Evaluation of Bayesian classifiers in asthma exacerbation prediction after medication discontinuation.

OBJECTIVE: The achievement of the optimal control of the disease is of cardinal importance in asthma treatment. As the control of the disease is sustained the medication should be gradually reduced and then stopped. Nevertheless, the discontinuation of asthma medication may lead to loss of disease control and eventually to an exacerbation of the disease. The goal of this paper is to examine the performance of Bayesian network classifiers in predicting asthma exacerbation based on several patient's parameters such as objective measurements and medical history data. RESULTS: In this study several Bayesian network classifiers are presented and evaluated. It is shown that the proposed semi-naive network classifier with the use of Backward Sequential Elimination and Joining algorithm is able to predict if a patient will have an exacerbation of the disease after his last assessment with 93.84% accuracy and 90.9% sensitivity. In addition, the resulting structure and the conditional probability tables give a clear view of the probabilistic relationships between the used factors. This network may help the clinicians to identify the patients who are at high risk of having an exacerbation after stopping the medication and to confirm which factors are the most important.

The presence of asthma, the use of inhaled steroids, and parental education level affect school performance in children.

OBJECTIVE: Childhood asthma is a frequent cause of absenteeism that affects school performance. We aimed to investigate the impact of asthma on absenteeism and school performance level of elementary and high school students. METHODS: Data about sociodemographics, absenteeism, and academic achievement were obtained from 1539 students attending 98 schools in Greece. School performance was assessed for the last two years of school attendance using parents' and teachers' reports and grade point average promotion. RESULTS: The mean of the days of absence of students with asthma was higher compared to the healthy students (6.2 ± 11.7 versus 0.3 ± 3.1, resp., P < 0.001). Students with reduced healthcare use presented less absenteeism than those with increased healthcare use for asthma (4.3 ± 8.6 versus 12.4 ± 17.0 days, resp., P < 0.001). Asthma and healthcare use for asthma accounted for an overall estimated variability in absence days of 13.8% and 9%, respectively. Absenteeism was associated with poor school performance for the last two years of school (P = 0.002) and with lower grade point promotion in elementary school students (P = 0.001) but not in high school students (P = 0.316). Higher level of parental education was associated with better school performance (P < 0.001). Asthma was associated with a decreased possibility for excellent performance (OR = 0.64, P = 0.049, 95%CI = 0.41-1.00) in elementary students. Students with asthma using inhalers were four times more likely to perform excellently in elementary school (OR = 4.3, P = 0.028, 95%CI = 1.17-15.95) than their asthmatic peers with alternative asthma treatments. Conclusions. Asthma and increased healthcare use enhance school absenteeism. Inhaled steroid use and the higher parental education level were the most important predicting factors for good school performance in elementary school asthmatic children.

An intelligent system approach for asthma prediction in symptomatic preschool children.

OBJECTIVES: In this study a new method for asthma outcome prediction, which is based on Principal Component Analysis and Least Square Support Vector Machine Classifier, is presented. Most of the asthma cases appear during the first years of life. Thus, the early identification of young children being at high risk of developing persistent symptoms of the disease throughout childhood is an important public health priority. METHODS: The proposed intelligent system consists of three stages. At the first stage, Principal Component Analysis is used for feature extraction and dimension reduction. At the second stage, the pattern classification is achieved by using Least Square Support Vector Machine Classifier. Finally, at the third stage the performance evaluation of the system is estimated by using classification accuracy and 10-fold cross-validation. RESULTS: The proposed prediction system can be used in asthma outcome prediction with 95.54 % success as shown in the experimental results. CONCLUSIONS: This study indicates that the proposed system is a potentially useful decision support tool for predicting asthma outcome and that some risk factors enhance its predictive ability.

Safety considerations in the management of allergic diseases: focus on antihistamines.

OBJECTIVE: To conduct a systematic review of evidence supporting the safety profiles of frequently used oral H(1)-antihistamines (AHs) for the treatment of patients with histamine-release related allergic diseases, e.g. allergic rhinitis and urticaria, and to compare them to the safety profiles of other medications, mostly topical corticosteroids and leukotriene antagonists (LTRA). RESEARCH DESIGN AND METHODS: Systematic search of the published literature (PubMed) and of the regulatory authorities databases (EMA and FDA) for oral AHs. RESULTS: Similarly to histamine, antihistamines (AHs) have organ-specific efficacy and adverse effects. The peripheral H(1)-receptor (PrH1R) stimulation leads to allergic symptoms while the brain H(1)-receptor (BrH1R) blockade leads to somnolence, fatigue, increased appetite, decreased cognitive functions (impaired memory and learning), seizures, aggressive behaviour, etc. First-generation oral AHs (FGAHs) inhibit the effects of histamine not only peripherally but also in the brain, and additionally have potent antimuscarinic, anti-α-adrenergic and antiserotonin effects leading to symptoms such as visual disturbances (mydriasis, photophobia, and diplopia), dry mouth, tachycardia, constipation, urinary retention, agitation, and confusion. The somnolence caused by FGAHs interferes with the natural circadian sleep-wake cycle and therefore FGAHs are not suitable to be used as sleeping pills. Second-generation oral AHs (SGAHs) have proven better safety and tolerability profiles, much lower proportional impairment ratios, with at least similar if not better efficacy, than their predecessors. Only SGAHs, and especially those with a proven long-term (e.g., ≥12 months) clinical safety, should be prescribed for young children. Evidence exist that intranasally applied medications, like intranasal antihistamines, have the potential to reach the brain and cause somnolence. CONCLUSIONS: Second-generation oral antihistamines are the preferred first-line treatment option for allergic rhinitis and urticaria. Patients taking SGAHs report relatively little and mild adverse events even after long-term continuous treatments. An antihistamine should ideally possess high selectivity for the H(1)-receptor, high PrH1R occupancy and low to no BrH1R occupancy.

Microsatellite DNA instability and loss of heterozygosity in bronchial asthma.

Genetic alterations, such as loss of heterozygosity (LOH) or microsatellite instability (MI), have been reported in both malignant and benign disorders. In order to identify loci of deoxyribonucleic acid (DNA) mutation in asthma, MI and LOH were studied in sputum cells. DNA was extracted from cells in the sputum and blood cells of 22 patients with moderate asthma. Cells were analysed for MI and LOH using 18 polymorphic markers on chromosome 5q, 6p, 11q, 14q. Microsatellite analysis was also performed in six healthy subjects. None of the healthy individuals exhibited any genetic alteration. Genetic alterations were found in 16 of 22 asthmatic patients (73%). In total, 12 (54.5%) patients exhibited LOH only, one (4.5%) MI only, while three showed both MI and LOH. The highest incidence of LOH and MI was found on chromosome 14q. Mean immunoglobulin E and blood eosinophil levels were significantly higher in asthmatics with three or more genetic alterations. A high incidence of genetic alterations in the deoxyribonucleic acid of the sputum cells was found in asthmatic patients. Further studies are needed to identify the role of loss of heterozygosity and microsatellite instability in the investigation of genetic susceptibility of asthma and thus, in its pathogenesis.

Epidemiology of childhood type I diabetes in Crete, 1990-2001.

AIM: To study the epidemiological patterns of childhood-onset type I diabetes in Crete, Greece. METHODS: The incidence (new cases per 100,000 per year) from 1990 to 2001 was determined in the population of Crete < or = 14 y of age. RESULTS: A total of 89 cases was ascertained. The standardized annual incidence rate was 6.1 per 100,000 population [95% confidence interval (95% CI) 4.9-7.5]. Incidence rates were higher in children 10-14 y of age, boys and residents of urban areas (6.8, 6.7 and 6.6 per 100,000, respectively). Incidence rates were higher [relative risk (RR) 1.46, 95% CI 0.956-2.24] during the 6 y period 1996-2001 (7.2, 95% CI 5.4-9.4) than during the 6 y period 1990-1995 (4.9, 95% CI 3.4-6.9). This increase was more prominent in residents of urban areas and 10-14-y-old children. CONCLUSIONS: Although an increase was noted during the period 1990-2001, the childhood type I diabetes incidence rates in Crete remain among the lowest both in Europe and in the Mediterranean islands.

Mucus plugging as a cause of acute lobar overdistension.

Acute lobar overdistension in children is usually indicative of foreign body aspiration, especially when a history of a choking episode is recalled. An unusual presentation of asthma as recurrent overdistension of the left lung in a toddler is described. The child had undergone two consecutive negative bronchoscopies with a presumptive diagnosis of foreign body aspiration; however, it was only the antiasthmatic treatment that resulted in an excellent outcome.