Browsing by Subject "Early cancer detection"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    A neural network approach to multi-biomarker panel discovery by high-throughput plasma proteomics profiling of breast cancer
    (Springer Nature, 2013) Zhang, Fan; Chen, Jake; Wang, Mu; Drabier, Renee; Computer and Information Science, Purdue School of Science
    Background: In the past several years, there has been increasing interest and enthusiasm in molecular biomarkers as tools for early detection of cancer. Liquid chromatography tandem mass spectrometry (LC/MS/MS) based plasma proteomics profiling technique is a promising technology platform to study candidate protein biomarkers for early detection of cancer. Factors such as inherent variability, protein detectability limitation, and peptide discovery biases among LC/MS/MS platforms have made the classification and prediction of proteomics profiles challenging. Developing proteomics data analysis methods to identify multi-protein biomarker panels for breast cancer diagnosis based on neural networks provides hope for improving both the sensitivity and the specificity of candidate cancer biomarkers for early detection. Results: In our previous method, we developed a Feed Forward Neural Network-based method to build the classifier for plasma samples of breast cancer and then applied the classifier to predict blind dataset of breast cancer. However, the optimal combination C* in our previous method was actually determined by applying the trained FFNN on the testing set with the combination. Therefore, in this paper, we applied a three way data split to the Feed Forward Neural Network for training, validation and testing based. We found that the prediction performance of the FFNN model based on the three way data split outperforms our previous method and the prediction performance is improved from (AUC = 0.8706, precision = 82.5%, accuracy = 82.5%, sensitivity = 82.5%, specificity = 82.5% for the testing set) to (AUC = 0.895, precision = 86.84%, accuracy = 85%, sensitivity = 82.5%, specificity = 87.5% for the testing set). Conclusions: Further pathway analysis showed that the top three five-marker panels are associated with complement and coagulation cascades, signaling, activation, and hemostasis, which are consistent with previous findings. We believe the new approach is a better solution for multi-biomarker panel discovery and it can be applied to other clinical proteomics.
  • Thumbnail Image
    Item
    Making the Rounds: Exploring the Role of Circulating Tumor DNA (ctDNA) in Non-Small Cell Lung Cancer
    (MDPI, 2022-08-12) Shields, Misty Dawn; Chen, Kevin; Dutcher, Giselle; Patel, Ishika; Pellini, Bruna; Medicine, School of Medicine
    Advancements in the clinical practice of non-small cell lung cancer (NSCLC) are shifting treatment paradigms towards increasingly personalized approaches. Liquid biopsies using various circulating analytes provide minimally invasive methods of sampling the molecular content within tumor cells. Plasma-derived circulating tumor DNA (ctDNA), the tumor-derived component of cell-free DNA (cfDNA), is the most extensively studied analyte and has a growing list of applications in the clinical management of NSCLC. As an alternative to tumor genotyping, the assessment of oncogenic driver alterations by ctDNA has become an accepted companion diagnostic via both single-gene polymerase chain reactions (PCR) and next-generation sequencing (NGS) for advanced NSCLC. ctDNA technologies have also shown the ability to detect the emerging mechanisms of acquired resistance that evolve after targeted therapy. Furthermore, the detection of minimal residual disease (MRD) by ctDNA for patients with NSCLC after curative-intent treatment may serve as a prognostic and potentially predictive biomarker for recurrence and response to therapy, respectively. Finally, ctDNA analysis via mutational, methylation, and/or fragmentation multi-omic profiling offers the potential for improving early lung cancer detection. In this review, we discuss the role of ctDNA in each of these capacities, namely, for molecular profiling, treatment response monitoring, MRD detection, and early cancer detection of NSCLC.
  • Thumbnail Image
    Item
    Validation of a Novel Multitarget Blood Test Shows High Sensitivity to Detect Early Stage Hepatocellular Carcinoma
    (Elsevier, 2022) Chalasani, Naga P.; Porter, Kyle; Bhattacharya, Abhik; Book, Adam J.; Neis, Brenda M.; Xiong, Kong M.; Ramasubramanian, Tiruvidaimarudur S.; Edwards, David K., V; Chen, Irene; Johnson, Scott; Roberts, Lewis R.; Kisiel, John B.; Reddy, K. Rajender; Singal, Amit G.; Olson, Marilyn C.; Bruinsma, Janelle J.; Medicine, School of Medicine
    Background & aims: Hepatocellular carcinoma (HCC) is a leading cause of cancer-related death worldwide. Although biannual ultrasound surveillance with or without α-fetoprotein (AFP) testing is recommended for at-risk patients, sensitivity for early stage HCC, for which potentially curative treatments exist, is suboptimal. We conducted studies to establish the multitarget HCC blood test (mt-HBT) algorithm and cut-off values and to validate test performance in patients with chronic liver disease. Methods: Algorithm development and clinical validation studies were conducted with participants in an international, multicenter, case-control study. Study subjects had underlying cirrhosis or chronic hepatitis B virus; HCC cases were diagnosed per the American Association for the Study of Liver Diseases criteria and controls were matched for age and liver disease etiology. Whole blood and serum were shipped to a central laboratory and processed while blinded to case/control status. An algorithm was developed for the mt-HBT, which incorporates methylation biomarkers (HOXA1, TSPYL5, and B3GALT6), AFP, and sex. Results: In algorithm development, with 136 HCC cases (60% early stage) and 404 controls, the mt-HBT showed 72% sensitivity for early stage HCC at 88% specificity. Test performance was validated in an independent cohort of 156 HCC cases (50% early stage) and 245 controls, showing 88% overall sensitivity, 82% early stage sensitivity, and 87% specificity. Early stage sensitivity in clinical validation was significantly higher than AFP at 20 ng/mL or greater (40%; P < .0001) and GALAD (gender, age, Lens culinaris agglutinin-reactive AFP, AFP, and des-γ-carboxy-prothrombin score) of -0.63 or greater (71%; P = .03), although AFP and GALAD at these cut-off values had higher specificities (100% and 93%, respectively). Conclusions: The mt-HBT may significantly improve early stage HCC detection for patients undergoing HCC surveillance, a critical step to increasing curative treatment opportunities and reducing mortality.