biostudies-literatureMatsuzaki JNational Cancer Center Research and Development FundJapan Agency for Medical Research and DevelopmentNational Cancer Center Biobankpkac080https://www.ebi.ac.uk/biostudies/studies/S-EPMC9825310biostudies-literatureUnknown7(1)<h4>Background</h4>Noninvasive detection of early stage cancers with accurate prediction of tumor tissue-of-origin could improve patient prognosis. Because miRNA profiles differ between organs, circulating miRNomics represent a promising method for early detection of cancers, but this has not been shown conclusively.<h4>Methods</h4>A serum miRNA profile (miRNomes)-based classifier was evaluated for its ability to discriminate cancer types using advanced machine learning. The training set comprised 7931 serum samples from patients with 13 types of solid cancers and 5013 noncancer samples. The validation set consisted of 1990 cancer and 1256 noncancer samples. The contribution of each miRNA to the cancer-type classification was evaluated, and those with a high contribution were identified.<hJNCI cancer spectrumPrediction of tissue-of-origin of early stage cancers using serum miRNomes.PMC982531014ae0101011h000118ae0101011h000515ae0101011h000217ae0101011h000416ae0101011h0003Saito YKatai HShimomura AProject Team for Development and Diagnostic Technology for Detection of miRNA in Body FluidsKobayashi MShimada KAsakura KAkiba TUeno HNiida SOhno MAkio KWada TSakamoto HTsuchiya NOta NHatada IHirai MOkusaka TFujimoto HWatanabe SIFuruta KOono KTakeshita FBaba YAbe SKuroda MOchiai HShiino SSudo KFujimiya HKawai AOkanohara DAsano NTakashima HTamura KNakagama HTakamaru HOchiya THotta TOchiai AOhe YMori MKohno TKato KShiraishi KHashimoto KMitsunaga SDaiko HTakizawa SMurakami YIshikawa MMatsuzaki JIshii HBoku NKato TNarita YKondo SKanemitsu YNakae HKinoshita TMimori KYoshida YYokota TTahara HfalsePrediction of tissue-of-origin of early stage cancers using serum miRNomes.<h4>Background</h4>Noninvasive detection of early stage cancers with accurate prediction of tumor tissue-of-origin could improve patient prognosis. Because miRNA profiles differ between organs, circulating miRNomics represent a promising method for early detection of cancers, but this has not been shown conclusively.<h4>Methods</h4>A serum miRNA profile (miRNomes)-based classifier was evaluated for its ability to discriminate cancer types using advanced machine learning. The training set comprised 7931 serum samples from patients with 13 types of solid cancers and 5013 noncancer samples. The validation set consisted of 1990 cancer and 1256 noncancer samples. The contribution of each miRNA to the cancer-type classification was evaluated, and those with a high contribution were identified.<h2023-01-01T00:00:00Z2023 Jan2025-04-21T18:00:00.407Z2025-04-05T17:01:59.611ZS-EPMC98253103642687110.1093/jncics/pkac080