{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T06:21:46Z","timestamp":1773642106271,"version":"3.50.1"},"reference-count":20,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to identify the clinical and laboratory variables determining the true diagnostic contribution of FDG-PET\/CT in patients with fever of unknown origin (FUO) or inflammation of unknown origin (IUO), and to develop machine learning models capable of predicting which patients are most likely to benefit from PET\/CT imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort of patients aged over 18\u202fyears who underwent FDG-PET\/CT for FUO\/IUO evaluation was analyzed. Machine learning algorithms\u2014including Extreme Gradient Boosting (XGBoost), linear and radial basis function Support Vector Machines, Multilayer Perceptron (MLP), k-Nearest Neighbors (KNN), Random Forest, Decision Tree, Logistic Regression (LR), and Na\u00efve Bayes (NB)\u2014were trained to predict true positive and true negative PET\/CT results. Feature selection was performed using the PowerSHAP method. Model performance was compared using area under the precision\u2013recall curve (PR-AUC), Receiver Operating Characteristic \u2013 Area Under the Curve (ROC-AUC), accuracy, precision, recall, and F1-score metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 273 patients (151 men, 55.3%; mean age: 59\u202f\u00b1\u202f16.9\u202fyears) were included. PET\/CT provided diagnostic benefit in 203 patients (74.4%). All algorithms performed well in terms of PR-AUC (&amp;gt;0.79), with the highest scores achieved by MLP and XGBoost, reaching PR-AUC values of 0.86 and 0.85, respectively. All algorithms except NB demonstrated good accuracy. When both PR-AUC and accuracy were considered together, the best-performing models were MLP and Logistic Regression. LR achieved accuracy, ROC-AUC, PR-AUC, precision, recall, and F1-score values of 0.75, 0.74, 0.84, 0.85, 0.86, and 0.83, respectively, whereas MLP achieved 0.73, 0.73, 0.86, 0.85, 1.00, and 0.85. The PowerSHAP analysis suggested that lower procalcitonin and erythrocyte sedimentation rate levels, longer symptom duration, older age, generalized body pain, inpatient evaluation, and higher lymphocyte counts were associated with increased model-predicted PET\/CT usefulness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models\u2014particularly MLP and LR\u2014may have potential to assist in identifying FUO\/IUO patients who could benefit from PET\/CT imaging. The clinical and biochemical predictors highlighted in this study might help guide PET\/CT use and support more tailored diagnostic approaches in complex FUO and IUO cases, though further validation is needed.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1763501","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T05:23:38Z","timestamp":1773638618000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning approach to determine the diagnostic value and predictive factors of PET\/CT in FUO and IUO patients"],"prefix":"10.3389","volume":"13","author":[{"given":"Sule","family":"Ceylan","sequence":"first","affiliation":[{"name":"Department of Nuclear Medicine, University of Health Science, Gaziosmanpasa Training and Research Hospital","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bahadir","family":"Ceylan","sequence":"additional","affiliation":[{"name":"Department of Infectious Diseases and Clinical Microbiology, Medical Faculty, Istanbul Medipol University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oktay","family":"Olmuscelik","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Medical Faculty, Istanbul Medipol University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tansel","family":"Cakir","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Medical Faculty, Istanbul Medipol University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.amjmed.2021.07.038","article-title":"Fever of unknown origin (FUO) - a call for new research standards and updated clinical management","volume":"135","author":"Wright","year":"2022","journal-title":"Am J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.ejim.2009.01.002","article-title":"Inflammation of unknown origin versus fever of unknown origin: two of a kind","volume":"20","author":"Vanderschueren","year":"2009","journal-title":"Eur J Intern Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"5861","DOI":"10.3390\/jcm14165861","article-title":"Role of 18F FDG-PET-CT in fever and inflammation of unknown origin","volume":"14","author":"Romano Gargarella","year":"2025","journal-title":"J Clin Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"28197","DOI":"10.1038\/s41598-024-79794-1","article-title":"Retrospective study on clinical value and optimal use of [18F] FDG PET\/CT for inflammation of unknown origin in Japanese patients","volume":"14","author":"Kobayashi","year":"2024","journal-title":"Sci Rep"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e150","DOI":"10.3346\/jkms.2021.36.e150","article-title":"Predictors of diagnostic contributions and spontaneous remission of symptoms associated with positron emission tomography with Fluorine-18-fluorodeoxy glucose combined with computed tomography in classic fever or inflammation of unknown origin: a retrospective study","volume":"36","author":"Tsuzuki","year":"2021","journal-title":"J Korean Med Sci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1093\/qjmed\/hcu193","article-title":"[18F]FDG-PET\/CT for the diagnosis of patients with fever of unknown origin","volume":"108","author":"Gafter-Gvili","year":"2015","journal-title":"QJM"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1511710","DOI":"10.3389\/fmed.2024.1511710","article-title":"Diagnostic efficacy and necessity of 18F-FDG PET\/CT in fever of unknown origin: insights from a retrospective cohort study","volume":"11","author":"Yu","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"5360","DOI":"10.3390\/ijerph18105360","article-title":"The utility of 18FDG-PET\/CT in diagnosing fever of unknown origin: the experience of a large tertiary medical center","volume":"18","author":"Mahajna","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1097\/mnm.0000000000000300","article-title":"The predictive value of C-reactive protein and erythrocyte sedimentation rate for 18F-FDG PET\/CT outcome in patients with fever and inflammation of unknown origin","volume":"36","author":"Balink","year":"2015","journal-title":"Nucl Med Commun"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"449","DOI":"10.7861\/clinmed.2020-0268","article-title":"The diagnostic value of 18F-FDG PET\/CT in identifying the causes of fever of unknown origin","volume":"20","author":"Zhu","year":"2020","journal-title":"Clin Med (Lond)"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1007\/s10096-011-1440-6","article-title":"Place of (18)F-FDG-PET with computed tomography in the diagnostic algorithm of patients with fever of unknown origin","volume":"31","author":"Crouzet","year":"2012","journal-title":"Eur J Clin Microbiol Infect Dis"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.ejim.2021.07.014","article-title":"The yield of F18 FDG PET-CT for the investigation of fever of unknown origin, compared with diagnostic CT","volume":"93","author":"Buchrits","year":"2021","journal-title":"Eur J Intern Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"313","DOI":"10.23736\/s1824-4785.17.02833-3","article-title":"Evaluation of predictor variables of diagnostic [18F] FDG-PET\/CT in fever of unknown origin","volume":"62","author":"Okuyucu","year":"2018","journal-title":"Q J Nucl Med Mol Imaging"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1053\/j.semnuclmed.2021.06.008","article-title":"Limitations and pitfalls of FDG-PET\/CT in infection and inflammation","volume":"51","author":"Pijl","year":"2021","journal-title":"Semin Nucl Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"463","DOI":"10.3390\/s18020463","article-title":"Naive Bayes bearing fault diagnosis based on enhanced Independence of data","volume":"18","author":"Zhang","year":"2018","journal-title":"Sensors (Basel)"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s00259-017-3798-x","article-title":"Effect of CRP value on 18F-FDG PET vascular positivity in Takayasu arteritis: a systematic review and per-patient based meta-analysis","volume":"45","author":"Gomez","year":"2018","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1097\/RLU.0000000000002381","article-title":"FDG-PET\/CT for detecting an infection focus in patients with bloodstream infection: factors affecting diagnostic yield","volume":"44","author":"Pijl","year":"2019","journal-title":"Clin Nucl Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.2967\/jnumed.117.192062","article-title":"Does antibiotic treatment affect the diagnostic accuracy of 18F-FDG PET\/CT studies in patients with suspected infectious processes?","volume":"58","author":"Kagna","year":"2017","journal-title":"J Nucl Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1763501\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T05:23:39Z","timestamp":1773638619000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1763501\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":20,"alternative-id":["10.3389\/fmed.2026.1763501"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1763501","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"article-number":"1763501"}}