%0 Journal Article %1 Stack2013 %A Stack, Catharine B %A Localio, A Russell %A Griswold, Michael E %A Goodman, Steven N %A Mulrow, Cynthia D %D 2013 %J Annals of internal medicine %K DataInterpretation DiabetesMellitus Humans HypoglycemicAgents HypoglycemicAgents:therapeuticuse Meta-AnalysisasTopic PatientDropouts ResearchDesign ResearchDesign:standards ResearchDesign:statistics&numericaldata SensitivityandSpecificity Sodium-GlucoseTransporter2 Sodium-GlucoseTransporter2:antagonists&inhibi Statistical Type2 Type2:drugtherapy %N 4 %P 285-8 %R 10.7326/0003-4819-159-4-201308200-00009 %T Handling of rescue and missing data affects synthesis and interpretation of evidence: the sodium-glucose cotransporter 2 inhibitor example. %U http://dx.doi.org/10.7326/0003-4819-159-4-201308200-00009 http://www.ncbi.nlm.nih.gov/pubmed/24026261 %V 159 %X Confidence in evidence summarized in meta-analyses depends on the strength of the underlying studies. This inherent limitation of syntheses appears in the case of a meta-analysis of sodium-glucose cotransporter 2 inhibitors for the treatment of type 2 diabetes because many of the pertinent randomized trials did not handle patient dropout and "rescue" medication properly. Repudiated statistical methods, such as last observation carried forward, and unsophisticated methods for handling postrescue data produce unreliable summary estimates. Future reports of randomized studies and meta-analyses of those studies must focus on posing precise questions about the treatment effect of interest and then implement appropriate statistical methods to account for missing data, patient dropout, and use of rescue medication.

@article{Stack2013, abstract = {Confidence in evidence summarized in meta-analyses depends on the strength of the underlying studies. This inherent limitation of syntheses appears in the case of a meta-analysis of sodium-glucose cotransporter 2 inhibitors for the treatment of type 2 diabetes because many of the pertinent randomized trials did not handle patient dropout and "rescue" medication properly. Repudiated statistical methods, such as last observation carried forward, and unsophisticated methods for handling postrescue data produce unreliable summary estimates. Future reports of randomized studies and meta-analyses of those studies must focus on posing precise questions about the treatment effect of interest and then implement appropriate statistical methods to account for missing data, patient dropout, and use of rescue medication.}, added-at = {2023-02-03T11:44:35.000+0100}, author = {Stack, Catharine B and Localio, A Russell and Griswold, Michael E and Goodman, Steven N and Mulrow, Cynthia D}, biburl = {https://www.bibsonomy.org/bibtex/24271a2421e99889e898b4318d9060554/jepcastel}, doi = {10.7326/0003-4819-159-4-201308200-00009}, interhash = {a6e25637ca8844244c18cfd37c5d764f}, intrahash = {4271a2421e99889e898b4318d9060554}, issn = {1539-3704}, journal = {Annals of internal medicine}, keywords = {DataInterpretation DiabetesMellitus Humans HypoglycemicAgents HypoglycemicAgents:therapeuticuse Meta-AnalysisasTopic PatientDropouts ResearchDesign ResearchDesign:standards ResearchDesign:statistics&numericaldata SensitivityandSpecificity Sodium-GlucoseTransporter2 Sodium-GlucoseTransporter2:antagonists&inhibi Statistical Type2 Type2:drugtherapy}, month = {8}, note = {Metaanàlisi}, number = 4, pages = {285-8}, pmid = {24026261}, timestamp = {2023-02-03T11:44:35.000+0100}, title = {Handling of rescue and missing data affects synthesis and interpretation of evidence: the sodium-glucose cotransporter 2 inhibitor example.}, url = {http://dx.doi.org/10.7326/0003-4819-159-4-201308200-00009 http://www.ncbi.nlm.nih.gov/pubmed/24026261}, volume = 159, year = 2013 }