Differential diagnosis of pleural mesothelioma using Logic Learning Machine

Abstract

BackgroundTumour 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.MethodsLogic 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.ResultsLLM 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.ConclusionsLLM is a new flexible tool potentially useful for the differential diagnosis of pleural mesothelioma.

The Effectiveness of Electronic Differential Diagnoses (DDX) Generators: A Systematic Review and Meta-Analysis

“…These computer programmes suggest differential diagnoses based on clinical data input by users and the programmes vary in their computational methods such as utilising Bayesian probabilities and/or utilising text mining techniques. DDX programmes continue to evolve with their computational methods, particularly across medical specialities [ 8 ]. Some of the contemporary DDX generators available for generalist clinicians are capable of searching large electronic databases and are predominantly web-based providing easy access and flexibility in use while being continuously updated to reflect current evidence.…”

Pleural effusion biomarkers and computed tomography findings in diagnosing malignant pleural mesothelioma: A retrospective study in a single center

“…Our study has four important clinical strengths compared to the two previous reports mentioned above [ 9 , 18 ]. First, this is the first study to examine the sensitivity of chest CT findings combined with these PE biomarkers.…”

“…To the best of our knowledge, two previous reports have assessed the diagnostic accuracy of simultaneous SMRP, CYFRA 21–1 and CEA measurements when diagnosing MPM [ 9 , 18 ]. According to one of those reports, SMRP differentiated MPM from non-MPM better than either CYFRA 21–1 or CEA (AUC = 0.84, 0.76, and 0.32 respectively; p = 0.003) [ 9 ].…”

“…Furthermore, the utility of assessment of the PE levels of soluble mesothelin-related peptide (SMRP), which is also known as mesothelin, in MPM diagnosis has been reported [ 1 , 4 , 8 – 20 ]. However, only two previous reports have assessed the diagnostic accuracy of simultaneous assessment of SMRP, CYFRA 21–1 and CEA when diagnosing MPM [ 9 , 18 ]. Moreover, no previous reports have analyzed if the addition of chest CT findings to these PE biomarkers might enhance the sensitivity in diagnosing MPM, even though chest CT findings are important when malignant pleural diseases are suspected [ 21 ].…”

Molecular markers and new diagnostic methods to differentiate malignant from benign mesothelial pleural proliferations: a literature review

“…In this context, we can mainly categorize the identification of reliable diagnostic biomarkers as the following: historical MPM biomarkers, including immunohistochemical ones (such as GLUT-1, p53, desmin, EMA, IMP-3) (5-13) and PE soluble ones analyzable by ELISA (such as mesothelin and fibulin-3) (41-47), which have been and are still extensively studied; emerging biomarkers recently introduced into clinical practice (BAP1 analyzable by IHC and p16 by FISH) (3); suggested MPM signatures based on miRNAs and mRNA expression panels (50-52); and new diagnostic tools based on molecular panels and classification algorithms (53,(55)(56)(57).…”