Hematological parameters and prevalence of anemia in white and British Indian vegetarians and nonvegetarians in the UK Biobank

Abstract

Background: There may be differences in hematological parameters between meat-eaters and vegetarians.

Objective: The aim of this study was to perform cross-sectional analyses of hematological parameters by diet group in a large cohort in the United Kingdom.

Methods: A complete blood count was carried out in all UK Biobank participants at recruitment (2006-2010). We examined hemoglobin, red and white blood cell counts, and platelet counts and volume in regular meat eaters (>3 times/wk of red/processed meat consumption, n = 212,831), low meat eaters (n = 213,092), poultry eaters (n = 4815), fish eaters (n = 10,042), vegetarians (n = 6548), and vegans (n = 398) of white ethnicity and meat eaters (n = 3875) and vegetarians (n = 1362) of British Indian ethnicity.

Results: In both white and British Indian populations, compared with regular meat eaters (or meat eaters in Indians), the other diet groups had up to 3.7% lower age-adjusted hemoglobin concentrations (difference not significant in white vegan women) and were generally more likely to have anemia (e.g., 8.7% of regular meat eaters compared with 12.8% of vegetarians in white premenopausal women; P < 0.05 after Bonferroni correction). In the white population, compared with regular meat eaters, all other diet groups had lower age- and sex-adjusted total white cells, neutrophils, lymphocytes, monocytes, and eosinophils (P-heterogeneity < 0.001 for all), but basophil counts were similar across diet groups; in British Indians, there was no significant difference in any of the white blood cell counts by diet group. Compared with white regular meat eaters, the low meat eaters, poultry eaters, fish eaters, and vegans had significantly lower platelet counts and higher platelet volume, whereas vegetarians had higher counts and lower volume. Compared with British Indian meat eaters, vegetarians had higher platelet count and lower volume.

Conclusions: In the UK Biobank, people with low or no red meat intake generally had lower hemoglobin concentrations and were slightly more likely to be anemic. The lower white blood cell counts observed in low and non-meat eaters, and differences in mean platelet counts and volume between diet groups, warrant further investigation. This observational study was registered at http://www.isrctn.com/ as ISRCTN10125697.

Keywords: UK Biobank; anemia; blood count; ethnicity; hematology; vegan; vegetarian.

FIGURE 1

Hemoglobin concentration and red blood cell count by diet group and ethnicity in the UK Biobank. Point estimates represent adjusted mean levels (95% CIs), estimated based on linear regression models. All estimates were adjusted for age at recruitment (<45, 45–49, 50–54, 55–59, 60–64, and ≥65 y) and smoking (never, previous, current <15 cigarettes/d, current ≥15 cigarettes/d, and unknown). Total numbers of men, premenopausal women, and postmenopausal women, respectively, in the diet groups were as follows: white regular meat eaters: 121,433, 20,791, 67,145; white low meat eaters: 77,457, 29,570, 101,184; white poultry eaters: 1074, 810, 2797; white fish eaters: 2789, 2287, 4643; white vegetarians: 2130, 1636, 2583; white vegans: 166, 76, 149; Indian meat eaters: 2254, 565, 980; Indian vegetarians: 485, 229, 615. P for heterogeneity across the diet groups (stratified by ethnicity and estimated by regressing each variable against diet group) was 0.01 for hemoglobin in British Indian premenopausal women, >0.5 for red blood cell count in all British Indians, and <0.001 for all other variables.

FIGURE 2

Reticulocyte percentage and immature reticulocyte fraction by diet group and ethnicity in the UK Biobank. Point estimates represent adjusted mean levels (95% CIs), estimated based on linear regression models. All estimates were adjusted for age at recruitment (<45, 45–49, 50–54, 55–59, 60–64, and ≥65 y), sex, and smoking (never, previous, current <15 cigarettes/d, current ≥15 cigarettes/d, and unknown). Total numbers of participants in the diet groups were as follows: white regular meat eaters, 212,831; white low meat eaters, 213,092; white poultry eaters, 4815; white fish eaters, 10,042; white vegetarians, 6548; white vegans, 398; Indian meat eaters, 3875; and Indian vegetarians, 1362. P for heterogeneity across the diet groups (stratified by ethnicity and estimated by regressing each variable against diet group) was >0.2 for reticulocyte percentage and immature reticulocyte fraction in British Indian premenopausal women and <0.001 for all other variables.

FIGURE 3

White blood cell counts by diet group and ethnicity in the UK Biobank. Point estimates represent adjusted mean levels (95% CIs), estimated based on linear regression models. All estimates were adjusted for age at recruitment (<45, 45–49, 50–54, 55–59, 60–64, and ≥65 y), sex, and smoking (never, previous, current <15 cigarettes/d, current ≥15 cigarettes/d, and unknown). Total numbers of participants in the diet groups were as follows: white regular meat eaters, 212,831; white low meat eaters, 213,092; white poultry eaters, 4815; white fish eaters, 10,042; white vegetarians, 6548; white vegans, 398; Indian meat eaters, 3875; and Indian vegetarians, 1362. P for heterogeneity across the diet groups (stratified by ethnicity and estimated by regressing each variable against diet group) was >0.1 for all variables in British Indians and <0.001 for all variables in white British participants.

FIGURE 4

Platelet count and volume by diet group and ethnicity in the UK Biobank. Point estimates represent adjusted mean levels (95% CIs), estimated based on linear regression models. All estimates were adjusted for age at recruitment (<45, 45–49, 50–54, 55–59, 60–64, and ≥65 y), sex, and smoking (never, previous, current <15 cigarettes/d, current ≥15 cigarettes/d, and unknown). Total numbers of participants in the diet groups were as follows: white regular meat eaters, 212,831; white low meat eaters, 213,092; white poultry eaters, 4815; white fish eaters, 10,042; white vegetarians, 6548; white vegans, 398; Indian meat eaters, 3875; and Indian vegetarians, 1362. P for heterogeneity across the diet groups (stratified by ethnicity and estimated by regressing each variable against diet group) was <0.001 for all variables.