Biomedical subjects

Eric Leifer

Publications and source records attributed to Eric Leifer.

3 recordsLinked to original sources

PubMed2003

A statistical method for adjusting covariates in linkage analysis with sib pairs.

BACKGROUND: We propose a statistical method that includes the use of longitudinal regression models and estimation procedures for adjusting for covariate effects in applying the Haseman-Elston (HE) method for linkage analysis. Our methodology, which uses the covariate adjusted trait, contains three steps: a) modelling the covariate-adjusted population means of quantitative traits through regression; b) estimating the value of covariate-adjusted quantitative traits; and c) evaluating the linkage between the adjusted trait values and the markers based on alleles shared identically by descent. RESULTS: We applied our adjusted HE method and the standard HE method in S.A.G.E. to the sib-pair subset of the Framingham Heart Study distributed by Genetic Analysis Workshop 13 with systolic blood pressure as the quantitative trait. Both methods gave similar patterns for the LOD scores, and exhibited highest multipoint LOD scores near location 70 cM of chromosome 12. CONCLUSION: The adjusted HE method has two major advantages over the standard HE method used in S.A.G.E.: a) it has the capability to handle longitudinal data; b) it provides a more natural approach for adjusting the repeatedly measured covariates from each subject.

Age Factors↗

PubMed2003

Multiple outputation: inference for complex clustered data by averaging analyses from independent data.

This article applies a simple method for settings where one has clustered data, but statistical methods are only available for independent data. We assume the statistical method provides us with a normally distributed estimate, theta, and an estimate of its variance sigma. We randomly select a data point from each cluster and apply our statistical method to this independent data. We repeat this multiple times, and use the average of the associated theta's as our estimate. An estimate of the variance is given by the average of the sigma2's minus the sample variance of the theta's. We call this procedure multiple outputation, as all "excess" data within each cluster is thrown out multiple times. Hoffman, Sen, and Weinberg (2001, Biometrika 88, 1121-1134) introduced this approach for generalized linear models when the cluster size is related to outcome. In this article, we demonstrate the broad applicability of the approach. Applications to angular data, p-values, vector parameters, Bayesian inference, genetics data, and random cluster sizes are discussed. In addition, asymptotic normality of estimates based on all possible outputations, as well as a finite number of outputations, is proven given weak conditions. Multiple outputation provides a simple and broadly applicable method for analyzing clustered data. It is especially suited to settings where methods for clustered data are impractical, but can also be applied generally as a quick and simple tool.

Acute Disease↗

PubMed2002

Antithymocyte globulin for treatment of the bone marrow failure associated with myelodysplastic syndromes.

BACKGROUND: Almost half of the deaths that result from myelodysplastic syndromes are due to cytopenia associated with bone marrow failure. Treatment is mostly supportive care. OBJECTIVE: To determine whether treatment with antithymocyte globulin improves cytopenia and reverses dependence on red blood cell transfusions in patients with myelodysplastic syndromes. DESIGN: Single-treatment, prospective study. SETTING: Tertiary referral center. PATIENTS: 61 patients with myelodysplastic syndromes. INTERVENTION: Antithymocyte globulin, 40 mg/kg of body weight, given daily for 4 days. MEASUREMENTS: Evaluation of bone marrow, blood counts, transfusions, progression, and survival for a median of 30 months (range, 1 to 88 months). RESULTS: Within 8 months of treatment, 21 of 61 patients (34%) no longer required red blood cell transfusions. This independence from transfusions was maintained in 17 responders (81%) for a median of 36 months (range, 3 to 72 months). Ten of 21 patients (47.5%) with severe thrombocytopenia had sustained platelet count increases, and 6 of 11 patients (55%) with severe neutropenia had sustained neutrophil counts of greater than 1 x 10(9) cells/L. Characteristics favorable for response were younger patient age (P = 0.005) and lower platelet counts (P = 0.038). One of the 21 responders (5%) and 22 of the 40 nonresponders (55%) died before the end of the study (P = 0.008). One of the 21 responders (5%) and 13 of the 40 nonresponders (33%) had disease progression (P = 0.086). CONCLUSIONS: Although this study was a nonrandomized, single-treatment study, 34% of patients treated with antithymocyte globulin became transfusion independent. Response was associated with a statistically significant longer survival and an almost significant decreased time to disease progression. Treatment with antithymocyte globulin did not seem to be detrimental because historical overall median survival times were similar to those of nonresponders.

Adult↗