Improving Alzheimer`s Disease Diagnosis with Machine Learning Techniques

There is not a specific test to diagnose Alzheimer`s disease (AD). Its diagnosis should be based upon clinical history, neuropsychological and laboratory tests, neuroimaging and electroencephalography (EEG). Therefore, new approaches are necessary to enable earlier and more accurate diagnosis and to follow treatment results. In this study we used a Machine Learning (ML) technique, named Support Vector Machine (SVM), to search patterns in EEG epochs to differentiate AD patients from controls. As a result, we developed a quantitative EEG (qEEG) processing method for automatic differentiation of patients with AD from normal individuals, as a complement to the diagnosis of probable dementia. We studied EEGs from 19 normal subjects (14 females/5 males, mean age 71.6 years) and 16 probable mild to moderate symptoms AD patients (14 females/2 males, mean age 73.4 years. The results obtained from analysis of EEG epochs were accuracy 79.9% and sensitivity 83.2%. The analysis considering the diagnosis of each individual patient reached 87.0% accuracy and 91.7% sensitivity.

Inflammatory Cytokines during Liver Transplantation: Prospective Randomized Trial Comparing Conventional and Piggyback Techniques

Background/Aims: Cytokines have a significant role in the response to injury following liver transplantation, but the origin and course of such molecules are not completely known. The aim of this study was to evaluate the production and liver metabolism of the inflammatory cytokines interleukin (IL)-1 beta, IL-6, IL-8, interferon (IFN)-Y and tumor necrosis factor (TNF)-alpha in orthotopic liver transplantation (OLT), comparing the conventional and the piggyback methods. Methodology: We performed a study of 30 patients who underwent elective OLT and were randomized for the conventional or piggyback techniques at the beginning of the operation. The amount of cytokines and their hepatic metabolism were calculated based on plasma concentrations and vascular blood flow at 2, 5, 10, 15, 30, 60, 90, and 120 minutes after revascularization. Results: The amount of IL-1 beta in portal blood was higher in patients who underwent surgery using the conventional technique (estimate interest = 63,783.9 +/- 16,586.1 pg/min, versus 11,979.6 +/- 16,585.7 pg/min in the piggyback group, p=0.035). There were no significant differences between the two operative`s methods for IL-6, IL-8, IFN-Y and TNF-alpha production. The hepatic metabolism of cytokines was not different between groups. Although all the curves showed higher amounts of cytokines with the conventional technique, these were not statistically significant. Conclusion: The study shows the similarity between the two techniques concerning the stimuli for the production of inflammatory molecules.

Analysis of Different Staining Techniques for C4d Detection in Renal Allograft Biopsies

Capillary C4d deposition has been recognized as a marker of antibody-mediated rejection (AMR). Although the detection of capillary C4d by means of immunofluorescence (IF) in cryostat sections is well established, frozen tissue is not always available, thus limiting the diagnosis of AMR. The aim of the present study was to analyze different techniques for C4d staining and the prevalence of C4d in renal allograft biopsies. Detection of C4d was carried out using IF or immunohistochemistry (IHC) on frozen and paraffin sections of renal allograft biopsies available from the same patients. Biopsies obtained from 20 patients were classified into 3 groups: no rejection, acute rejection, and chronic allograft nephropathy (CAN). The capillary C4d deposition prevalence in frozen-IF, considered the gold standard technique for C4d detection, was 45% (9/20 cases). Compared with frozen-IF, the frozen-IHC technique presented an 85% concordance rate (17/20 cases; r =.70; P <.001; sensitivity = 77.8%; specificity = 90.9%). The paraffin-IF technique showed similar results, with an 80% concordance rate (16/20 cases; r =.64; P <.005; sensitivity = 55.6%; specificity = 100%), whereas C4d detection occurred in only 65% of paraffin-IHC cases (13/20; r =.30; not significant; sensitivity = 66.7%; specificity = 63.6%). No capillary C4d deposition was detected in cases without evidence of rejection. However, 4/7 cases (57%) of acute rejection were C4d positive. In the CAN group, 5111 cases (45%) were C4d positive. In conclusion, these results demonstrated that frozen-IHC and paraffin-IF can be considered alternative techniques to frozen-IF for C4d detection. The paraffin-IHC technique displayed the lowest concordance rate for C4d detection.

Intracardiac Cavopulmonary Connection in Patients with Univentricular Heart Using Intra-atrial Lateral Tunnel and Intra-atrial Conduit Techniques

Background: In this study, we analyzed the time course of hemodynamic efficiency and follow-up in Fontan candidates who underwent the bidirectional Glenn procedure for staged intracardiac cavopulmonary connection (ICPC). Methods: Between 1991 and 2008, 52 patients with univentricular heart (mean age, 3.3 years; range, 2-8 years; 27 female patients [51.9%]) underwent ICPC. The cardiac malformations were as follows: tricuspid atresia, 25 cases (48.0%); common ventricle, 16 cases (30.7%); and pulmonary atresia with intact ventricular septum, 11 cases (21.1%). The intracardiac cavopulmonary procedure was indicated for all 52 cases. In 42 patients (80.7%), an intra-atrial lateral tunnel was constructed with a bovine pericardium patch. In the last 10 consecutive cases (19.3%), we performed a modified surgical technique in which we implanted an intra-atrial corrugated bovine pericardium tube sutured around the superior and inferior vena cava ostium. In all cases, a 4-mm fenestration was made to reduce the intratunnel pressure. All 52 patients had previously undergone a Glenn operation. Results: There were 2 hospital deaths (3.8%) and no recorded late deaths. During the follow-up, all patients were medicated with antiplatelet drugs. To evaluate the hemodynamic performance, we used Doppler echocardiography, computed tomography, and magnetic nuclear resonance studies. There were no prosthesis thromboses during this follow-up period. To evaluate cardiac arrhythmias, we conducted a Holter study. The last 10 patients with an intra-atrial conduit (IAC) presented with sinus rhythm and no arrhythmias during the last 4 years. The 50 surviving patients (96.1%) have been followed up for 6 to 204 months; all these patients are free of reoperation. Conclusion: The Glenn operation, which is performed at an early age, prepares the pulmonary bed to receive the ICPC. The midterm results of the intracardiac Fontan procedure seem to be good. The modified surgical procedure (IAC) can be a good alternative technique to the Fontan procedure in suitable patients.

Effects of semen storage and separation techniques on sperm DNA fragmentation

Objective: To determine the effect of semen storage and separation techniques on sperm DNA fragmentation. Design: Controlled clinical study. Setting: An assisted reproductive technology laboratory. Patient(s): Thirty normoozospermic semen samples obtained from patients undergoing infertility evaluation. Intervention(s): One aliquot from each sample was immediately prepared (control) for the sperm chromatin dispersion assay (SCD). Aliquots used to assess storage techniques were treated in the following ways: snap frozen by liquid nitrogen immersion, slow frozen with Tris-yolk buffer and glycerol, kept on ice for 24 hours or maintained at room temperature for 4 and 24 hours. Aliquots used to assess separation techniques were processed by the following methods: washed and centrifuged in media, swim-up from washed sperm pellet, density gradient separation, density gradient followed by swim-up. DNA integrity was then measured by SCD. Main Outcome Measure(s): DNA fragmentation as measured by SCD. Result(s): There was no significant difference in fragmentation among the snap frozen, slow frozen, and wet-ice groups. Compared to other storage methods short-term storage at room temperature did not impact DNA fragmentation yet 24 hours storage significantly increased fragmentation. Swim-up, density gradient and density gradient/swim-up had significantly reduced DNA fragmentation levels compared with washed semen. Postincubation, density gradient/swim-up showed the lowest fragmentation levels. Conclusion(s): The effect of sperm processing methods on DNA fragmentation should be considered when selecting storage or separation techniques for clinical use. (Fertil Steril (R) 2010;94:2626-30. (C) 2010 by American Society for Reproductive Medicine.)

Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.