Jordi Cortés1, José A González2, Michael J Campbell3, Erik Cobo2. 1. Department of Statistics and Operations Research, UPC BarcelonaTech, 31 Jordi Girona St, Barcelona, Spain. Electronic address: jordicortes40@gmail.com. 2. Department of Statistics and Operations Research, UPC BarcelonaTech, 31 Jordi Girona St, Barcelona, Spain. 3. Design, Trials & Statistics, School of Health and Related Research, The University of Sheffield, Regent Court 30 Regent Street, Sheffield S1 4DA, UK.
Abstract
OBJECTIVES: To evaluate the empirical concordance between the hazard ratio (HR) and the median ratio (MR) in survival cancer studies. STUDY DESIGN AND SETTING: We selected all cancer survival articles from the New England Journal of Medicine published between 2000 and 2010. The qualitative concordance was estimated by the proportion of measured pairs in which the treatment effects for the MR and HR are in the same direction. The quantitative concordance was assessed through (1) the mean difference between the logarithms of the measures, (2) the Lin coefficient, and (3) the Bland-Altman plot. RESULTS: We retrieved 106 measured pairs (HR-MR) corresponding to 54 articles. Concordance was high, at both the qualitative (99 of 106, 93.4%) and quantitative levels (mean MR-to-HR ratio, 1.01; 95% confidence interval: 0.95, 1.06). However, the 95% Bland-Altman discordance limits indicate that the MR can be up to 50% higher or 50% lower than the HR. CONCLUSION: The average concordance allows trialists to approximate HR from MR to determine sample size. However, the discordance limits are too great to consider that both measures are interchangeable. The actual policy to report HR only is not enough. Our results emphasize the need to attach descriptive survival measures to the HR.
OBJECTIVES: To evaluate the empirical concordance between the hazard ratio (HR) and the median ratio (MR) in survival cancer studies. STUDY DESIGN AND SETTING: We selected all cancer survival articles from the New England Journal of Medicine published between 2000 and 2010. The qualitative concordance was estimated by the proportion of measured pairs in which the treatment effects for the MR and HR are in the same direction. The quantitative concordance was assessed through (1) the mean difference between the logarithms of the measures, (2) the Lin coefficient, and (3) the Bland-Altman plot. RESULTS: We retrieved 106 measured pairs (HR-MR) corresponding to 54 articles. Concordance was high, at both the qualitative (99 of 106, 93.4%) and quantitative levels (mean MR-to-HR ratio, 1.01; 95% confidence interval: 0.95, 1.06). However, the 95% Bland-Altman discordance limits indicate that the MR can be up to 50% higher or 50% lower than the HR. CONCLUSION: The average concordance allows trialists to approximate HR from MR to determine sample size. However, the discordance limits are too great to consider that both measures are interchangeable. The actual policy to report HR only is not enough. Our results emphasize the need to attach descriptive survival measures to the HR.
Authors: Stacey J Winham; Ailith Pirie; Yian Ann Chen; Melissa C Larson; Zachary C Fogarty; Madalene A Earp; Hoda Anton-Culver; Elisa V Bandera; Daniel Cramer; Jennifer A Doherty; Marc T Goodman; Jacek Gronwald; Beth Y Karlan; Susanne K Kjaer; Douglas A Levine; Usha Menon; Roberta B Ness; Celeste L Pearce; Tanja Pejovic; Mary Anne Rossing; Nicolas Wentzensen; Yukie T Bean; Maria Bisogna; Louise A Brinton; Michael E Carney; Julie M Cunningham; Cezary Cybulski; Anna deFazio; Ed M Dicks; Robert P Edwards; Simon A Gayther; Aleksandra Gentry-Maharaj; Martin Gore; Edwin S Iversen; Allan Jensen; Sharon E Johnatty; Jenny Lester; Hui-Yi Lin; Jolanta Lissowska; Jan Lubinski; Janusz Menkiszak; Francesmary Modugno; Kirsten B Moysich; Irene Orlow; Malcolm C Pike; Susan J Ramus; Honglin Song; Kathryn L Terry; Pamela J Thompson; Jonathan P Tyrer; David J van den Berg; Robert A Vierkant; Allison F Vitonis; Christine Walsh; Lynne R Wilkens; Anna H Wu; Hannah Yang; Argyrios Ziogas; Andrew Berchuck; Georgia Chenevix-Trench; Joellen M Schildkraut; Jennifer Permuth-Wey; Catherine M Phelan; Paul D P Pharoah; Brooke L Fridley; Thomas A Sellers; Ellen L Goode Journal: Cancer Epidemiol Biomarkers Prev Date: 2016-01-08 Impact factor: 4.254
Authors: Georgia Herbert; Rachel Perry; Henning Keinke Andersen; Charlotte Atkinson; Christopher Penfold; Stephen J Lewis; Andrew R Ness; Steven Thomas Journal: Cochrane Database Syst Rev Date: 2019-07-22
Authors: Rachel Perry; Georgia Herbert; Charlotte Atkinson; Clare England; Kate Northstone; Sarah Baos; Tim Brush; Amanda Chong; Andy Ness; Jessica Harris; Anne Haase; Sanjoy Shah; Maria Pufulete Journal: BMJ Open Date: 2021-09-30 Impact factor: 3.006
Authors: Georgia Herbert; Rachel Perry; Henning Keinke Andersen; Charlotte Atkinson; Christopher Penfold; Stephen J Lewis; Andrew R Ness; Steven Thomas Journal: Cochrane Database Syst Rev Date: 2018-10-24