Prediction of prostate cancer using hair trace element concentration and support vector machine method

Guo, Jingkang; Deng, Wenhua; Zhang, Liecheng; Li, Chonghe; Wu, Ping; Mao, Peiling

doi:10.1007/bf02698010

Cited by 28 publications

(24 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hyperplane acts as a discriminant that assigns new data to a given class. SVMs have been widely used and gained popularity for classification and prediction problems in medical research in which the feature size far exceeds the available number of samples, such as in microarray or MS analyses (23)(24)(25)(26)(27)(28)(29)(30)(31)(32). Lately, approaches have been developed to adapt SVM for feature selection purposes (17,33,34).…”

Section: Data Set Designmentioning

confidence: 99%

A Critical Assessment of Feature Selection Methods for Biomarker Discovery in Clinical Proteomics

Christin

Hoefsloot

Smilde

et al. 2013

Molecular & Cellular Proteomics

134

View full text Add to dashboard Cite

In this paper, we compare the performance of six different feature selection methods for LC-MS-based proteomics and metabolomics biomarker discovery-t test, the Mann-Whitney-Wilcoxon test (mww test), nearest shrunken centroid (NSC), linear support vector machinerecursive features elimination (SVM-RFE), principal component discriminant analysis (PCDA), and partial least squares discriminant analysis (PLSDA)-using human urine and porcine cerebrospinal fluid samples that were spiked with a range of peptides at different concentration levels. The ideal feature selection method should select the complete list of discriminating features that are related to the spiked peptides without selecting unrelated features. Whereas many studies have to rely on classification error to judge the reliability of the selected biomarker candidates, we assessed the accuracy of selection directly from the list of spiked peptides. The feature selection methods were applied to data sets with different sample sizes and extents of sample class separation determined by the concentration level of spiked compounds. For each feature selection method and data set, the performance for selecting a set of features related to spiked compounds was assessed using the harmonic mean of the recall and the precision (f-score) and the geometric mean of the recall and the true negative rate (g-score). We conclude that the univariate t test and the mww test with multiple testing corrections are not applicable to data sets with small sample sizes (n ‫؍‬ 6), but their performance improves markedly with increasing sample size up to a point (n > 12) at which they outperform the other methods. PCDA and PLSDA select small feature sets with high precision but miss many true positive features related to the spiked peptides. NSC strikes a reasonable compromise between recall and precision for all data sets independent of spiking level and number of samples. Linear SVM-RFE performs poorly for selecting features related to the spiked compounds, even though the classification error is relatively low. Molecular & Cellular

show abstract

Section: Data Set Designmentioning

confidence: 99%

A Critical Assessment of Feature Selection Methods for Biomarker Discovery in Clinical Proteomics

Christin

Hoefsloot

Smilde

et al. 2013

Molecular & Cellular Proteomics

134

View full text Add to dashboard Cite

show abstract

“…17 Vanadium-containing compounds have exhibited anticancer properties, and nickel has been shown to have antimitotic properties in laboratory studies on rats. 18,19 Therefore, the effects of HESA-A against cancer cells are possibly a result of the presence of these trace elements in its composition. In toxicological studies, HESA-A did not induce any biochemical, hematological, or histopathological signs of toxicity.…”

Section: Discussionmentioning

confidence: 99%

Anticancer Effects of HESA-A in Patients With Metastatic Colon Cancer

et al. 2009

View full text Add to dashboard Cite

Background: HESA-A is a natural biological compound of herbal—marine origin. The aim of this study was to investigate the therapeutic effects of HESA-A in patients with metastatic colon cancer. Methods: Fifty consecutive patients with end-stage colon cancer and liver metastasis at the Cancer Research Center of Tehran University of Medical Sciences were studied. Patients received HESA-A 50 mg/kg/d orally in 2 to 3 divided doses for 6 months. The patients were assessed at the start and end of the 1st, 2nd, 4th, 8th, 12th, 16th, 20th, and 26th weeks of the study. The Karnofsky Performance Scale questionnaire was completed for each patient. Results: The mean Karnofsky performance score increased from 33.6 ± 9.8 to 63.3 ± 11 after 10 weeks of study. No significant hepatic or hematological adverse effects were seen during the study. Conclusion: It seems that HESA-A is an effective and safe anticancer drug, which can be used in selected patients.

show abstract

“…About 1 g of hair was collected from the occipital region of the head of each subject [13]. Each sample was put into a paper envelope and labeled for the analysis.…”

Section: Sample Collectionmentioning

confidence: 99%

Identification of Human Age Using Trace Element Concentrations in Hair and the Support Vector Machine Method

Wang

Zhang

et al. 2011

Biol Trace Elem Res

View full text Add to dashboard Cite

Trace element content in hair is affected by the age of the donor. Hair samples of subjects from four counties in China where people are known to have long lifespan ("longevity counties") were collected and the trace element content determined. Samples were subdivided into three age groups based on the age of the donors from whom these were taken: children (0-15 years); elderly (80-99 years); and centenarians (≥100 years). We compared the trace element content in hair of different age groups of subjects. Support vector machine classification results showed that a non-linear polynomial kernel function could be used to classify the three age groups of people. Age did not have a significant effect on the content of Ca and Cd in human hair. The content of Li, Mg, Mn, Zn, Cr, Cu, and Ni in human hair changed significantly with age. The magnitude of the age effect on trace element content in hair was in the order Cu>Zn>Ni>Mg>Mn>Cr>Li. Cu content in hair decreased significantly with increasing age. The hair of centenarians had higher levels of Li and Mn, and lower levels of Cr, Cu, and Ni comparing with that of the children and elderly subjects. This could be a beneficial factor of their long lifespan.

show abstract

Prediction of prostate cancer using hair trace element concentration and support vector machine method

Cited by 28 publications

References 13 publications

A Critical Assessment of Feature Selection Methods for Biomarker Discovery in Clinical Proteomics

A Critical Assessment of Feature Selection Methods for Biomarker Discovery in Clinical Proteomics

Anticancer Effects of HESA-A in Patients With Metastatic Colon Cancer

Identification of Human Age Using Trace Element Concentrations in Hair and the Support Vector Machine Method

Contact Info

Product

Resources

About