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.

"Evaluating the model of classification and valuation of disabilities used in Brazil and defining the elaboration and adoption of a unique model for all the country": Brazilian Interministerial Workgroup Task

The President of Brazil established an Interministerial Work Group in order to “evaluate the model of classification and valuation of disabilities used in Brazil and to define the elaboration and adoption of a unique model for all the country”. Eight Ministries and/or Secretaries participated in the discussion over a period of 10 months, concluding that a proposed model should be based on the United Nations Convention on the Rights of Person with Disabilities, the International Classification of Functioning, Disability and Health, and the ‘support theory’, and organizing a list of recommendations and necessary actions for a Classification, Evaluation and Certification Network with national coverage.

Determination of trace elements in bovine semen samples by inductively coupled plasma mass spectrometry and data mining techniques for identification of bovine class

The reproductive performance of cattle may be influenced by several factors, but mineral imbalances are crucial in terms of direct effects on reproduction. Several studies have shown that elements such as calcium, copper, iron, magnesium, selenium, and zinc are essential for reproduction and can prevent oxidative stress. However, toxic elements such as lead, nickel, and arsenic can have adverse effects on reproduction. In this paper, we applied a simple and fast method of multi-element analysis to bovine semen samples from Zebu and European classes used in reproduction programs and artificial insemination. Samples were analyzed by inductively coupled plasma spectrometry (ICP-MS) using aqueous medium calibration and the samples were diluted in a proportion of 1:50 in a solution containing 0.01% (vol/vol) Triton X-100 and 0.5% (vol/vol) nitric acid. Rhodium, iridium, and yttrium were used as the internal standards for ICP-MS analysis. To develop a reliable method of tracing the class of bovine semen, we used data mining techniques that make it possible to classify unknown samples after checking the differentiation of known-class samples. Based on the determination of 15 elements in 41 samples of bovine semen, 3 machine-learning tools for classification were applied to determine cattle class. Our results demonstrate the potential of support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF) chemometric tools to identify cattle class. Moreover, the selection tools made it possible to reduce the number of chemical elements needed from 15 to just 8.

Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study

Abstract Background Smear negative pulmonary tuberculosis (SNPT) accounts for 30% of pulmonary tuberculosis cases reported yearly in Brazil. This study aimed to develop a prediction model for SNPT for outpatients in areas with scarce resources. Methods The study enrolled 551 patients with clinical-radiological suspicion of SNPT, in Rio de Janeiro, Brazil. The original data was divided into two equivalent samples for generation and validation of the prediction models. Symptoms, physical signs and chest X-rays were used for constructing logistic regression and classification and regression tree models. From the logistic regression, we generated a clinical and radiological prediction score. The area under the receiver operator characteristic curve, sensitivity, and specificity were used to evaluate the model's performance in both generation and validation samples. Results It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%. Conclusion The results suggest that those models might be useful as screening tools for estimating the risk of SNPT, optimizing the utilization of more expensive tests, and avoiding costs of unnecessary anti-tuberculosis treatment. Those models might be cost-effective tools in a health care network with hierarchical distribution of scarce resources.

Sleep patterns and sleepiness of working college students

The double journey (work and study) may result or aggravate health problems, including sleep disturbances, as observed in previous studies with high school students. The aim of this study is to analyze the sleep-wake cycle and perceived sleepiness of working college students during weekdays. Twenty-three healthy college male students, 21-24 years old, working during the day and attending classes in the evening, participated in this study. During five consecutive days, the students filled out daily activities logs and wore actigraphs. Mean sleeping time was lower than 6 hours per night. No significant differences were observed in the sleep-wake cycle during the weekdays. The observed lack of changes in the sleep-wake cycle of these college students might occur as participants were not on a free schedule, but exposed to social constraints, as was the regular attendance to evening college and day work activities. Sleepiness worsened over the evening school hours. Those results show the burden carried by College students who perform double activities - work and study.

Multi-element determination in Brazilian honey samples by inductively coupled plasma mass spectrometry and estimation of geographic origin with data mining techniques

Multi-element analysis of honey samples was carried out with the aim of developing a reliable method of tracing the origin of honey. Forty-two chemical elements were determined (Al, Cu, Pb, Zn, Mn, Cd, Tl, Co, Ni, Rb, Ba, Be, Bi, U, V, Fe, Pt, Pd, Te, Hf, Mo, Sn, Sb, P, La, Mg, I, Sm, Tb, Dy, Sd, Th, Pr, Nd, Tm, Yb, Lu, Gd, Ho, Er, Ce, Cr) by inductively coupled plasma mass spectrometry (ICP-MS). Then, three machine learning tools for classification and two for attribute selection were applied in order to prove that it is possible to use data mining tools to find the region where honey originated. Our results clearly demonstrate the potential of Support Vector Machine (SVM), Multilayer Perceptron (MLP) and Random Forest (RF) chemometric tools for honey origin identification. Moreover, the selection tools allowed a reduction from 42 trace element concentrations to only 5. (C) 2012 Elsevier Ltd. All rights reserved.

The impact of psychiatric diagnosis on treatment adherence and duration among victimized children and adolescents in Sao Paulo, Brazil

OBJECTIVE: Despite the high prevalence of substance abuse and mood disorders among victimized children and adolescents, few studies have investigated the association of these disorders with treatment adherence, represented by numbers of visits per month and treatment duration. We aimed to investigate the effects of substance abuse and mood disorders on treatment adherence and duration in a special programfor victimized children in Sao Paulo, Brazil. METHODS: A total of 351 participants were evaluated for psychiatric disorders and classified into one of five groups: mood disorders alone; substance abuse disorders alone; mood and substance abuse disorders; other psychiatric disorders; no psychiatric disorders. The associations between diagnostic classification and adherence to treatment and the duration of program participation were tested with logistic regression and survival analysis, respectively. RESULTS: Children with mood disorders alone had the highest rate of adherence (79.5%); those with substance abuse disorders alone had the lowest (40%); and those with both disorders had an intermediate rate of adherence (50%). Those with other psychiatric disorders and no psychiatric disorders also had high rates of adherence (75.6% and 72.9%, respectively). Living with family significantly increased adherence for children with substance abuse disorders but decreased adherence for those with no psychiatric disorders. The diagnostic correlates of duration of participation were similar to those for adherence. CONCLUSIONS: Mood and substance abuse disorders were strong predictive factors for treatment adherence and duration, albeit in opposite directions. Living with family seems to have a positive effect on treatment adherence for patients with substance abuse disorders. More effective treatment is needed for victimized substance-abusing youth.

Comparison between innominate osteotomy and arthrodistraction as a primary treatment for Legg-Calve-Perthes disease: a prospective controlled trial

Legg-Calv,-Perthes (LCP) disease is currently managed by mechanical containment of the femoral head in the hip socket. As evidence suggests that hip distraction may offer a new treatment strategy, we used arthrodistraction as a primary treatment for active forms of LCP disease and prospectively compared the results with the Salter innominate osteotomy. A total of 54 children, six years or older of both genders with severe forms of LCP disease in the stages of necrosis or revascularisation, were enrolled. Patients were submitted to either Salter innominate osteotomy (n = 28) or hip arthrodistraction (n = 26). Final radiographs were used to evaluate the Mose index, Wiberg angle, extrusion index and the Stulberg et al. classification. There were no significant differences in gender, age, lateral pillar classification and average follow-up time between the two groups. The osteotomy group progressed without major complications, but children in the joint distraction group experienced episodes of pin tract pain and infection, leading to the early removal of the external device in one case. Two patients developed joint stiffness, treated by physiotherapy or manipulation, and one child developed subluxation of the femoral head. The average time in distraction was 4.44 months (2.53-7.23 months). In the final evaluation the osteotomy group showed better containment of the femoral head. The Mose index and the Stulberg et al. classification were statistically similar between the two groups. Despite similar final radiological results, arthrodistraction was associated with a higher morbidity. Consequently, we do not recommend hip distraction as a primary treatment for the early stages of LCP disease.

Coronary plaque rupture in patients with myocardial infarction after noncardiac surgery: Frequent and dangerous

Purpose: The pathophysiology of acute coronary syndromes (ACS) after noncardiac surgery is not established yet. Thrombosis over a vulnerable plaque or decreased oxygen supply secondary to anemia or hypotension may be involved. The purpose of this study was to investigate the pathophysiology of ACS complicating noncardiac surgery. Methods: Clinical and angiographic data were prospectively recorded into a database for 120 consecutive patients that had an ACS after noncardiac surgery (PACS), for 120 patients with spontaneous ACS (SACS), and 240 patients with stable coronary artery disease (CAD). Coronary lesions with obstructions greater than 50% were classified based on two criteria: Ambrose's classification and complex morphology. The presence of Ambrose's type II or complex lesions were compared between the three groups. Results: We analyzed 1470 lesions in 480 patients. In PACS group, 45% of patients had Ambrose's type II lesions vs. 56.7% in SACS group and 16.4% in stable CAD group (P < 0.001). Both PACS and SACS patients had more complex lesions than patients in stable CAD group (56.7% vs. 79.2% vs. 31.8%, respectively; P < 0.001). Overall, the independent predictors of plaque rupture were being in the group PACS (P < 0.001, OR 2.86; CI, 1.82-4.52 for complex lesions and P < 0.001, OR 3.43; CI, 2.1-5.6 for Ambrose's type II lesions) or SACS (P < 0.001, OR 8.71; CI, 5.15-14.73 for complex lesions and P < 0.001, OR 5.99; CI, 3.66-9.81 for Ambrose's type II lesions). Conclusions: Nearly 50% of patients with perioperative ACS have evidence of coronary plaque rupture, characterizing a type 1 myocardial infarction. (C) 2012 Elsevier Ireland Ltd. All rights reserved.

Assessment of Pharmaceutical Equivalence: Difference Test or Equivalence Test?

Pharmaceutical equivalence is an important step towards the confirmation of similarity and Interchangeability among pharmaceutical products, particularly regarding those that win not be tested for bioequivalence. The aim of this paper is to compare traditional difference testing to two one-side equivalence tests in the assessment of pharmaceutical equivalence, by means of equivalence studies between similar, generic and reference products of acyclovir cream, atropine sulfate injection, meropenem for injection, and metronidazole injection. All tests were performed in accordance with the Brazilian Pharmacopeia or the United States Pharmacopeia. All four possible combinations of results arise in these comparisons of difference testing and equivalence testing. Most of the former did not show significant difference, whereas the latter presented similarity. We concluded that equivalence testing is more appropriate than difference testing, what can make it a useful tool to assess pharmaceutical equivalence in products that will not be tested for bioequivalence.

Sero-epidemiological evaluation of changes in Plasmodium falciparum and Plasmodium vivax transmission patterns over the rainy season in Cambodia

Background: In Cambodia, malaria transmission is low and most cases occur in forested areas. Seroepidemiological techniques can be used to identify both areas of ongoing transmission and high-risk groups to be targeted by control interventions. This study utilizes repeated cross-sectional data to assess the risk of being malaria sero-positive at two consecutive time points during the rainy season and investigates who is most likely to sero-convert over the transmission season. Methods: In 2005, two cross-sectional surveys, one in the middle and the other at the end of the malaria transmission season, were carried out in two ecologically distinct regions in Cambodia. Parasitological and serological data were collected in four districts. Antibodies to Plasmodium falciparum Glutamate Rich Protein (GLURP) and Plasmodium vivax Merozoite Surface Protein-119 (MSP-119) were detected using Enzyme Linked Immunosorbent Assay (ELISA). The force of infection was estimated using a simple catalytic model fitted using maximum likelihood methods. Risks for sero-converting during the rainy season were analysed using the Classification and Regression Tree (CART) method. Results: A total of 804 individuals participating in both surveys were analysed. The overall parasite prevalence was low (4.6% and 2.0% for P. falciparum and 7.9% and 6.0% for P. vivax in August and November respectively). P. falciparum force of infection was higher in the eastern region and increased between August and November, whilst P. vivax force of infection was higher in the western region and remained similar in both surveys. In the western region, malaria transmission changed very little across the season (for both species). CART analysis for P. falciparum in the east highlighted age, ethnicity, village of residence and forest work as important predictors for malaria exposure during the rainy season. Adults were more likely to increase their antibody responses to P. falciparum during the transmission season than children, whilst members of the Charay ethnic group demonstrated the largest increases. Discussion: In areas of low transmission intensity, such as in Cambodia, the analysis of longitudinal serological data enables a sensitive evaluation of transmission dynamics. Consecutive serological surveys allow an insight into spatio-temporal patterns of malaria transmission. The use of CART enabled multiple interactions to be accounted for simultaneously and permitted risk factors for exposure to be clearly identified.

The impact of psychiatric diagnosis on treatment adherence and duration among victimized children and adolescents in São Paulo, Brazil

OBJECTIVE: Despite the high prevalence of substance abuse and mood disorders among victimized children and adolescents, few studies have investigated the association of these disorders with treatment adherence, represented by numbers of visits per month and treatment duration. We aimed to investigate the effects of substance abuse and mood disorders on treatment adherence and duration in a special program for victimized children in São Paulo, Brazil. METHODS: A total of 351 participants were evaluated for psychiatric disorders and classified into one of five groups: mood disorders alone; substance abuse disorders alone; mood and substance abuse disorders; other psychiatric disorders; no psychiatric disorders. The associations between diagnostic classification and adherence to treatment and the duration of program participation were tested with logistic regression and survival analysis, respectively. RESULTS: Children with mood disorders alone had the highest rate of adherence (79.5%); those with substance abuse disorders alone had the lowest (40%); and those with both disorders had an intermediate rate of adherence (50%). Those with other psychiatric disorders and no psychiatric disorders also had high rates of adherence (75.6% and 72.9%, respectively). Living with family significantly increased adherence for children with substance abuse disorders but decreased adherence for those with no psychiatric disorders. The diagnostic correlates of duration of participation were similar to those for adherence. CONCLUSIONS: Mood and substance abuse disorders were strong predictive factors for treatment adherence and duration, albeit in opposite directions. Living with family seems to have a positive effect on treatment adherence for patients with substance abuse disorders. More effective treatment is needed for victimized substance-abusing youth

CID: an efficient complexity-invariant distance for time series

The ubiquity of time series data across almost all human endeavors has produced a great interest in time series data mining in the last decade. While dozens of classification algorithms have been applied to time series, recent empirical evidence strongly suggests that simple nearest neighbor classification is exceptionally difficult to beat. The choice of distance measure used by the nearest neighbor algorithm is important, and depends on the invariances required by the domain. For example, motion capture data typically requires invariance to warping, and cardiology data requires invariance to the baseline (the mean value). Similarly, recent work suggests that for time series clustering, the choice of clustering algorithm is much less important than the choice of distance measure used.In this work we make a somewhat surprising claim. There is an invariance that the community seems to have missed, complexity invariance. Intuitively, the problem is that in many domains the different classes may have different complexities, and pairs of complex objects, even those which subjectively may seem very similar to the human eye, tend to be further apart under current distance measures than pairs of simple objects. This fact introduces errors in nearest neighbor classification, where some complex objects may be incorrectly assigned to a simpler class. Similarly, for clustering this effect can introduce errors by “suggesting” to the clustering algorithm that subjectively similar, but complex objects belong in a sparser and larger diameter cluster than is truly warranted.We introduce the first complexity-invariant distance measure for time series, and show that it generally produces significant improvements in classification and clustering accuracy. We further show that this improvement does not compromise efficiency, since we can lower bound the measure and use a modification of triangular inequality, thus making use of most existing indexing and data mining algorithms. We evaluate our ideas with the largest and most comprehensive set of time series mining experiments ever attempted in a single work, and show that complexity-invariant distance measures can produce improvements in classification and clustering in the vast majority of cases.