Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

Specific label-free and real-time detection of oxidized low density lipoprotein (oxLDL) using an immunosensor with three monoclonal antibodies

Increased levels of plasma oxLDL, which is the oxidized fraction of Low Density Lipoprotein (LDL), are associated with atherosclerosis, an inflammatory disease, and the subsequent development of severe cardiovascular diseases that are today a major cause of death in modern countries. It is therefore important to find a reliable and fast assay to determine oxLDL in serum. A new immunosensor employing three monoclonal antibodies (mAbs) against oxLDL is proposed in this work as a quick and effective way to monitor oxLDL. The oxLDL was first employed to produce anti-oxLDL monoclonal antibodies by hybridoma cells that were previously obtained. The immunosensor was set-up by selfassembling cysteamine (Cyst) on a gold (Au) layer (4 mm diameter) of a disposable screen-printed electrode. Three mAbs were allowed to react with N-hydroxysuccinimide (NHS) and ethyl(dimethylaminopropyl)carbodiimide (EDAC), and subsequently incubated in the Au/Cys. Albumin from bovine serum (BSA) was immobilized further to ensure that other molecules apart from oxLDL could not bind to the electrode surface. All steps were followed by various characterization techniques such as electrochemical impedance spectroscopy (EIS) and square wave voltammetry (SWV). The analytical operation of the immunosensor was obtained by incubating the sensing layer of the device in oxLDL for 15 minutes, prior to EIS and SWV. This was done by using standard oxLDL solutions prepared in foetal calf serum, in order to simulate patient's plasma with circulating oxLDL. A sensitive response was observed from 0.5 to 18.0 mg mL 1 . The device was successfully applied to determine the oxLDL fraction in real serum, without prior dilution or necessary chemical treatment. The use of multiple monoclonal antibodies on a biosensing platform seemed to be a successful approach to produce a specific response towards a complex multi-analyte target, correlating well with the level of oxLDL within atherosclerosis disease, in a simple, fast and cheap way.