Salivary metabolomics with alternative decision tree-based machine learning methods for breast cancer discrimination

Murata, Takeshi; Yanagisawa, T.; Kurihara, Toru; Kaneko, Miku; Ota, Sana; Enomoto, Ayame; Tomita, Masaru; Sugimoto, Masahiro; Sunamura, Makoto; Hayashida, Tetsu; Kitagawa, Yuko; Jinno, Hiromitsu

doi:10.1007/s10549-019-05330-9

Cited by 65 publications

(58 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Targeted and untargeted metabolomics both accounted for 6 articles ( Figure 5C). [15,27], plasma [17], tissue [18], saliva [42], urine [46] 6 plasma [9,34,41], serum [14,18,23] 2 Alanine 6 saliva [11,42], serum [15], plasma [21,41], urine [43] 5 plasma [9,34], serum [14], urine [22], serum&plasma [30] 3 Glutamic acid 6 serum [15], tissue [16,18], plasma [21], saliva [17,42] 4 plasma [9], serum [14], urine [22], serum&plasma[32] 4…”

Section: Study Characteristicsmentioning

confidence: 99%

“…Valine 4 saliva [11,42], serum [15], plasma [21] 6 plasma [9,17,24,34], serum [14], urine[22] 5 Phenylalanine 5 serum [15], tissue [18], saliva [26,42], urine […”

Section: Study Characteristicsmentioning

confidence: 99%

“…Altered utilization of energy relative to normal cells caused by the proliferative tumor cells is an acknowledged hallmark of several cancers [62]. In glycolysis metabolism, a decreasing trend of glucose [23,34,37,53,57] and an increasing tendency of lactate [11,17,21,37,57] were observed in BC. This phenomenon might be accounted for a shift in energy production of tumor cells with a preference to anaerobic glycolysis even in the presence of oxygen, known as the Warburg effect [63], which is a better way for the rapid acquisition of energy and self-protection by immune disruptions with an acidic environment [64].…”

Section: Energy Metabolismmentioning

confidence: 99%

See 2 more Smart Citations

Application of metabolomics in the diagnosis of breast cancer: a systematic review

Yang¹,

Wang²,

Cai³

et al. 2020

J. Cancer

View full text Add to dashboard Cite

Breast cancer (BC) remains the most frequent type of cancer in females worldwide. However, the pathogenesis of BC is still under the cloud, along with the huge challenge of early diagnosis, which is widely acknowledged as the key to a successful therapy. Metabolomics, a newborn innovative technique in recent years, has demonstrated great potential in cancer-related researches. The aim of this review is to look back on clinical and cellular metabolomic studies in the diagnosis of BC over the past decade, and provide a systematic summary of metabolic biomarkers and pathways related to BC diagnosis.

show abstract

Section: Study Characteristicsmentioning

confidence: 99%

“…Valine 4 saliva [11,42], serum [15], plasma [21] 6 plasma [9,17,24,34], serum [14], urine[22] 5 Phenylalanine 5 serum [15], tissue [18], saliva [26,42], urine […”

Section: Study Characteristicsmentioning

confidence: 99%

Section: Energy Metabolismmentioning

confidence: 99%

See 1 more Smart Citation

Application of metabolomics in the diagnosis of breast cancer: a systematic review

Yang¹,

Wang²,

Cai³

et al. 2020

J. Cancer

View full text Add to dashboard Cite

show abstract

“…Several studies have already been conducted to explore the possibility of using metabolite panels as biomarkers for early diagnosis, tumor characterization and clinical outcome prediction [3,[14][15][16][17][18][19][20]. Human body fluids such as saliva, urine, serum and plasma have been re-discovered as a great source of potential biological markers, and hence analyzed in the search of a metabolic profile that may be representative of systemic metabolic dysregulation in breast cancer patients [19][20][21][22][23]. However, up to today, efforts on proving highly accurate markers or proven targets for tailored therapeutic treatments have not yet delivered the expected results [24][25][26][27][28] due to the high heterogeneity displayed by breast cancer, from histology to prognosis, early recurrence, risk of metastatic progression or response to treatment and survival rates [29].…”

Section: Introductionmentioning

confidence: 99%

Human Plasma Metabolomics for Biomarker Discovery: Targeting the Molecular Subtypes in Breast Cancer

Díaz-Beltrán

González-Olmedo

Luque-Caro

et al. 2021

Cancers

View full text Add to dashboard Cite

Purpose: The aim of this study is to identify differential metabolomic signatures in plasma samples of distinct subtypes of breast cancer patients that could be used in clinical practice as diagnostic biomarkers for these molecular phenotypes and to provide a more individualized and accurate therapeutic procedure. Methods: Untargeted LC-HRMS metabolomics approach in positive and negative electrospray ionization mode was used to analyze plasma samples from LA, LB, HER2+ and TN breast cancer patients and healthy controls in order to determine specific metabolomic profiles through univariate and multivariate statistical data analysis. Results: We tentatively identified altered metabolites displaying concentration variations among the four breast cancer molecular subtypes. We found a biomarker panel of 5 candidates in LA, 7 in LB, 5 in HER2 and 3 in TN that were able to discriminate each breast cancer subtype with a false discovery range corrected p-value < 0.05 and a fold-change cutoff value > 1.3. The model clinical value was evaluated with the AUROC, providing diagnostic capacities above 0.85. Conclusion: Our study identifies metabolic profiling differences in molecular phenotypes of breast cancer. This may represent a key step towards therapy improvement in personalized medicine and prioritization of tailored therapeutic intervention strategies.

show abstract

“…The polyamine spermine displayed the greatest AUC values for comparing IC to C and the MLR model containing spermine and Ru5P together showed higher AUC values than each component model alone. Since only these two metabolites remained after features were selected using P = 0.05, this suggested a positive correlation between other metabolites and spermine or Ru5P [15] . When compared together, both models showed no significant difference between ROC curves.…”

Section: Progress Of Machine Learning Modeling In Biofluid Analysis and Cancer Metabolomics From 2000s To 2020smentioning

confidence: 99%

Clinical Applications of Artificial Intelligence on Accuracy of Cancer Prediction, Detection, and Diagnosis

Huang¹,

Zhao²,

Fan³

2020

ijirms

View full text Add to dashboard Cite

Ever since the world entered the age of information, scientists have looked into the developments and applications of the growing prospects of machine learning and neural networks. In particular, the ability for deep learning machines to determine the risk, survivability, and prognosis of tumors based on medical cancer databases has intrigued healthcare researchers seeking to improve these algorithms in recent years. There are distinct aspects of medical procedures where artificial intelligence (AI) training can be applied; for example, the calculation of risk scores for patients based on mammographic screening, analysis of the presence of biomarkers like spermine and other polyamines in fluids surrounding tumors, genomic and epigenetic assessments to map genes that influence cancer expression, as well as the utilization of metabolomic data from FTIR spectroscopy of a patient’s biofluids to help make a more reproducible and conclusive diagnosis. The goal of this review is to discuss the progress of AI and deep learning in clinical procedures and applications in recent years and evaluate the efficacy of certain AI methods for tumor diagnosis, prognosis, and prediction based on patient information from available medical databases.

show abstract

Salivary metabolomics with alternative decision tree-based machine learning methods for breast cancer discrimination

Cited by 65 publications

References 45 publications

Application of metabolomics in the diagnosis of breast cancer: a systematic review

Application of metabolomics in the diagnosis of breast cancer: a systematic review

Human Plasma Metabolomics for Biomarker Discovery: Targeting the Molecular Subtypes in Breast Cancer

Clinical Applications of Artificial Intelligence on Accuracy of Cancer Prediction, Detection, and Diagnosis

Contact Info

Product

Resources

About