Improve discrimination power of serum markers for diagnosis of cholangiocarcinoma using data mining-based approach

Pattanapairoj, Sirorat; Silsirivanit, Atit; Muisuk, Kanha; Seubwai, Wunchana; Cha’on, Ubon; Vaeteewoottacharn, Kulthida; Sawanyawisuth, Kanlayanee; Chetchotsak, Danaipong; Wongkham, Sopit

doi:10.1016/j.clinbiochem.2015.03.022

Cited by 28 publications

(22 citation statements)

References 26 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…87 Carcinoembryonic antigen level has been shown to correlate with tumor metastasis. 88 Several articles investigated the application of the two biomarkers, either alone 72 or a combination of the two, 67 and even in combination with other relevant biomarkers [53][54][55][56]66,75 for the diagnosis of CCA or differentiation of CCA from other similar tumors. Carbohydrate antigen-S27, studied as a diagnostic marker, was found to be significantly higher in CCA cases compared with controls (P < 0.001).…”

Section: Resultsmentioning

confidence: 99%

Biomarkers for the Diagnosis of Cholangiocarcinoma: A Systematic Review

Tshering

Dorji

Chai่jaroenkul

et al. 2018

The American Journal of Tropical Medicine and Hygiene

View full text Add to dashboard Cite

Cholangiocarcinoma (CCA), a malignant tumor of the bile duct, is a major public health problem in many Southeast Asian countries, particularly Thailand. The slow progression makes it difficult for early diagnosis and most patients are detected in advanced stages. This study aimed to review all relevant articles related to the biomarkers for the diagnosis of CCA and point out potential biomarkers. A thorough search was performed in PubMed and ScienceDirect for CCA biomarker articles. Required data were extracted. A total of 46 articles that fulfilled the inclusion and had none of the exclusion criteria were included in the analysis (17, 22, 3, 4, and 1 articles on blood, tissue, bile, both blood and tissue, and urine biomarkers, respectively). Carbohydrate antigen 19-9 (CA19-9) and carcinoembryonic antigen (CEA), either alone or in combination with other biomarkers, are the most commonly studied biomarkers in the serum. Their sensitivity and specificity ranged from 47.2% to 98.2% and 89.7% to 100%, respectively. However, in the tissue, gene methylations and DNA-related markers were the most studied CCA biomarkers. Their sensitivity and specificity ranged from 58% to 87% and 98% to 100%, respectively. Some articles investigated biomarkers both in blood and tissues, particularly CA19-9 and CEA, with sensitivity and specificity ranging from 33% to 100% and 50% to 97.7%, respectively. Although quite a number of biomarkers with a potential role in the early detection of CCA have been established, it is difficult to single out any particular marker that could be used in the routine clinical settings.

show abstract

Section: Resultsmentioning

confidence: 99%

Biomarkers for the Diagnosis of Cholangiocarcinoma: A Systematic Review

Tshering

Dorji

Chai่jaroenkul

et al. 2018

The American Journal of Tropical Medicine and Hygiene

View full text Add to dashboard Cite

show abstract

“…This means that both C4.5 and J48 are classification algorithms used to generate decision trees. The classification algorithms are useful for the diagnosis of hepatitis [48], cancer of the biliary tract [49], and lung cancer [50]; support vector machines used for the prediction of cancer growth [51] and stage I ovarian cancer [52]; for the prediction of cardiac diseases [53] and classification of eye disease [54]; to differentiate malignant, benign, and advanced pulmonary nodules [55]; and in the classification of tumors in digital mammograms [56] and diagnosis of pancreatic cancer [57]. In addition, J48 was selected because it has been used to build predictive models in similar classification problems and has shown better performance than other algorithms.…”

Section: Data Analysis Layermentioning

confidence: 99%

PISIoT: A Machine Learning and IoT-Based Smart Health Platform for Overweight and Obesity Control

et al. 2019

View full text Add to dashboard Cite

Overweight and obesity are affecting productivity and quality of life worldwide. The Internet of Things (IoT) makes it possible to interconnect, detect, identify, and process data between objects or services to fulfill a common objective. The main advantages of IoT in healthcare are the monitoring, analysis, diagnosis, and control of conditions such as overweight and obesity and the generation of recommendations to prevent them. However, the objects used in the IoT have limited resources, so it has become necessary to consider other alternatives to analyze the data generated from monitoring, analysis, diagnosis, control, and the generation of recommendations, such as machine learning. This work presents PISIoT: a machine learning and IoT-based smart health platform for the prevention, detection, treatment, and control of overweight and obesity, and other associated conditions or health problems. Weka API and the J48 machine learning algorithm were used to identify critical variables and classify patients, while Apache Mahout and RuleML were used to generate medical recommendations. Finally, to validate the PISIoT platform, we present a case study on the prevention of myocardial infarction in elderly patients with obesity by monitoring biomedical variables.

show abstract

“…Machine learning decisions can effectively assist researchers in selecting a combination of potential markers with designed specificity and sensitivity. Using a decision tree diagram built by the C4.5 algorithm, 2 of the 8 diagnostic markers were selected to distinguish CCA patients from non-CCA subjects with sensitivity, specificity and accuracy 95% 8 . With the high sensitivity, specificity and accuracy, a simple blood test could be the way to replace the biopsy; the gold standard for detecting cancer.…”

Section: Innovation Of Tumour Markers For Diagnosis and Prognosis Of mentioning

confidence: 99%

Translational cancer research towards Thailand 4.0

Sawanyawisuth¹,

Wongkham²,

Pairojkul³

et al. 2018

ScienceAsia

Self Cite

View full text Add to dashboard Cite

Cancer is still a major cause of mortality in the Thai population. The heterogeneity and complexity of cancer make this disease often result in ineffective treatment and a fatal outcome. Primary prevention for a knownrisk cancer is one way to minimize the number of new cancer cases; however, effective treatment with reasonable cost-effectiveness is important for cancer patients. Basic and preclinical cancer research are necessary for better and deeper understanding of the nature of cancer. Several research initiatives should be implemented to translate the preclinical developments to clinical outcome. High specificity and sensitivity of tumour markers in serum or secretory fluids are helpful for diagnosis of cancer before advanced, high cost, or invasive diagnoses are implemented. A set of potential markers instead of a single marker should be researched to increase the diagnostic power of the tests for a particular cancer. Simplicity, low cost, and highly effective diagnostic power of the test is also required to validate a test for clinical use. The knowledge generated at the molecular level together with the advanced technologies of next-generation sequencing, cellular and molecular biology, and computational biology, provide a new trend of precise treatment against individual cancers. Histoculture drug response assays or in vitro chemo-sensitivity assays, genomic profiling of tumours by next-generation sequencing, drug repositioning for cancer, and chimeric antigen receptor T-cell therapy are exciting approaches that lead to precise and effective therapy for cancer patients. In this review, several new directions for the precise diagnosis and effective treatments of cancer are highlighted.

show abstract

Improve discrimination power of serum markers for diagnosis of cholangiocarcinoma using data mining-based approach

Cited by 28 publications

References 26 publications

Biomarkers for the Diagnosis of Cholangiocarcinoma: A Systematic Review

Biomarkers for the Diagnosis of Cholangiocarcinoma: A Systematic Review

PISIoT: A Machine Learning and IoT-Based Smart Health Platform for Overweight and Obesity Control

Translational cancer research towards Thailand 4.0

Contact Info

Product

Resources

About