University of Iowa

About: University of Iowa is a education organization based out in Iowa City, Iowa, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 49229 authors who have published 109171 publications receiving 5021465 citations. The organization is also known as: UI & The University of Iowa.

A streaming ensemble algorithm (SEA) for large-scale classification

Abstract: Ensemble methods have recently garnered a great deal of attention in the machine learning community. Techniques such as Boosting and Bagging have proven to be highly effective but require repeated resampling of the training data, making them inappropriate in a data mining context. The methods presented in this paper take advantage of plentiful data, building separate classifiers on sequential chunks of training points. These classifiers are combined into a fixed-size ensemble using a heuristic replacement strategy. The result is a fast algorithm for large-scale or streaming data that classifies as well as a single decision tree built on all the data, requires approximately constant memory, and adjusts quickly to concept drift.

Menopausal Hormone Therapy and Health Outcomes During the Intervention and Extended Poststopping Phases of the Women’s Health Initiative Randomized Trials

Abstract: RESULTS During the CEE plus MPA intervention phase, the numbers of CHD cases were 196 for CEE plus MPA vs 159 for placebo (hazard ratio [HR], 1.18; 95% CI, 0.95-1.45) and 206 vs 155, respectively, for invasive breast cancer (HR, 1.24; 95% CI, 1.01-1.53). Other risks included increased stroke, pulmonary embolism, dementia (in women aged65 years), gallbladder disease, and urinary incontinence; benefits included decreased hip fractures, diabetes, and vasomotor symptoms. Most risks and benefits dissipated postintervention, although some elevation in breast cancer risk persisted during cumulative follow-up (434 cases for CEE plus MPA vs 323 for placebo; HR, 1.28 [95% CI, 1.11-1.48]). The risks and benefits were more balanced during the CEE alone intervention with 204 CHD cases for CEE alone vs 222 cases for placebo (HR, 0.94; 95% CI, 0.781.14) and 104 vs 135, respectively, for invasive breast cancer (HR, 0.79; 95% CI, 0.61-1.02); cumulatively, there were 168 vs 216, respectively, cases of breast cancer diagnosed (HR, 0.79; 95% CI, 0.65-0.97). Results for other outcomes were similar to CEE plus MPA. Neither regimen affected all-cause mortality. For CEE alone, younger women (aged 50-59 years) had more favorable results for all-cause mortality, myocardial infarction, and the global index (nominal P < .05 for trend by age). Absolute risks of adverse events (measured by the global index) per 10 000 women annually taking CEE plus MPA ranged from 12 excess cases for ages of 50-59 years to 38 for ages of 70-79 years; for women taking CEE alone, from 19 fewer cases for ages of 50-59 years to 51 excess cases for ages of 70-79 years. Quality-of-life outcomes had mixed results in both trials. CONCLUSIONS AND RELEVANCE Menopausal hormone therapy has a complex pattern of risks and benefits. Findings from the intervention and extended postintervention follow-up of the 2 WHI hormone therapy trials do not support use of this therapy for chronic disease prevention, although it is appropriate for symptom management in some women.

Genome Scan Meta-Analysis of Schizophrenia and Bipolar Disorder, Part II: Schizophrenia

Abstract: Schizophrenia is a common disorder with high heritability and a 10-fold increase in risk to siblings of probands. Replication has been inconsistent for reports of significant genetic linkage. To assess evidence for linkage across studies, rank-based genome scan meta-analysis (GSMA) was applied to data from 20 schizophrenia genome scans. Each marker for each scan was assigned to 1 of 120 30-cM bins, with the bins ranked by linkage scores (1 = most significant) and the ranks averaged across studies (R(avg)) and then weighted for sample size (N(sqrt)[affected casess]). A permutation test was used to compute the probability of observing, by chance, each bin's average rank (P(AvgRnk)) or of observing it for a bin with the same place (first, second, etc.) in the order of average ranks in each permutation (P(ord)). The GSMA produced significant genomewide evidence for linkage on chromosome 2q (PAvgRnk<.000417). Two aggregate criteria for linkage were also met (clusters of nominally significant P values that did not occur in 1,000 replicates of the entire data set with no linkage present): 12 consecutive bins with both P(AvgRnk) and P(ord)<.05, including regions of chromosomes 5q, 3p, 11q, 6p, 1q, 22q, 8p, 20q, and 14p, and 19 consecutive bins with P(ord)<.05, additionally including regions of chromosomes 16q, 18q, 10p, 15q, 6q, and 17q. There is greater consistency of linkage results across studies than has been previously recognized. The results suggest that some or all of these regions contain loci that increase susceptibility to schizophrenia in diverse populations.