Data mining techniques for cancer detection using serum proteomic profiling

Li, Lihua; Tang, Hong; Wu, Zuobao; Jianli, Gong; Gruidl, Michael E.; Zou, Jun; Tockman, Melvyn S.; Clark, Robert A.

doi:10.1016/j.artmed.2004.03.006

Cited by 167 publications

(91 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The addition of more peaks to the model initially improves its ability to separate groups; however, continued inclusion of additional peaks will increase chance differences between groups and potentially overfit the data, and may in fact detract from the accuracy of the model when applied to a larger sample population. 32,33 Therefore, 2 or 3 peaks were used in the biomarker panels in the present study to maximize discriminatory ability while minimizing effects due to chance. To obtain unbiased estimates, the crossvalidation of the prediction rule was external to the selection process.…”

Section: Discussionmentioning

confidence: 99%

Proteomic profiling of cholangiocarcinoma: Diagnostic potential of SELDI-TOF MS in malignant bile duct stricture

et al. 2006

View full text Add to dashboard Cite

Proteomic techniques promise to improve the diagnosis of cholangiocarcinoma (CC) in both tissue and serum as histological diagnosis and existing serum markers exhibit poor sensitivities. We explored the use of surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF MS) to identify potential protein biomarkers of CC. Twenty-two resected CC samples were compared with adjacent noninvolved bile duct tissue. Serum from patients with CC (n ‫؍‬ 20) was compared with patients with benign disease (n ‫؍‬ 20), and healthy volunteers (n ‫؍‬ 25). Samples were analyzed on hydrophobic protein chips via SELDI-TOF MS, and classification models were developed using logistic regression and cross-validation analysis. Univariate analysis revealed 14 individual peaks differentially expressed between CC and bile duct tissue, 4 peaks between CC and benign disease, and 12 peaks between CC and sera of healthy volunteers. The 4,462 mass-to-charge serum peak had superior discriminatory ability to carbohydrate antigen 19.9 (CA19.9) and carcinoembryonic antigen ( C holangiocarcinoma (CC) is a rare but devastating neoplasm that accounts for 3% of all gastrointestinal cancers and 15% of all primary liver cancers worldwide. 1 Five thousand new cases are diagnosed on average per year in the United States, and the incidence is rising. 2 Northeast Thailand sees the highest incidence, with 96 cases per 100,000. 1 Surgical resection is the only current chance of cure, with no proven adjunctive therapy; however, this approach has a mortality rate of 5% to 10%. 3 Even with margin-free resection, 5-year survival figures only reach 20% to 40%. 3,4 Unresectable disease is usually fatal within 6 months to 1 year, and over one third of patients present at a stage too late for resection. 3 This confirms the need for earlier and more accurate diagnostic processes.At present, diagnosis of CC relies on imaging of the biliary tree with computed tomography or ultrasonography in the presence of high clinical suspicion. Tissue diagnostic confirmation is possible for intrahepatic tumors but is very difficult in more distal and more common (2/3 of cases) extrahepatic cases. These frequently present as a stricture of the common bile duct, which can be further characterized by means of endoscopic retrograde cholangio-pancreatography. 5

show abstract

Section: Discussionmentioning

confidence: 99%

Proteomic profiling of cholangiocarcinoma: Diagnostic potential of SELDI-TOF MS in malignant bile duct stricture

et al. 2006

View full text Add to dashboard Cite

show abstract

“…This is a well-established method for the investigation of gene expression in organs or tissues undergoing pathological changes [5]. Several studies have used array analysis to investigate genomic features of EC, resulting in detection of a large range of molecular alterations.…”

Section: Array-based Technologymentioning

confidence: 99%

Biological markers with potential clinical value in endometrial cancer — review of the literature

et al. 2017

View full text Add to dashboard Cite

Endometrial carcinoma (EC) is the most common malignancy of the female genital tract encountered in western countries, making it the fourth most common cancer in women. The incidence of uterine cancer is on the rise throughout the developed world where diagnosis is increasingly observed among younger patients. With regard to this, attention has been focused on conducting more studies to achieve a better understanding of the molecular genetics related to endometrial carcinogenesis. Over the years, EC has been classified into two broad histopathological subtypes based on the mechanism of development, and we can therefore observe specific biomarkers related to the respective subtype. Based on this idea, more research has been carried out in the last decade, using biotechnological methods, with the aim to identify new potential tumor markers. By translating these findings into clinical use one may facilitate accurate diagnosis and prognostic prediction, and contribute to individualized treatment. Without a doubt, there is a demanding need to identify biomarkers that can be adopted in clinical practice in order to reduce the time needed to obtain diagnosis. Such markers may be of great value in improving patient outcome. However, a number of problems remain to be solved before this becomes a reality. This paper briefly reviews the current status of rising biomarkers in EC.

show abstract

“…Many different techniques exist such as "Inverse Normalization" [36] or "Logarithmic Normalization" [25]. The most frequently used method is global normalization with respect to the average total ion current (TIC) [12,2].…”

Section: Normalizationmentioning

confidence: 99%

Beating the Noise: New Statistical Methods for Detecting Signals in MALDI-TOF Spectra Below Noise Level

Conrad

Leichtle

Hagehülsmann

et al. 2006

Computational Life Sciences II

View full text Add to dashboard Cite

Data mining techniques for cancer detection using serum proteomic profiling

Cited by 167 publications

References 31 publications

Proteomic profiling of cholangiocarcinoma: Diagnostic potential of SELDI-TOF MS in malignant bile duct stricture

Proteomic profiling of cholangiocarcinoma: Diagnostic potential of SELDI-TOF MS in malignant bile duct stricture

Biological markers with potential clinical value in endometrial cancer — review of the literature

Beating the Noise: New Statistical Methods for Detecting Signals in MALDI-TOF Spectra Below Noise Level

Contact Info

Product

Resources

About