Parkinson's disease identification through Optimum-Path Forest

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.

ECG arrhythmia classification based on optimum-path forest

An important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e.; cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graph-based pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e.; support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e.; there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis. © 2012 Elsevier Ltd. All rights reserved.

The influence of citrus rootstocks on the relationship between the mite Brevipalpus phoenicis and citrus leprosis disease

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Social-spider optimization-based artificial neural networks training and its applications for Parkinson's disease identification

Evolutionary algorithms have been widely used for Artificial Neural Networks (ANN) training, being the idea to update the neurons' weights using social dynamics of living organisms in order to decrease the classification error. In this paper, we have introduced Social-Spider Optimization to improve the training phase of ANN with Multilayer perceptrons, and we validated the proposed approach in the context of Parkinson's Disease recognition. The experimental section has been carried out against with five other well-known meta-heuristics techniques, and it has shown SSO can be a suitable approach for ANN-MLP training step.

Identification of Candida Spp. In Patients with Denture Stomatitis: Relationship with Gender, Age, Time of Denture use and Newton’s Classification

Epidemiological researches are important to understand the distribution and etiology of oral diseases. The actual researches that show the relationship between patient ages, denture status and denture stomatitis are scarce. So, the aim of this study was to identify of Candida spp. in patients with Denture Stomatitis (DS) and to correlate with gender, age, time of denture use and Newton’s classification. 204 complete denture patients (46 males and 158 females) were selected. DS was classified according to Newton’s classification and it was related to gender, age and time of denture use. Samples from the palatal mucosa and the surface of the upper denture of patients with DS were evaluated using PCR test for identification of Candida species. T-test, chisquare and Fisher’s exact tests were used for statistical analysis. DS was evidenced in 54.4% of the sample. According to gender 41.3% of the males and 58.3% females had the disease and the differences were statistically significant (p = 0.032). The type of DS was directly influenced by the time of denture use (p<0.001), but it was not significantly related to the age of the participants (p>0.05). C. albicans, C. tropicalis, C. glabrata, C. krusei and C. dubliniensis were identified by PCR test. DS is more prevalent in women and the prevalence of DS was influenced by the time of denture use (years). C. albicans was identified as the most frequent specie in patients with DS.

Severity of Brazilian sickle cell disease patients: severity scores and feasibility of the Bayesian network model use

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Adalimumab for maintenance therapy for one year in Crohn's disease: results of a Latin American single-center observational study

Adalimumab is a fully-human antibody that inhibits TNF alpha, with a significant efficacy for long-term maintenance of remission. Studies with this agent in Latin American Crohn's disease patients are scarce. The objective of this study was to outline clinical remission rates after 12 months of adalimumab therapy for Crohn's disease patients. Retrospective, single-center, observational study of a Brazilian case series of Crohn's disease patients under adalimumab therapy. Variables analyzed: demographic data, Montreal classification, concomitant medication, remission rates after 1, 4, 6 and 12 months. Remission was defined as Harvey-Bradshaw Index ≤ 4, and non-responder-imputation and last-observation-carried-forward analysis were used. The influence of infliximab on remission rates was analyzed by Fischer and Chi-square tests (P<0.05). Fifty patients, with median age of 35 years at therapy initiation, were included. Remission rates after 12 months of therapy were 54% under non-responder-imputation and 88% under last-observation-carried-forward analysis. After 12 months, remission on patients with previous infliximab occurred in 69.23% as compared to 94.59% in infliximab-naïve patients (P = 0.033). Adalimumab was effective in maintaining clinical remission after 12 months of therapy, with an adequate safety profile, and was also more effective in infliximab naïve patients.

Risk factors for postoperative endoscopic recurrence in Crohn's disease: a Brazilian observational study

Introduction: Postoperative endoscopic recurrence (PER) is the initial event after intestinal resection in Crohn’s disease (CD), and after a few years most patients present with progressive symptoms and complications related to the disease. The identification of risk factors for PER can help in the optimization of postoperative therapy and contribute to its prevention. Methods: Retrospective, longitudinal, multicenter, observational study involving patients with CD who underwent ileocolic resections. The patients were allocated into two groups according to the presence of PER and the variables of interest were analyzed to identify the associated factors for recurrence. Results: Eighty-five patients were included in the study. The mean period of the first postoperative colonoscopy was 12.8 (3–120) months and PER was observed in 28 patients (32.9%). There was no statistical difference in relation to gender, mean age, duration of CD, family history, previous intestinal resections, smoking, Montreal classification, blood transfusion, residual CD, surgical technique, postoperative complications, presence of granulomas at histology, specimen extension and use of postoperative biological therapy. The preoperative use of corticosteroids was the only variable that showed a significant difference between the groups in univariate analysis, being more common in patients with PER (42.8% vs. 21%; p = 0.044). Conclusions: PER was observed in 32.9% of the patients. The preoperative use of corticosteroids was the only risk factor associated with PER in this observational analysis.

P-215-Quantitative variation of some gut bacteria in Crohn's disease can be related to the patient's gender

Background: Imbalance in bacterial species composition of the gut microbiota is one of the factors associated with the cause or complication of the symptoms of Crohn's disease (CD). This disequilibrium consists in the reduction of biodiversity, decrease of genus such as Bifidobacterium and elevation of species such as Escherichia coli. Human microbiota varies among subjects of a same population irrespective of their health condition and among individuals living in distinct geographic locations. In animal models, sex related differences could also be observed in gut bacterial species composition under some pathological conditions. Experiments conducted with mice have demonstrated that the manifestation of type 1 diabetes (T1D) could be under the influence of the animal sex and its serum level of testosterone, which in turn could be modulated by a particular gut microbiota. Considering the existence of similar features between T1D and CD, such as strong genetic component and malfunctioning of the immune system, we investigated whether differences could be observed in the gut microbiota dysbiosis of male and female CD patients. Methods: Fifty and 5 gut mucosal biopsies from 25 adult CD patients (11 males and 14 females) and 43 specimens of an equivalent clinical material from 22 control subjects (11 males and 11 females) were screened for bacterial biodiversity by analyzing sequences of 16SrDNA V6 region. A number of 2-3 samples each from distinct gut segments (from ileum to rectum) were taken from each subject. The 16SrDNA sequences were obtained by sequencing PCR amplicons of the corresponding gene in the Ion torrent PGM sequencer. Identification and classification of the bacterial groups followed the Ribosomal Database Project (RDP) website pipeline. The relationships of the bacterial taxa with each of the study parameters was performed by compiling the data in a MS Excel and the level of statistical significance determined by the Chi-square test. Results: A total of 3203 16SrDNA sequences were detected in the 98 biopsies samples, the majority of which matching Proteobacteria, Firmicutes, Bacterioidetes, and Actinobacteria. The percentage of DNA sequences for each of these phyla found in Male control subjects/Male CD patients was 40.5/33, 32.7/32.4, 20.8/24.5, and 4.4/4,4 for Proteobacteria, Firmicutes, Bacterioidetes, and Actinobacteria, respectively. In Female comparisons, these values were 35.6/42, 39.2/26.3, 19.8/23.3, 5.2/7. Both Male and Female CD patients presented higher numbers of sequences of Actinobacteria and Bacterioidetes than those of control subjects of the same gender. Case-control differences for Firmicutes could be observed only in female comparisons and, for Proteobacteria, although case-control differences were observed in both genders, the nature of difference was distinct, since while in CD female patients a higher number of sequences matching this phylum was detected, in males a reduced number was observed, in comparison with controls. The species responsible for the Proteobacteria variation in both gender was Escherichia coli. Conclusions: The data presented above suggest that any analysis of dysbiosis in CD must take in account the patient's gender, an observation particularly relevant for Escherichia coli, whose association with CD has been most intensively investigated and for which the present study shows a reverse quantitative variation regarding the patients' gender.

Revised Diagnostic Criteria for Vogt-Koyanagi-Harada Disease: Considerations on the Different Disease Categories

PURPOSE: To evalulate the applicability of the Revised Diagnostic Criteria for Vogt-Koyanagi-Harada (VKH) disease to Brazilian patients and to verify the association between different disease categories, clinical parameters, and the presence of HLA-DRB1*0405. DESIGN: A retrospective observational case series. METHODS: Medical charts of 67 patients (10 to 64 years in age; 12 men and 55 women), from the Uveitis Service, Hospital das Clinicas, University of Sao Paulo School of Medicine (HCFMUSP), Sao Paulo, Brazil were reviewed. Patients, previously diagnosed with VKH disease using criteria proposed by the American Uveitis Society, underwent retrospective classification based on the Revised Diagnostic Criteria. The degree of concordance was assessed. At presentation, 46 patients (69%) were in the early phase. In this group, the mean time from disease onset to treatment was 15 days (range, one to 30 days). Forty-eight patients (72%) were typed for HLA-DRB1*0405 by polymerase chain reaction-sequence specific primer and polymerase chain reaction,sequence, specific oligonucleotides primer. Disease categories, phase at initial presentation, and ocular complications were analyzed. RESULTS: There was a 100% of concordance between the two criteria. Disease was classified as complete in 10 patients (15%), incomplete in 37 patients (55%), and probable in 20 patients (30%). In each group, respectively, 90%, 76%, and 45% were in the early phase at presentation (P = .017). There was no association between disease categories, the presence of HLA-DRB1*0405, and clinical parameters. CONCLUSION. The Revised Diagnostic Criteria proved useful for diagnosis of VKH disease in Brazilian patients. The present retrospective study did not find any association between disease category and severity parameters. To better understand the relevance of disease categories, a minimum follow-up period to categorize patients should be included in future prospective studies. (Am J Ophthalmol 2009;147:339-345. (C) 2009 by Elsevier Inc. All rights reserved.)

Dyspeptic symptoms and delayed gastric emptying of solids in patients with inactive Crohn's disease

Background: Patients with Crohn's disease (CD) have been shown to present dyspeptic symptoms more frequently than the general population. Some of these symptoms could be related to motility disorders to some degree. Then, we propose to investigate whether gastric emptying of solids in patients with inactive CD is delayed and to determine the relationships between gastric emptying and dyspeptic symptoms in inactive CD. Methods: Twenty-six patients with inactive Crohn's disease, as defined by a Crohn's Disease Activity Index (CDAI) < 150, underwent a gastric emptying test by breath test using C-13 octanoic acid coupled to a solid meal and answered a validated questionnaire (The Porto Alegre Dyspeptic Symptoms Questionnaire) to assess dyspeptic symptoms. Patients with scores >= 6 were considered to have dyspepsia. The control group was composed by 19 age-and sex-matched healthy volunteers. Results: Patients with CD had a significantly longer t 1/2 and t lag (p<0.05) than the controls. CD patients with dyspepsia had significantly (p<0.05) prolonged gastric emptying when compared to patients without dyspeptic symptoms. When the individual symptom patterns were analyzed, only vomiting was significantly associated with delayed gastric emptying (p<0.05). There was no difference between the subgroups of patients with respect to gender, CDAI scores, disease location, clinical behavior (obstructive/obstructive) or previous gastrointestinal surgery. Conclusion: Delayed gastric emptying in inactive Crohn's disease patients seems to be associated with dyspeptic symptoms, particularly vomiting, even without any evidence of gastrointestinal obstruction.

Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients

Background: Tuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for predicting pulmonary TB in hospitalized patients in a high prevalence area in order to contribute to a more rational use of isolation rooms without increasing the risk of transmission. Methods: Cross sectional study of patients admitted to CFFH from March 2003 to December 2004. A classification and regression tree (CART) model was generated and validated. The area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values were used to evaluate the performance of model. Validation of the model was performed with a different sample of patients admitted to the same hospital from January to December 2005. Results: We studied 290 patients admitted with clinical suspicion of TB. Diagnosis was confirmed in 26.5% of them. Pulmonary TB was present in 83.7% of the patients with TB (62.3% with positive sputum smear) and HIV/AIDS was present in 56.9% of patients. The validated CART model showed sensitivity, specificity, positive predictive value and negative predictive value of 60.00%, 76.16%, 33.33%, and 90.55%, respectively. The AUC was 79.70%. Conclusions: The CART model developed for these hospitalized patients with clinical suspicion of TB had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but our model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.

Autoimmune disease and multiple autoantibodies in 42 patients with RASopathies

The association of RASopathies [Noonan syndrome (NS) and Noonan-related syndromes] and autoimmune disorders has been reported sporadically. However, a concomitant evaluation of autoimmune diseases and an assessment of multiple autoantibodies in a large population of patients with molecularly confirmed RASopathy have not been performed. The clinical and laboratory features were analyzed in 42 RASopathy patients, the majority of whom had NS and five individuals had Noonan-related disorders. The following autoantibodies were measured: Anti-nuclear antibodies, anti-double stranded DNA, anti-SS-A/Ro, anti-SS-B/La, anti-Sm, anti-RNP, anti-Scl-70, anti-Jo-1, anti-ribosomal P, IgG and IgM anticardiolipin (aCL), thyroid, anti-smooth muscle, anti-endomysial (AE), anti-liver cytosolic protein type 1 (LC1), anti-parietal cell (APC), anti-mitochondrial (AM) antibodies, anti-liver-kidney microsome type 1 antibodies (LKM-1), and lupus anticoagulant. Six patients (14%) fulfilled the clinical criteria for autoimmune diseases [systemic lupus erythematous, polyendocrinopathy (autoimmune thyroiditis and celiac disease), primary antiphospholipid syndrome (PAPS), autoimmune hepatitis, vitiligo, and autoimmune thyroiditis]. Autoimmune antibodies were observed in 52% of the patients. Remarkably, three (7%) of the patients had specific gastrointestinal and liver autoantibodies without clinical findings. Autoimmune diseases and autoantibodies were frequently present in patients with RASopathies. Until a final conclusion of the real incidence of autoimmunity in Rasopathy is drawn, the physicians should be alerted to the possibility of this association and the need for a fast diagnosis, proper referral to a specialist and ultimately, adequate treatment. (c) 2012 Wiley Periodicals, Inc.

Kawasaki disease and juvenile systemic lupus erythematosus

Kawasaki disease (KD) is a common vasculitis in childhood. To the authors' knowledge, only one case of juvenile systemic lupus erythematosus (JSLE)-like onset mimicking KD and another case of KD and JSLE association have previously been described. However, the prevalence of this association of the two diseases was not reported. Therefore, over 27 consecutive years, 5419 patients were followed at the Pediatric Rheumatology Unit and 271 (5%) of them met the ACR classification criteria for JSLE. Two (0.7%) of them were female. These also had KD according to European League against Rheumatism / Paediatric Rheumatology European Society (EULAR/PReS) consensus criteria and are described in this report. One case was a 13-year-old who presented all six KD criteria. Echocardiogram showed pericardial effusion, dilatation and tortuosity of right and left coronary, and her symptoms promptly improved after treatment with intravenous immunoglobulin (IVIG). Lupus diagnosis was established a few days later. Another case was a 4-year-old who had also met all six KD criteria, with improvement after IVIG, and lupus diagnosis was made 1 year later. In conclusion, the frequency of the association between these two autoimmune diseases was rare. The occurrence of a second autoimmune systemic disease in a patient with a history of KD should also be considered. Furthermore, the initial presentation of lupus may mimic KD. Lupus (2012) 21, 89-92.

Effect of age at disease onset in the clinical profile of spondyloarthritis: a study of 1424 Brazilian patients

Objectives To analyse demographic and clinical variables in patients with disease onset before and after 40, 45 and 50 years in a large series of Brazilian SpA patients. Methods A common protocol of investigation was prospectively applied to 1424 SpA patients in 29 centres distributed through the main geographical regions in Brazil. The mean age at disease onset was 28.56 +/- 12.34 years, with 259 patients (18.2%) referring disease onset after 40 years, 15.1 (10.6%) after 45 years and 81 (5.8%) after 50 years. Clinical and demographic variables and disease indices (BASDAI, BASFI, BASRI, MASES, ASQoL) were investigated. Ankylosing spondylitis was the most frequent disease (66.3%), followed by psoriatic arthritis (18%), undifferentiated SpA (6.7%), reactive arthritis (5.5%), and enteropathic arthritis (3.5%). Results Comparing the groups according to age of disease onset, those patients with later onset presented statistical association with female gender, peripheral arthritis, dactylitis, nail involvement and psoriasis, as well as negative statistical association with inflammatory low hack pain, alternating buttock pain, radiographic sacroiliitis, hip involvement, positive familial history, HLA-B27 and uveitis. BASDAI, BASFI and quality of life, as well as physicians and patient's global assessment, were similar in all the groups. Radiographic indices showed worse results in the younger age groups. Conclusion There are two different clinical patterns in SpA defined by age at disease onset: one with predominance of axial symptoms in the group with disease onset <= 40 years and another favouring the peripheral manifestations in those with later disease onset.