|
| ||
|
|
||
Birth Data (birth + data)
Selected AbstractsCoping With Missing Attribute Values Based on Closest Fit in Preterm Birth Data: A Rough Set ApproachCOMPUTATIONAL INTELLIGENCE, Issue 3 2001Jerzy W. Grzymala-Busse Data mining is frequently applied to data sets with missing attribute values. A new approach to missing attribute values, called closest fit, is introduced in this paper. In this approach, for a given case (example) with a missing attribute value we search for another case that is as similar as possible to the given case. Cases can be considered as vectors of attribute values. The search is for the case that has as many as possible identical attribute values for symbolic attributes, or as the smallest possible value differences for numerical attributes. There are two possible ways to conduct a search: within the same class (concept) as the case with the missing attribute values, or for the entire set of all cases. For comparison, we also experimented with another approach to missing attribute values, where the missing values are replaced by the most common value of the attribute for symbolic attributes or by the average value for numerical attributes. All algorithms were implemented in the system OOMIS. Our experiments were performed on the preterm birth data sets provided by the Duke University Medical Center. [source] Preterm birth but not mode of delivery is associated with an increased risk of developing inflammatory bowel disease later in lifeINFLAMMATORY BOWEL DISEASES, Issue 11 2007Barbara Sonntag MD Abstract Background: Exposure to bacterial antigens and other environmental factors in combination with a genetic susceptibility have been implicated in the etiology of inflammatory bowel disease (IBD). As certain perinatal circumstances, e.g., delivery by cesarean section, predispose to a different intestinal colonizations the aim of this analysis was to define a potential influence on the development of IBD in later life. Methods: In a case-control study design, birth data were recorded from patients diagnosed with IBD (Crohn's disease [CD], n = 1096; ulcerative colitis [UC], n = 763) and healthy controls ([C], n = 878) by a self-administered questionnaire. Results: Preterm birth (CD: odds ratio [OR] 1.5 [95% confidence interval 1.1,2.0], UC: OR 1.3 [0.9,1.9]), mother's disease during pregnancy (CD: OR 1.9 [1.3,2.9], UC: OR 1.6 [1.0,2.4]), and disease in the first year of life (CD: OR 2.2 [1.6,2.9], UC: OR 1.7 [1.3,2.3]) are associated with the development of IBD in later life. No significant associations were found for the mode of delivery and breast feeding. In a logistic regression analysis female sex, smoking, appendectomy, maternal IBD, and disease in the first year of life were independently associated with CD. Female sex, appendectomy, and disease in the first year of life were independently associated with UC. Conclusions: Preterm birth and other perinatal circumstances are associated with the development of IBD, of which disease in the first year of life is an independent risk factor in multivariate analysis. (Inflamm Bowel Dis 2007) [source] A comparison of three closest fit approaches to missing attribute values in preterm birth dataINTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 2 2002Jerzy W. Grzymala-Busse One of the main problems of data mining is imperfection of input data. Such data may be uncertain, vague, and incomplete. In our data set, describing preterm birth, many attribute values were missing, that is, the input data set was incomplete. The main approach to solving the missing attribute value problem was based on a closest fit: a missing attribute value in a case was replaced by the existing attribute value in the best candidate, a case that fits as closely as possible (resembles the most) the case with the missing attribute value. We experimented with three methods based on the idea of the closest fit: looking for the best candidate among the set of all cases, among the cases that belong to the same concept (cases within the same class as the case with missing attribute values), and a special method, where the set of all attributes was restricted to a single attribute with the missing attribute value. In the last method, the missing attribute value was replaced by the most common value within the concept for symbolic attributes, and by the average value of all attribute values of the same concept for numerical attributes. © 2002 John Wiley & Sons, Inc. [source] Human birth seasonality and sunshineAMERICAN JOURNAL OF HUMAN BIOLOGY, Issue 3 2010David R. CummingsArticle first published online: 20 OCT 200 The environmental light intensity/photoperiod (ELI/PP) hypothesis proposes that the seasonality of human births is primarily associated with seasonal changes in ambient atmospheric luminosity or ELI. This study tests for the presence of increased ELI during the 1 or 2-month period preceding the conceptual month. Monthly birth data for Helsinki, Finland; Kiev, Ukraine; Hanoi, Vietnam; Matlab, Bangladesh; Nashville, Tennessee; Los Angeles, California; Dallas, Texas; Denver, Colorado and Pretoria, South Africa, are correlated (Pearsonian r) to corresponding monthly meteorological data. With the exception of Matlab, birth data are adjusted for conception date, 31-day months, leap years and monthly deviation from an annual mean. Meteorological data are adjusted for a 1,2-month exposure to ELI before conception. From these correlations, Helsinki r = 0.82, Kiev r = 0.80, Hanoi r = 0.93, Matlab r = 0.91, Nashville r = 0.84, Los Angeles r = 0.71, Dallas r = 0.86, Denver r = 0.53, and Pretoria r = ,82. Weakness and strengths of the ELI/PP hypothesis are reviewed using the criteria developed by AB Hill. Substituting meteorological variables for ELI may be a weakness, whereas the specificity of ELI/PP predictions may be a strength. Increased periods of ELI precede increased periods of conceptions. Increased ELI may influence seasonality for chimpanzee, baboon, and humans. Atmospheric pollution may alter the onset of seasonality. Increased ELI may be the initial, but not the singular variable to affect seasonality. Am. J. Hum. Biol., 2010. © 2009 Wiley-Liss, Inc. [source] The differential effect of foreign-born status on preterm birth: a Taiwan population-based birth registry studyBJOG : AN INTERNATIONAL JOURNAL OF OBSTETRICS & GYNAECOLOGY, Issue 8 2007L-C See Whether foreign-born status confers a protective effect on preterm birth in Taiwan was investigated using singleton live birth data from the 2004 Taiwan Birth Registry (n= 211 946). Newborns of foreign-born mothers (FBMs) comprised 13.7% of the population. The preterm birth rate of newborns of FBMs (5.9%) was significantly lower than that of newborns of Taiwan-born mothers (TBMs) (8.0%) (P < 0.0001). After having adjusted for predisposing maternal factors or adverse pregnancy conditions, newborns of FBMs still had a lower risk in preterm birth than that of TBMs, with an odds ratio of 0.74 and 95% confidence interval between 0.71 and 0.79. Selection was hypothesised to explain the low preterm birth rate in FBMs. [source] Optic nerve hypoplasia in North America: a re-appraisal of perinatal risk factorsACTA OPHTHALMOLOGICA, Issue 5 2010Pamela Garcia-Filion Abstract. Purpose:, The purpose of this study is to describe and clarify the birth and prenatal characteristics of a large cohort of children with optic nerve hypoplasia. Methods:, This is a descriptive report of 204 patients aged , 36 months and enrolled in a prospective study at the Children's Hospital Los Angeles. Birth characteristics, including complications, were abstracted from study files and medical records. Systematic maternal interviews were conducted to obtain detailed prenatal histories. National birth data were used for comparison with birth findings. Results:, Birth characteristics were unremarkable for birthweight and gestation, but significant for increased frequency of caesarean delivery and fetal and neonatal complications. Young maternal age and primaparity were dominating maternal features. Preterm labour, gestational vaginal bleeding, low maternal weight gain and weight loss during pregnancy were prevalent. Conclusions:, These findings confirm young maternal age and primaparity as associated risk factors, challenge many other suggested factors such as alcohol and drug abuse, and introduce potentially significant prenatal characteristics such as maternal weight loss and early gestational vaginal bleeding as aetiological correlates. [source] | |||||||||||||