Takeshi Murata1, Takako Yanagisawa2, Toshiaki Kurihara3, Miku Kaneko4, Sana Ota4, Ayame Enomoto4, Masaru Tomita4, Masahiro Sugimoto5,6, Makoto Sunamura7, Tetsu Hayashida3, Yuko Kitagawa3, Hiromitsu Jinno3. 1. Department of Breast Surgery, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo, Tokyo, 104-0045, Japan. 2. Department of Surgery, Teikyo University School of Medicine, 2-11-1 Kaga, Itabashi, Tokyo, 173-8606, Japan. 3. Department of Surgery, Keio University School of Medicine, 35 Shinanomachi, Shinjuku, Tokyo, 160-0016, Japan. 4. Institute for Advanced Biosciences, Keio University, Tsuruoka, Yamagata, 997-0052, Japan. 5. Institute for Advanced Biosciences, Keio University, Tsuruoka, Yamagata, 997-0052, Japan. mshrsgmt@gmail.com. 6. Health Promotion and Preemptive Medicine, Research and Development Center for Minimally Invasive Therapies, Tokyo Medical University, Shinjuku, Tokyo, 160-8402, Japan. mshrsgmt@gmail.com. 7. Digestive Surgery and Transplantation Surgery, Tokyo Medical University Hachioji Medical Center, Tokyo, 193-0998, Japan.
Abstract
PURPOSE: The aim of this study is to explore new salivary biomarkers to discriminate breast cancer patients from healthy controls. METHODS: Saliva samples were collected after 9 h fasting and were immediately stored at - 80 °C. Capillary electrophoresis and liquid chromatography with mass spectrometry were used to quantify hundreds of hydrophilic metabolites. Conventional statistical analyses and artificial intelligence-based methods were used to assess the discrimination abilities of the quantified metabolites. A multiple logistic regression (MLR) model and an alternative decision tree (ADTree)-based machine learning method were used. The generalization abilities of these mathematical models were validated in various computational tests, such as cross-validation and resampling methods. RESULTS: One hundred sixty-six unstimulated saliva samples were collected from 101 patients with invasive carcinoma of the breast (IC), 23 patients with ductal carcinoma in situ (DCIS), and 42 healthy controls (C). Of the 260 quantified metabolites, polyamines were significantly elevated in the saliva of patients with breast cancer. Spermine showed the highest area under the receiver operating characteristic curves [0.766; 95% confidence interval (CI) 0.671-0.840, P < 0.0001] to discriminate IC from C. In addition to spermine, polyamines and their acetylated forms were elevated in IC only. Two hundred each of two-fold, five-fold, and ten-fold cross-validation using different random values were conducted and the MLR model had slightly better accuracy. The ADTree with an ensemble approach showed higher accuracy (0.912; 95% CI 0.838-0.961, P < 0.0001). These prediction models also included spermine as a predictive factor. CONCLUSIONS: These data indicated that combinations of salivary metabolomics with the ADTree-based machine learning methods show potential for non-invasive screening of breast cancer.
PURPOSE: The aim of this study is to explore new salivary biomarkers to discriminate breast cancerpatients from healthy controls. METHODS: Saliva samples were collected after 9 h fasting and were immediately stored at - 80 °C. Capillary electrophoresis and liquid chromatography with mass spectrometry were used to quantify hundreds of hydrophilic metabolites. Conventional statistical analyses and artificial intelligence-based methods were used to assess the discrimination abilities of the quantified metabolites. A multiple logistic regression (MLR) model and an alternative decision tree (ADTree)-based machine learning method were used. The generalization abilities of these mathematical models were validated in various computational tests, such as cross-validation and resampling methods. RESULTS: One hundred sixty-six unstimulated saliva samples were collected from 101 patients with invasive carcinoma of the breast (IC), 23 patients with ductal carcinoma in situ (DCIS), and 42 healthy controls (C). Of the 260 quantified metabolites, polyamines were significantly elevated in the saliva of patients with breast cancer. Spermine showed the highest area under the receiver operating characteristic curves [0.766; 95% confidence interval (CI) 0.671-0.840, P < 0.0001] to discriminate IC from C. In addition to spermine, polyamines and their acetylated forms were elevated in IC only. Two hundred each of two-fold, five-fold, and ten-fold cross-validation using different random values were conducted and the MLR model had slightly better accuracy. The ADTree with an ensemble approach showed higher accuracy (0.912; 95% CI 0.838-0.961, P < 0.0001). These prediction models also included spermine as a predictive factor. CONCLUSIONS: These data indicated that combinations of salivary metabolomics with the ADTree-based machine learning methods show potential for non-invasive screening of breast cancer.
Entities:
Keywords:
Alternative decision tree; Biomarker; Breast cancer; Metabolomics; Polyamines; Saliva
Authors: Lyudmila V Bel'skaya; Elena A Sarf; Sergey P Shalygin; Tatyana V Postnova; Victor K Kosenok Journal: Biol Trace Elem Res Date: 2021-04-10 Impact factor: 3.738
Authors: Philipe Oliveira Fernandes; Diego Magno Martins; Aline de Souza Bozzi; João Paulo A Martins; Adolfo Henrique de Moraes; Vinícius Gonçalves Maltarollo Journal: Mol Divers Date: 2021-06-30 Impact factor: 3.364
Authors: Leticia Díaz-Beltrán; Carmen González-Olmedo; Natalia Luque-Caro; Caridad Díaz; Ariadna Martín-Blázquez; Mónica Fernández-Navarro; Ana Laura Ortega-Granados; Fernando Gálvez-Montosa; Francisca Vicente; José Pérez Del Palacio; Pedro Sánchez-Rovira Journal: Cancers (Basel) Date: 2021-01-05 Impact factor: 6.639