Differential diagnosis of pleural mesothelioma using Logic Learning Machine.

BACKGROUND: Tumour markers are standard tools for the differential diagnosis of cancer. However, the occurrence of nonspecific symptoms and different malignancies involving the same cancer site may lead to a high proportion of misclassifications. Classification accuracy can be improved by combining information from different markers using standard data mining techniques, like Decision Tree (DT), Artificial Neural Network (ANN), and k-Nearest Neighbour (KNN) classifier. Unfortunately, each method suffers from some unavoidable limitations. DT, in general, tends to show a low classification performance, whereas ANN and KNN produce a "black-box" classification that does not provide biological information useful for clinical purposes. METHODS: Logic Learning Machine (LLM) is an innovative method of supervised data analysis capable of building classifiers described by a set of intelligible rules including simple conditions in their antecedent part. It is essentially an efficient implementation of the Switching Neural Network model and reaches excellent classification accuracy while keeping low the computational demand. LLM was applied to data from a consecutive cohort of 169 patients admitted for diagnosis to two pulmonary departments in Northern Italy from 2009 to 2011. Patients included 52 malignant pleural mesotheliomas (MPM), 62 pleural metastases (MTX) from other tumours and 55 benign diseases (BD) associated with pleurisies. Concentration of three tumour markers (CEA, CYFRA 21-1 and SMRP) was measured in the pleural fluid of each patient and a cytological examination was also carried out. The performance of LLM and that of three competing methods (DT, KNN and ANN) was assessed by leave-one-out cross-validation. RESULTS: LLM outperformed all other considered methods. Global accuracy was 77.5% for LLM, 72.8% for DT, 54.4% for KNN, and 63.9% for ANN, respectively. In more details, LLM correctly classified 79% of MPM, 66% of MTX and 89% of BD. The corresponding figures for DT were: MPM = 83%, MTX = 55% and BD = 84%; for KNN: MPM = 58%, MTX = 45%, BD = 62%; for ANN: MPM = 71%, MTX = 47%, BD = 76%. Finally, LLM provided classification rules in a very good agreement with a priori knowledge about the biological role of the considered tumour markers. CONCLUSIONS: LLM is a new flexible tool potentially useful for the differential diagnosis of pleural mesothelioma.

The CREST biorepository: a tool for molecular epidemiology and translational studies on malignant mesothelioma, lung cancer, and other respiratory tract diseases.

OBJECTIVES: The Cancer of RESpiratory Tract (CREST) biorepository was established to investigate biological mechanisms and to develop tools and strategies for primary and secondary prevention of respiratory tract cancer. The CREST biorepository is focused on pleural malignant mesothelioma, a rare and severe cancer linked to asbestos exposure whose incidence is particularly high in the Ligurian region. METHODS: The CREST biorepository includes biological specimens from (a) patients with pleural malignant mesothelioma and lung cancer, (b) patients with nonneoplastic respiratory conditions, and (c) control subjects. Whole blood, plasma, serum, lymphocytes, pleural fluid, saliva, and biopsies are collected, and a questionnaire is administered. Collection, transportation, and storage are done according to international standards. RESULTS: As of January 31, 2008, the overall number of subjects recruited was 1,590 (446 lung cancer, 209 pleural malignant mesothelioma, and 935 controls). The biorepository includes a total of 10,055 aliquots (4,741 serum; 3,082 plasma; 1,599 whole blood; 633 pleural fluid; and 561 lymphocytes) and 107 biopsies. Demographic, clinical, and epidemiologic information is collected for each subject and processed in a dedicated database. CONCLUSIONS: The CREST biorepository is a valuable tool for molecular epidemiology and translational studies. This structure relies on a network of contacts with local health districts that allows for an active search for patients. This is a particularly efficient approach, especially when the object of the study is a rare cancer type. The CREST experience suggests that the presence of limited resources can be overcome by the biorepository specialization, the high quality of the epidemiologic information, and the variety of samples.

Pleural malignant mesothelioma, genetic susceptibility and asbestos exposure.

Pleural malignant mesothelioma (MM) is a rare but extremely aggressive cancer. The limited impact of standard therapeutic treatments on survival rates makes the identification of factors that increase the individual risk a leading priority. The high proportion of cases explained by exposure to asbestos has guided intervention policies to an effective ban of this compound from our environment. However, MM cannot be solely attributed to this agent, and the role of predisposing factors and their interaction with asbestos exposure is increasingly studied. The role of mEH, GSTM1, GSTT1, NAT2, and CYP1A1 genotypes in modulating susceptibility to MM was examined in a case-control study of 80 subjects with a confirmed diagnosis of MM and 255 controls. Subjects with low mEH activity showed a significantly increased risk of MM (OR, 2.51; 95% CI, 1.11-5.68). The association was stronger in the group with low asbestos exposure (OR, 7.83; 95% CI, 0.98-62.60). A significant increased risk of MM was also found in NAT2 fast acetylators (OR, 1.74; 95% CI, 1.02-2.96). The presence of synergisms between genotypes, i.e., mEH and NAT2 (LRT for heterogeneity p<0.023), mEH and GSTM1 (LRT p<0.061), and NAT2 and GSTM1 (LRT p<0.049), combined with the interaction observed with exposure to asbestos, suggests the presence of gene-environment and gene-gene interactions in the development of MM, although the size of the study group does not allow to draw clearcut conclusions. Since genetic polymorphisms can also modify the extent of genetic damage occurring in subjects exposed to carcinogens, we measured the frequency of micronuclei in peripheral blood lymphocytes of a subgroup of MM cases. The limited number of cases (28) did not allow to observe significant effects. In conclusion, these results strengthen the hypothesis that individual susceptibility to MM can be modulated by the interaction between polymorphic genes involved in the metabolism and the intensity of asbestos exposure.

Diagnostic value of mesothelin in pleural fluids: comparison with CYFRA 21-1 and CEA.

CYFRA 21-1 and CEA have been applied for the differential diagnosis of malignant pleural mesothelioma (MPM). The soluble mesothelin-related peptide (SMRP) has been proposed as a specific marker for distinguishing MPM from benign diseases and other malignancies in pleural effusions (PEs). In this study, we evaluated the usefulness of SMRP in PEs in the detection of mesotheliomas by comparing it with that of CYFRA 21-1, CEA, and with cytological examination. One hundred and seventy-seven consecutive patients (57 MPM, 64 metastatic tumors, and 56 benign diseases) were evaluated using commercial tests. The performance of the markers was analyzed by standard ROC analysis methods, using the area under a ROC curve (AUC) as a measure of accuracy. CYFRA 21-1 better differentiated malignant from benign effusions. The corresponding area under the receiver operating characteristic curve was 0.87, while it was 0.74 for SMRP and 0.64 for CEA (p < 0.001). Conversely, SMRP differentiated MPM from all other PEs better than both CYFRA 21-1 and CEA (AUC = 0.84, 0.76, and 0.32, respectively, p = 0.003). Low levels of CEA were associated with a MPM diagnosis. The AUC for differentiating MPM from metastases was 0.81 for SMRP, 0.61 for CYFRA 21-1, and 0.20 for CEA (p < 0.001). In cases with negative or suspicious cytology, SMRP and CYFRA 21-1 identified 36/71 and 46/66 malignant PEs (29 and 31 MPM, respectively). Only 1 MPM showed a high CEA concentration. No single marker showed the best performance in any comparison. Results suggest that SMRP could improve CYFRA 21-1 and CEA accuracy in the differential diagnosis of MPM.

A bibliometric analysis of scientific production in mesothelioma research.

This study aims at comparing scientific production in malignant mesothelioma (MM) among countries and evaluating publication trends and impact factor (IF). The PubMed database was searched with a strategy combining keywords listed in the Medical Subject Headings and free-text search. Publications numbers and IF were evaluated both as absolute values and after standardization by population and gross domestic product (GDP). 5240 citations were retrieved from the biennium 1951-1952 (n = 22) to 2005-2006 (n = 535). The 177% increase of MM publications from 1987 to 2006 exceeded by large the corresponding value of total cancer literature (123.5%). In these two decades, 2559 articles with IF were published: 46.4% came from the European Union (EU) (the UK, Italy and France ranking at the top), and 36.2% from the US. The highest mean IF was reported for the US (3.346), followed by Australia (3.318), and EU (2.415, with the UK, Belgium and the Netherlands first). Finland, Sweden and Australia had the best ratio between IF (sum) and resident population or GDP. The number of publications correlated with GDP (p = 0.001) and national MM mortality rates (p = 0.002). An association was found between a country commitment to MM research and the burden of disease (p = 0.04). Asbestos, survival, prognosis, occupational exposure, differential diagnosis, and immunohistochemistry were the most commonly used keywords. This report represents the first effort to explore the geographical and temporal distribution of MM research and its determinants. This is an essential step in understanding science priorities and developing disease control policies.

Serum PDGF-AB in pleural mesothelioma.

Overexpression of platelet-derived growth factor (PDGF) has been observed in lung and pleural tumors. The aim of this study was to evaluate the diagnostic and prognostic role of serum PDGF in pleural mesothelioma (PM). Four groups of subjects were studied: 93 malignant PM patients, 33 primary non small cell lung cancer patients, 51 subjects exposed to asbestos, defined as high-risk controls, and 24 healthy controls. PDGF-AB mean concentration was higher in PM patients (45.8 ng/ml) than in high-risk controls (33.1 ng/ml) and healthy controls (26.8 ng/ml). Using the cut-off level of 49.8 ng/ml, corresponding to the mean+2SD of PDGF-AB in healthy controls, 43% of PM patients showed positive PDGF-AB levels. Survival was evaluated in 82 PM patients. At the end of the follow-up (median 9.8 months) 80.5% of patients had died. Median survival was 13.1 and 7.9 months for patients with PDGF-AB lower and higher than the cut-off, respectively. Adjusting for age, sex, histology and platelet count, positive PDGF-AB levels were associated with lower survival (OR=1.2, 95%CI: 0.9-1.6), even if not significantly so. In conclusion, serum PDGF may represent a useful additional parameter to prognostic factors already available for PM.