PubMed Health⌕ Search

Biomedical subjects

Melvyn Tockman

Publications and source records attributed to Melvyn Tockman.

3 recordsLinked to original sources
PubMed2004

Data mining techniques for cancer detection using serum proteomic profiling.

OBJECTIVE: Pathological changes in an organ or tissue may be reflected in proteomic patterns in serum. It is possible that unique serum proteomic patterns could be used to discriminate cancer samples from non-cancer ones. Due to the complexity of proteomic profiling, a higher order analysis such as data mining is needed to uncover the differences in complex proteomic patterns. The objectives of this paper are (1) to briefly review the application of data mining techniques in proteomics for cancer detection/diagnosis; (2) to explore a novel analytic method with different feature selection methods; (3) to compare the results obtained on different datasets and that reported by Petricoin et al. in terms of detection performance and selected proteomic patterns. METHODS AND MATERIAL: Three serum SELDI MS data sets were used in this research to identify serum proteomic patterns that distinguish the serum of ovarian cancer cases from non-cancer controls. A support vector machine-based method is applied in this study, in which statistical testing and genetic algorithm-based methods are used for feature selection respectively. Leave-one-out cross validation with receiver operating characteristic (ROC) curve is used for evaluation and comparison of cancer detection performance. RESULTS AND CONCLUSIONS: The results showed that (1) data mining techniques can be successfully applied to ovarian cancer detection with a reasonably high performance; (2) the classification using features selected by the genetic algorithm consistently outperformed those selected by statistical testing in terms of accuracy and robustness; (3) the discriminatory features (proteomic patterns) can be very different from one selection method to another. In other words, the pattern selection and its classification efficiency are highly classifier dependent. Therefore, when using data mining techniques, the discrimination of cancer from normal does not depend solely upon the identity and origination of cancer-related proteins.

Biomarkers, Tumor↗
PubMedDate not supplied

A systematic review and lessons learned from early lung cancer detection trials using low-dose computed tomography of the chest.

BACKGROUND: Computed tomography (CT) screening of the chest has shown promise for early detection of lung cancer, but evidence for a reduction in lung cancer mortality by CT screening is not available. METHODS: We reviewed 208 articles to synthesize available evidence for efficacy of CT screening in detecting potentially curative stages of lung cancer and for evidence in reducing lung cancer mortality. Other outcomes of interest included detection rate of cancer and of suspicious lesions, histology and stage of cancer at detection, screening-related morbidity, and the identification of populations uniquely suited for CT screening. We identified eight papers that reported the outcomes for CT of the chest in lung cancer screening. RESULTS: Since none of the studies utilized a control group, quantitative pooling was not done. In two studies, both CT and chest radiography (CXR) were used as screening tools in the same cohorts. A total of 19,107 subjects were screened using CT. The detected prevalence rate for lung cancer ranged from 0.40% to 13.6% and was a function of the subjects' age and smoking history. CT screening resulted in a 3-fold higher detection rate and a 5-fold increase in the rate of resectable cancers compared to CXR. Data on lung cancer and overall mortality and screening-related morbidity and mortality were incomplete. CT screening resulted in selective detection of adenocarcinomas with an approximately 2- to 3-fold oversampling of this histologic subtype. The positive predictive value of CT screening was highest for subjects in the 8th decade of life, and it was virtually nil for those in their 5th decade. CONCLUSIONS: Evidence regarding lung cancer screening by CT shows that this technology detects earlier-stage and smaller lung cancers with greater frequency than other screening methods. To date, no trials have demonstrated that CT screening leads to a reduction in lung cancer mortality. Until mortality trials are completed, low-dose CT screening should be considered an investigative tool rather than the standard of care.

Humans↗