{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:22:10Z","timestamp":1755796930304,"version":"3.44.0"},"reference-count":38,"publisher":"Termedia Sp. z.o.o.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pol J Radiol"],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To evaluate how different artificial intelligence (AI)-powered approaches affect human performance in a demanding chest computed tomography (CT) task, such as distinguishing between viral pneumonias.<\/jats:p><\/jats:sec><jats:sec><jats:title>Material and methods<\/jats:title><jats:p>Three radiologists blindly evaluated 220 chest CT scans of viral pneumonia cases (&lt;i&gt;n&lt;\/i&gt; = 151 COVID-19; &lt;i&gt;n&lt;\/i&gt; = 69 other viruses), classifying them with a probabilistic scoring system (COVID-19 Reporting and Data System \u2013 CO-RADS) in 2 phases: before (S1) and after (S2) receiving AI classifier results. Two S2 scenarios were investigated: a default approach, with AI predictions available for all cases, and a selective approach, with AI limited to equivocal S1 cases (CO-RADS = 3). Inter-reader agreement (Gwet\u2019s AC2) and diagnostic performance were analysed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Radiologists demonstrated good-to-excellent agreement across all scenarios (AC2 = 0.77-0.81). Evaluation changes between S1 and S2 occurred in 18% of cases, with 29% of cases initially classified as CO-RADS = 3. In these equivocal cases, AI led to an average correct classification rate of 85%. Conversely, when radiologists were confident in their S1 diagnoses (CO-RADS \u2260 3), classification changes in S2 occurred in 7% of cases, preventing incorrect diagnoses in 45% of patients but resulting in missed correct classifications in 55%. Regarding diagnostic performance, S1 accuracy was 78%, with 15% of CO-RADS = 3 cases. In S2, under the default approach, accuracy increased to 81%, with 16% of CO-RADS = 3 cases, whereas the selective approach achieved 79% accuracy with only 10% of CO-RADS = 3 cases. Only the selective approach significantly reduced the proportion of equivocal cases (&lt;i&gt;p&lt;\/i&gt; &lt; 0.009).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>A selective AI approach effectively reduces diagnostic uncertainty without introducing unnecessary complexity, emphasising its potential to optimise radiological workflows in challenging diagnostic scenarios.<\/jats:p><\/jats:sec>","DOI":"10.5114\/pjr\/205344","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T10:24:34Z","timestamp":1755512674000},"page":"384-393","source":"Crossref","is-referenced-by-count":0,"title":["Optimising strategies for artificial intelligence-assisted classification of viral pneumonias on CT imaging: a comparative study of selective and default approaches"],"prefix":"10.5114","volume":"90","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3451-9874","authenticated-orcid":true,"given":"Francesco","family":"Rizzetto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Berta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulia","family":"Zorzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Travaglini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diana","family":"Artioli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca Alessandro","family":"Carbonaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia","family":"Nerini Molteni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiara","family":"Vismara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Torresin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola Enrica","family":"Colombo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angelo","family":"Vanzulli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3061","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"ref-1496051","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-045343"},{"key":"ref-1496052","doi-asserted-by":"crossref","unstructured":"Sagili C. Enhancing diagnostic accuracy with AI: a review of current applications and future directions. Int J Sci Res Comput Sci Eng Inf Technol 2024; 10: 796-805.","DOI":"10.32628\/CSEIT241061119"},{"key":"ref-1496053","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105123"},{"key":"ref-1496054","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021"},{"key":"ref-1496055","doi-asserted-by":"crossref","unstructured":"Zhang K, Liu X, Shen J, Li Z, Sang Y, Wu X, et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell 2020; 181: 1423-1433.e11. DOI: https:\/\/doi.org\/10.1016\/j.cell.2020.04.045.","DOI":"10.1016\/j.cell.2020.04.045"},{"key":"ref-1496057","doi-asserted-by":"crossref","unstructured":"Yang W, Sirajuddin A, Zhang X, Liu G, Teng Z, Zhao S, et al. The role of imaging in 2019 novel coronavirus pneumonia (COVID-19). Eur Radiol 2020; 30: 4874-4882.","DOI":"10.1007\/s00330-020-06827-4"},{"key":"ref-1496058","doi-asserted-by":"crossref","unstructured":"Rubin GD, Ryerson CJ, Haramati LB, Sverzellati N, Kanne JP, Raoof S, et al. The role of chest imaging in patient management during the COVID-19 pandemic: a multinational consensus statement from the Fleischner Society. Radiology 2020; 296: 172-180.","DOI":"10.1148\/radiol.2020201365"},{"key":"ref-1496059","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021"},{"key":"ref-1496060","doi-asserted-by":"crossref","unstructured":"Fusco R, Grassi R, Granata V, Setola SV, Grassi F, Cozzi D, et al. Artificial intelligence and covid-19 using chest ct scan and chest x-ray images: machine learning and deep learning approaches for diagnosis and treatment. J Pers Med 2021; 11. DOI: https:\/\/doi.org\/3390\/jpm11100993.","DOI":"10.3390\/jpm11100993"},{"key":"ref-1496062","doi-asserted-by":"crossref","unstructured":"Kriza C, Amenta V, Zeni\u00e9 A, Panidis D, Chassaigne H, Urb\u00e1n P, et al. Artificial intelligence for imaging-based COVID-19 detection: systematic review comparing added value of AI versus human readers. Eur J Radiol 2021; 145: 110028. DOI: https:\/\/doi.org\/10.1016\/j.ejrad.2021.110028.","DOI":"10.1016\/j.ejrad.2021.110028"},{"key":"ref-1496064","doi-asserted-by":"crossref","unstructured":"Ni Q, Sun ZY, Qi L, Chen W, Yang Y, Wang L, et al. A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. Eur Radiol 2020; 30: 6517-6527.","DOI":"10.1007\/s00330-020-07044-9"},{"key":"ref-1496065","doi-asserted-by":"crossref","unstructured":"Meng F, Kottlors J, Shahzad R, Liu H, Fervers P, Jin Y, et al. AI support for accurate and fast radiological diagnosis of COVID-19: an international multicenter, multivendor CT study. Eur Radiol 2022; 33: 4280-4291.","DOI":"10.1007\/s00330-022-09335-9"},{"key":"ref-1496066","doi-asserted-by":"publisher","DOI":"10.3233\/XST-200735"},{"key":"ref-1496067","doi-asserted-by":"crossref","unstructured":"van Leeuwen KG, Schalekamp S, Rutten MJCM, van Ginneken B, de Rooij M. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur Radiol 2021; 31: 3797-3804.","DOI":"10.1007\/s00330-021-07892-z"},{"key":"ref-1496068","doi-asserted-by":"crossref","unstructured":"Jussupow E, Spohrer K, Heinzl A. Radiologists\u2019 usage of diagnostic AI systems: the role of diagnostic self-efficacy for sensemaking from confirmation and disconfirmation. Business and Information Systems Engineering 2022; 64: 293-309.","DOI":"10.1007\/s12599-022-00750-2"},{"key":"ref-1496069","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020202504"},{"key":"ref-1496070","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2020200097"},{"key":"ref-1496071","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109650"},{"key":"ref-1496072","doi-asserted-by":"crossref","unstructured":"Garrana SH, Som A, Ndakwah GS, Yeung T, Febbo J, Heeger AP, et al. Comparison of chest CT findings of COVID-19, influenza, and organizing pneumonia: a multireader study. Am J Roentgenol 2021; 217: 1093-1102.","DOI":"10.2214\/AJR.21.25640"},{"key":"ref-1496073","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020201473"},{"key":"ref-1496074","doi-asserted-by":"publisher","DOI":"10.4103\/2452-2473.357348"},{"key":"ref-1496075","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00316-7"},{"key":"ref-1496076","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-022-00317-6"},{"key":"ref-1496077","doi-asserted-by":"crossref","unstructured":"Rizzetto F, Berta L, Zorzi G, Cincotta A, Travaglini F, Artioli D, et al. Diagnostic performance in differentiating COVID-19 from other viral pneumonias on CT Imaging: multi-reader analysis compared with an artificial intelligence-based model. Tomography 2022; 8: 2815-2827.","DOI":"10.3390\/tomography8060235"},{"key":"ref-1496078","doi-asserted-by":"crossref","unstructured":"Wilson EB. Probable Inference, the law of succession, and statistical inference. J Am Stat Assoc 1927; 22: 209-212.","DOI":"10.1080\/01621459.1927.10502953"},{"key":"ref-1496079","doi-asserted-by":"crossref","unstructured":"Tran D, Dolgun A, Demirhan H. Weighted inter-rater agreement measures for ordinal outcomes. Commun Stat Simul Comput 2020; 49: 989-1003.","DOI":"10.1080\/03610918.2018.1490428"},{"key":"ref-1496080","doi-asserted-by":"crossref","unstructured":"Quarfoot D, Levine RA. How robust are multirater interrater reliability indices to changes in frequency distribution? Am Stat 2016; 70: 373-384.","DOI":"10.1080\/00031305.2016.1141708"},{"key":"ref-1496081","doi-asserted-by":"crossref","unstructured":"Vial A, Assink M, Stams GJJM, van der Put C. Safety and risk assessment in child welfare: a reliability study using multiple measures. J Child Fam Stud 2019; 28: 3533-3544.","DOI":"10.1007\/s10826-019-01536-z"},{"key":"ref-1496082","doi-asserted-by":"crossref","unstructured":"Berta L, Rizzetto F, De Mattia C, Lizio D, Felisi M, Colombo PEE, et al. Automatic lung segmentation in COVID-19 patients: impact on quantitative computed tomography analysis. Phys Med 2021; 87: 115-122.","DOI":"10.1016\/j.ejmp.2021.06.001"},{"key":"ref-1496083","doi-asserted-by":"crossref","unstructured":"Altman D. Practical statistics for medical research. London: Chapman and Hall; 1991.","DOI":"10.1201\/9780429258589"},{"key":"ref-1496084","doi-asserted-by":"crossref","unstructured":"MacDonald PL, Gardner RC. Type I error rate comparisons of post hoc procedures for I \u00d7 j chi-square tables. Educational and Psychological Measurement 2000; 60: 735-754.","DOI":"10.1177\/00131640021970871"},{"key":"ref-1496085","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30199-0"},{"key":"ref-1496086","doi-asserted-by":"publisher","DOI":"10.21037\/ATM-20-5328"},{"key":"ref-1496087","doi-asserted-by":"crossref","unstructured":"Wang H, Wang L, Lee EH, Zheng J, Zhang W, Halabi S, et al. Decoding COVID-19 pneumonia: comparison of deep learning and radiomics CT image signatures. Eur J Nucl Med Mol Imaging 2021; 48: 1478-1486.","DOI":"10.1007\/s00259-020-05075-4"},{"key":"ref-1496088","doi-asserted-by":"publisher","DOI":"10.1148\/radiol"},{"key":"ref-1496089","doi-asserted-by":"crossref","unstructured":"Mulrenan C, Rhode K, Fischer BM. A literature review on the use of artificial intelligence for the diagnosis of COVID-19 on CT and Chest X-ray. Diagnostics 2022; 12: 869. DOI: https:\/\/doi.org\/3390\/diagnostics12040869.","DOI":"10.3390\/diagnostics12040869"},{"key":"ref-1496091","doi-asserted-by":"crossref","unstructured":"F\u00fcgener A, Grahl J, Gupta A, Ketter W. Cognitive challenges in human\u2013artificial intelligence collaboration: investigating the path toward productive delegation. Information Systems Research 2022; 33: 678-696.","DOI":"10.1287\/isre.2021.1079"},{"key":"ref-1496092","doi-asserted-by":"publisher","DOI":"10.1186\/s12982-024-00140-x"}],"container-title":["Polish Journal of Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.polradiol.com\/pdf-205344-127888","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.polradiol.com\/pdf-205344-127888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T10:24:39Z","timestamp":1755512679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.polradiol.com\/Optimising-strategies-for-artificial-intelligence-assisted-classification-of-viral,205344,0,2.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":38,"alternative-id":["205344"],"URL":"https:\/\/doi.org\/10.5114\/pjr\/205344","relation":{},"ISSN":["1899-0967"],"issn-type":[{"type":"print","value":"1899-0967"}],"subject":[],"published":{"date-parts":[[2025,8,5]]}}}