applied to medical imaging may strengthen screening programs by improving accuracy, consistency, and timeliness in resource-limited settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to evaluate the internally validated screening performance of CITOBOT AI, an artificial intelligence system for real-world cervical cancer screening using colposcopy imaging, in a public hospital setting in Colombia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A cross-sectional study was conducted among 650 women screened at \u2018Silo\u00e9\u2019 Hospital in Cali, Colombia, between February 2023 and July 2025. Colposcopy-guided biopsy served as the reference standard. A total of 2,648 cervical images were classified using a predefined binary endpoint: screen-negative\/no risk versus screen-positive\/at risk. The model was developed using transfer learning, image segmentation, data augmentation, patient-level data partitioning, and five-fold cross-validation within the training subset. Screening performance was evaluated using accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, predictive values, and confusion matrix analysis. A secondary exploratory analysis examined associations between selected clinical variables and AI-based screening classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CITOBOT AI achieved internally validated screening performance with an accuracy of 94.3%, sensitivity of 93.4%, specificity of 94.9%, and an area under the receiver operating characteristic curve of 0.98. Positive and negative predictive values were 92.9 and 96.2%, respectively. Performance estimates were stable across patient-level folds and consistent with the hold-out validation subset within the same dataset. HPV status showed an unexpected inverse association with AI screen-positive classification; this finding should not be interpreted as biologically protective or as evidence that HPV status influenced model output, since HPV status was not used as an input variable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>CITOBOT AI demonstrated promising internally validated performance for real-world cervical cancer screening based on colposcopy imaging. The predefined binary classification is consistent with its intended role as a screening support tool to identify women who may require confirmatory colposcopy and biopsy, while histopathology remains the reference standard for lesion grading and therapeutic decision-making. External validation in independent multicenter and population-based datasets is required before broader implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1802494","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:00:16Z","timestamp":1781276416000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CITOBOT AI for real-world cervical cancer screening using colposcopy imaging"],"prefix":"10.3389","volume":"14","author":[{"given":"Marcela","family":"Arrivillaga","sequence":"first","affiliation":[{"name":"Department of Public Health and Epidemiology, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Neira","sequence":"additional","affiliation":[{"name":"Alcald\u00eda de Santiago de Cali, Red de Salud Ladera ESE","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David Steven","family":"Rivero","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Science, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hern\u00e1n Dario","family":"Vargas-Cardona","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Science, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paula C.","family":"Berm\u00fadez","sequence":"additional","affiliation":[{"name":"Department of Public Health and Epidemiology, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Pablo","family":"Garc\u00eda-Cifuentes","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Science, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Carlos","family":"Aristizabal","sequence":"additional","affiliation":[{"name":"Department of Public Health and Epidemiology, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria del Mar","family":"Torres","sequence":"additional","affiliation":[{"name":"Department of Maternal and Child Health, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andres","family":"Jaramillo-Botero","sequence":"additional","affiliation":[{"name":"Institute of Omics Sciences, Pontificia Universidad Javeriana","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diana Maria","family":"Castrill\u00f3n","sequence":"additional","affiliation":[{"name":"Alcald\u00eda de Santiago de Cali, Red de Salud Ladera ESE","place":["Cali, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1002\/cncy.22733","article-title":"Cervical cancer prevention in the United States\u2014where we've been and where we're going: the American Cancer Society primary HPV screening initiative","volume":"131","author":"Ritu","year":"2023","journal-title":"Cancer Cytopathol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1136\/ijgc-2022-003703","article-title":"Updates on cervical cancer prevention","volume":"33","author":"Viveros-Carre\u00f1o","year":"2023","journal-title":"Int J Gynecol Cancer"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1002\/cncr.34006","article-title":"Cervical cancer prevention: human papillomavirus testing as primary screening","volume":"128","author":"Desai","year":"2022","journal-title":"Cancer"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"53","DOI":"10.30699\/jogcr.8.1.53","article-title":"Comparison of visual inspection methods using either acetic acid solution or Lugol\u2019s iodine solution with colposcopy in screening of cervical cancer: a cross-sectional study","volume":"8","author":"Tehranian","year":"2022","journal-title":"J Obstet Gynecol Cancer Res"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1002\/ijc.33588","article-title":"Cancer statistics for the year 2020: an overview","volume":"149","author":"Ferlay","year":"2021","journal-title":"Int J Cancer"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1186\/s12992-022-00890-w","article-title":"Associated factors and global adherence of cervical cancer screening in 2019: a systematic analysis and modelling study","volume":"18","author":"Zhang","year":"2022","journal-title":"Glob Health"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1002\/ijgo.15179","article-title":"Artificial intelligence for cervical cancer screening: scoping review, 2009\u20132022","volume":"165","author":"Vargas-Cardona","year":"2024","journal-title":"Int J Gynecol Obstet"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"852746","DOI":"10.3389\/fonc.2022.852746","article-title":"Machine learning for endometrial cancer prediction and prognostication","volume":"12","author":"Bhardwaj","year":"2022","journal-title":"Front Oncol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e70243","DOI":"10.1002\/mco2.70243","article-title":"Current bioinformatics tools in precision oncology","volume":"6","author":"Wolde","year":"2025","journal-title":"MedComm"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e1372","DOI":"10.1016\/j.crad.2024.07.018","article-title":"MRI-based radiomic models for predicting lymphovascular space invasion in cervical cancer: a systematic review and meta-analysis","volume":"79","author":"Zhao","year":"2025","journal-title":"Eur Radiol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"156","DOI":"10.3389\/frai.2024.00156","article-title":"Artificial intelligence technologies for automated cervical cancer detection: a review of applications and challenges","volume":"7","author":"Khare","year":"2024","journal-title":"Front Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1002\/uog.26312","article-title":"Ultrasound-based artificial intelligence applications for patient stratification and histopathological correlation in gynecologic oncology","volume":"62","author":"Moro","year":"2024","journal-title":"Ultrasound Obstet Gynecol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e082451","DOI":"10.1186\/s12978-024-01828-8","article-title":"Acceptability of smartphone-based artificial intelligence tools for cervical cancer screening in Cameroon: a mixed-methods study","volume":"14","author":"Sachdeva","year":"2024","journal-title":"BMJ Open"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1002\/cncy.22725","article-title":"Implementation of an AI-assisted cytology system for cervical cancer screening in high-risk populations in China","volume":"131","author":"Yang","year":"2024","journal-title":"Cancer Cytopathol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1177\/2150131914529307","article-title":"Psychosocial barriers to follow-up adherence after an abnormal cervical cytology test result among low-income, inner-city women","volume":"5","author":"Hui","year":"2014","journal-title":"J Prim Care Community Health"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1186\/s12885-023-11082-z","article-title":"Failure to follow up abnormal test results associated with cervical cancer in primary and ambulatory care: a systematic review","volume":"23","author":"Martinez-Gutierrez","year":"2023","journal-title":"BMC Cancer"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"107810","DOI":"10.1016\/j.pec.2023.107810","article-title":"Confusion and anxiety in between abnormal cervical cancer screening results and colposcopy: \u201cthe land of the unknown\u201d","volume":"114","author":"Kohler","year":"2023","journal-title":"Patient Educ Couns"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1186\/s12913-023-09700-4","article-title":"Barriers to adherence to cytology exam: a case study in low-income Colombian women","volume":"23","author":"Berm\u00fadez","year":"2023","journal-title":"BMC Health Serv Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"788376","DOI":"10.3389\/fpubh.2021.788376","article-title":"Machine learning assisted cervical cancer detection","volume":"9","author":"Mehmood","year":"2021","journal-title":"Front Public Health"},{"key":"ref20","first-page":"1","article-title":"The future of cervical cancer detection: a comprehensive analysis of artificial intelligence technologies","volume":"18","author":"Khan","year":"2024","journal-title":"Oncol Radiother"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1186\/s12885-023-10808-3","article-title":"Cervical cancer survival prediction by machine learning algorithms: a systematic review","volume":"23","author":"Rahimi","year":"2023","journal-title":"BMC Cancer"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.jbi.2014.02.013","article-title":"Sample size estimation in diagnostic test studies of biomedical informatics","volume":"48","author":"Hajian-Tilaki","year":"2014","journal-title":"J Biomed Inform"},{"key":"ref23","first-page":"3992","author":"Kirillov","year":"2023"},{"key":"ref24","first-page":"2818","author":"Szegedy","year":"2016"},{"key":"ref25","first-page":"248","author":"Deng","year":"2009"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3955","DOI":"10.2147\/IJWH.S551976","article-title":"A review on the applications of artificial intelligence for diagnosing and treating cervical cancer","volume":"17","author":"Wu","year":"2025","journal-title":"Int J Women's Health"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"19535","DOI":"10.1038\/s41598-024-70670-6","article-title":"Enhancing cervical cancer cytology screening via artificial intelligence innovation","volume":"14","author":"Kurita","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1802494\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:00:17Z","timestamp":1781276417000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1802494\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":27,"alternative-id":["10.3389\/fpubh.2026.1802494"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1802494","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]},"article-number":"1802494"}}