Kicky van Leeuwen KG, Schalekamp S, Rutten MJCM, Huisman M, Schaefer-Prokop CM, de Rooij M, van Ginneken B, Maresch B, Geurts BHJ, van Dijke CF, Laupman-Koedam E, Hulleman EV, Verhoeff EL, Meys EMJ, Mohamed Hoesein FAA, Ter Brugge FM, van Hoorn F, van der Wel F, van den Berk IAH, Luyendijk JM, Meakin J, Habets J, Verbeke JIML, Nederend J, Meys KME, Deden LN, Langezaal LCM, Nasrollah M, Meij M, Boomsma MF, Vermeulen M, Vestering MM, Vijlbrief O, Algra P, Algra S, Bollen SM, Samson T, von Brucken Fock YHG; Project AIR Working Group<\/p>\n
European Journal of Radiology, 2024<\/strong><\/p>\n Abstract<\/strong> Purpose<\/strong> Materials and Methods<\/strong>
\nBackground<\/strong>
\nMultiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited.<\/p>\n
\nTo perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs.<\/p>\n
\nThis retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience.<\/p>\n