“…The updated meta-analysis of 21 studies [ [77] , [78] , [79] , [80] , [81] , [82] , [83] , [84] , [85] , [86] , [87] , [88] , [89] , [90] , [91] , [92] , [93] , [94] ], including 136,298 cases among >1,030,243 participants, revealed an inverse association between cheese consumption and all-cause mortality (highest compared with lowest: RR = 0.95; 95% CI: 0.92, 0.99; P = 0.0052; I 2 = 34%) ( Figure 2 and Supplemental Figure 2 ). In the dose–response meta-analysis of 14 studies [ 77 , 79 , [81] , [82] , [83] , [84] , [85] , [87] , [88] , [89] , [90] , [91] ], each 30-g/d cheese increment was associated with a 2% lower risk of all-cause mortality (RR = 0.98; 95% CI: 0.96, 1.00; P = 0.027; I 2 = 60%) ( Figure 4 and Supplemental Figure 3 ). Nonlinear analyses further showed a U-shaped association, where the lowest risk of all-cause mortality was observed at ∼40 g/d of cheese consumption ( P -nonlinearity < 0.001) ( Figure 5 A).…”