Recently, instrumental variables methods have been used to address non-compliance in randomized experiments. Complicating such analyses is often the presence of missing data. The standard model for missing data, missing at random (MAR), has some unattractive features in this context. In this paper we compare MAR-based estimates of the complier average causal effect (CACE) with an estimator based on an alternative, nonignorable model for the missing data process, developed by Frangakis and Rubin (1999, Biometrika, 86, 365-379). We also introduce a new missing data model that, like the Frangakis-Rubin model, is specially suited for models with instrumental variables, but makes different substantive assumptions. We analyze these issues in the context of a randomized trial of breast self-examination (BSE). In the study two methods of teaching BSE, consisting of either mailed information about BSE (the standard treatment) or the attendance of a course involving theoretical and practical sessions (the new treatment), were compared with the aim of assessing whether teaching programs could increase BSE practice and improve examination skills. The study was affected by the two sources of bias mentioned above: only 55% of women assigned to receive the new treatment complied with their assignment and 35% of the women did not respond to the post-test questionnaire. Comparing the causal estimand of the new treatment using the MAR, Frangakis-Rubin, and our new approach, the results suggest that for these data the MAR assumption appears least plausible, and that the new model appears most plausible among the three choices.
To evaluate the impact of parental smoking on childhood asthma and wheezing, we studied two random samples of subjects ages 6-7 and 13-14 years in ten areas of northern and central Italy. Standardized questionnaires were completed by parents of 18,737 children and 21,068 adolescents (response rates, 92.8% and 96.3%, respectively) about their smoking habits and the respiratory health of their children. Adolescents were asked about their respiratory health and personal smoking. We compared two groups of cases with healthy subjects: (1) "current asthma" (children, 5.2%; adolescents, 6.2%) and (2) "current wheezing" not labeled as asthma (children = 4.5%, adolescents = 8.5%). Exposure to smoke of at least one parent increased the relative risk of current asthma among children [odds ratio (OR) = 1.34; 95% confidence interval (CI) = 1.11-1.62] and of current wheezing among adolescents (OR = 1.24; 95% CI = 1.07-1.44). Maternal smoking had a stronger effect than paternal smoking. Maternal smoking during pregnancy was associated with current asthma (OR = 1.62; 95% CI = 1.34-1.96) and current wheezing in children (OR = 1.31; 95% CI = 1.06-1.62); the effects were lower among adolescents. Among subjects with a negative history of parental asthma, maternal smoking was associated with current wheezing in both age groups, whereas among those with a positive history of parental asthma it was associated with current asthma in children, but not in adolescents. We estimated that 15% (95% CI = 12-19) of the current asthma cases among children and 11% (95% CI = 8.3-14) of the current wheezing cases among adolescents are attributable to parental smoking in Italy.
Our objective was to verify and expand previous evidence of psychometric inadequacies in the ALSFRS-R, in a different sample of subjects suffering from ALS. Since 2009, a prospective registry records all incident cases of ALS in Emilia Romagna Region, Italy (4.4 million inhabitants) referred to its 17 neurological departments. For each patient, demographic and clinical information is collected by the physician in charge, including compilation of the ALSFRS-R at each clinical follow-up. Results showed that a confirmatory factor analysis on the three-factor model previously found (bulbar, motor, respiratory function) showed a good fit. Rasch analysis on the whole scale showed the need to collapse some rating categories, confirmed the multidimensionality of the ALSFRS-R, and demonstrated the presence of differential item functioning between patients with spinal versus bulbar onset. Moreover, some items included in the three ALSFRS-R subscales showed a problematic fit to the respective construct they were intended to measure. In conclusion, the interpretation of a total raw score of ALSFRS-R is hampered by ambiguities due to the different metric properties of the three domains the scale aggregates, and their content and structure. This study confirms that a refinement of ALSFRS-R is warranted, pointing to the need to revise its whole structure, and providing detailed guidelines for its revision.
Guidelines for management of patients with myelodysplastic syndromes (MDS) have been generated by the National Comprehensive Cancer Network (NCCN) Myelodysplastic Syndromes Panel. Because MDS is a heterogeneous spectrum of disorders, these patients have been categorized into prognostic subgroups, predominantly using the International Prognostic Scoring System (IPSS). Several drugs have been used to treat these patients, and their selection and sequential recommended use by the panel depend on disease characteristics and responses to treatment. Recombinant erythropoietin alfa and darbepoetin alfa have been the mainstay of therapy for treating anemia associated with MDS. The FDA has recently approved several other drugs for treating MDS, including azacytidine and decitabine for all stages of disease, lenalidomide for low-risk anemic patients with del(5q) chromosomal abnormality, and deferasirox for treating iron overload. For iron chelation, deferoxamine is also used occasionally. Treatment with immunosuppressive therapy (antithymocyte globulin and cyclosporin) has been therapeutically beneficial for a subset of younger patients with MDS. Because the financial cost of these therapies are substantial and have received only limited attention, this article evaluates the costs of specific drugs and their sequential use in the lower-risk IPSS (low and intermediate-1) subgroups based on the NCCN guidelines. Results estimate an average annual cost for potentially anemia-altering drugs of $63,577 per patient, ranging from $26,000 to $95,000, depending on the specific therapies. In patients for whom the therapies fail, annual costs for iron chelation plus red blood cell transfusions are estimated to average $41,412. The economic impact of drug therapy should be weighed against the patient's potential for improvement in clinical outcomes, quality of life, and transfusion requirements.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.