Urinary Polyamine Biomarker Panels with Machine-Learning Differentiated Colorectal Cancers, Benign Disease, and Healthy Controls

• Published in: International journal of molecular sciences 2018-03, Vol.19 (3), p.756
• Main Authors: Nakajima, Tetsushi, Katsumata, Kenji, Kuwabara, Hiroshi, Soya, Ryoko, Enomoto, Masanobu, Ishizaki, Tetsuo, Tsuchida, Akihiko, Mori, Masayo, Hiwatari, Kana, Soga, Tomoyoshi, Tomita, Masaru, Sugimoto, Masahiro
• Format: Article
• Language: English
• Subjects: Adenomatous Polyposis Coli - diagnosis; Adenomatous Polyposis Coli - urine; Benign; Biomarkers, Tumor; Case-Control Studies; Chromatography, Liquid; Colorectal cancer; Colorectal carcinoma; Colorectal Neoplasms - diagnosis; Colorectal Neoplasms - urine; Computer applications; Confidence intervals; Diagnosis, Differential; Disease control; Health and safety screening; Humans; Learning algorithms; Liquid chromatography; liquid chromatography-mass spectrometry; Machine Learning; Mass spectrometry; Mass spectroscopy; Pattern recognition; polyamine; Polyamines; Polyamines - urine; Prognosis; Quadrupoles; Reproducibility of Results; Spermidine; Spermine; Tandem Mass Spectrometry; urine
• ISSN: 1422-0067; 1661-6596; 1422-0067
• DOI: 10.3390/ijms19030756

Colorectal cancer (CRC) is one of the most daunting diseases due to its increasing worldwide prevalence, which requires imperative development of minimally or non-invasive screening tests. Urinary polyamines have been reported as potential markers to detect CRC, and an accurate pattern recognition to differentiate CRC with early stage cases from healthy controls are needed. Here, we utilized liquid chromatography triple quadrupole mass spectrometry to profile seven kinds of polyamines, such as spermine and spermidine with their acetylated forms. Urinary samples from 201 CRCs and 31 non-CRCs revealed the ₁, -diacetylspermine showing the highest area under the receiver operating characteristic curve (AUC), 0.794 (the 95% confidence interval (CI): 0.704-0.885, < 0.0001), to differentiate CRC from the benign and healthy controls. Overall, 59 samples were analyzed to evaluate the reproducibility of quantified concentrations, acquired by collecting three times on three days each from each healthy control. We confirmed the stability of the observed quantified values. A machine learning method using combinations of polyamines showed a higher AUC value of 0.961 (95% CI: 0.937-0.984, < 0.0001). Computational validations confirmed the generalization ability of the models. Taken together, polyamines and a machine-learning method showed potential as a screening tool of CRC.