The population-based cohort Malmö Diet and Cancer study (MDC), from the city of Malmö in southern Sweden, was used in this study [13, 14]. In brief, all women born between 1923 and 1950 and men born between 1923 and 1945 living in Malmö city were invited to the MDC study during the period March 1991 to September 1996. A total of 30 447 individuals participated in clinical examinations at the screening center and filled in a self-administered questionnaire out of an eligible population of ≈74 000 individuals http://atvb.ahajournals.org/content/32/2/533.long-ref-17#ref-17. DNA was available for 28 767 subjects.

Subjects with history of diabetes (n = 1 311) at the baseline examination were excluded. In order to exclude individuals with severe inflammation, analyses were restricted to participants with information on total leukocyte counts less than 20.0 × 10⁹ cells/L [15]. In addition, 888 participants without complete information on covariates were excluded. Thus, the final study population in the project consisted of 26 667 subjects (10 364 men (38.9%) and 16 303 women (61.1%), aged 45–73 years. A random subsample from the MDC cohort, the MDC cardiovascular cohort (MDC-CV, n = 6,103), was invited to take part in a study of the epidemiology of carotid artery disease between October 1991 and February 1994 [16]. The additional examinations in this sub-cohort included measurements of fasting whole blood glucose, hemoglobin A1c (HbA_1c) and CRP.

The ethics committee at Lund University Lund, Sweden, approved the study (LU 51/90) and all participants provided informed written consent.

The examinations were performed by trained nurses at the screening center. Blood pressure (mmHg) was measured using a mercury-column sphygmomanometer after 10 minutes of rest in the supine position. Standing height (m) was measured with a fixed stadiometer calibrated in centimeters. Weight was measured to the nearest 0.1 kg using balance-beam scale with subjects wearing light clothing and no shoes. Body mass index (BMI) was calculated as weight (kg) divided by the square of the height (m²). Waist was measured as the circumference (cm) between the lowest rib margin and iliac crest.

Information on family history of diabetes, current use of lipid-lowering, blood pressure-lowering or anti-diabetic medications, smoking habits, leisure-time physical activity, education level and marital status were obtained from a self-administered questionnaire [13]. Family history of diabetes was defined as known diabetes in at least one first-degree relative [17]. History of myocardial infarction or stroke at the baseline examination was retrieved from the Swedish Hospital Discharge Register and the Stroke register in Malmö [18, 19]. Subjects were categorized into current smokers (i.e. those who smoked regularly or occasionally) or non-smokers (i.e. former smokers and never smokers). Low level of leisure-time physical activity was defined as the lowest quartile of a score revealed through 18 questions covering a range of activities in the 4 seasons. The evaluation of the questionnaire has been previously reported [20]. Educational level was divided into three groups: school year <9, 9–12 and > 12, respectively [21]. Marital status was categorized into married or not.

Total and differential leukocyte counts (neutrophils, lymphocytes, and a group of mixed cell types including monocytes, eosinophils and basophils) were counted in heparinized blood samples using a SYSMEX K1000 automatic counter (Sysmex Europe, Norderstedt, Germany). The analyses were performed consecutively at the time of the screening examination, at the central laboratory of Malmö University Hospital.

HbA1c and whole blood glucose was measured according to standard procedures at the Department of Clinical Chemistry. HbA_1c was measured by ion exchange chromatography, with reference values of 3.9–5.3% in non-diabetic individuals. Insulin was measured by a radioimmunoassay in mIU/ L and the HOMA index was calculated as fasting insulin*glucose/22.5 [16]. CRP was analyzed using a high-sensitive assay, Tina-quant^® CRP latex assay (Roche Diagnostics, Basel, Switzerland).

The missense polymorphism R262W (rs3184504), which previously has been associated with concentrations of leukocytes, neutrophils and lymphocytes [9, 10] was genotyped in 24,489 subjects. Based on results from previous GWAS studies of leukocyte count in subjects with European ancestry [25–27], we also tested whether polymorphisms in the 17q21 locus (rs4065321, rs3859192, rs9916158, rs4794822 and rs17609240) were useful as instrumental variables in this study. These genotypes were studied in relation to leukocyte count in a subsample of 4600 individuals, but none of the SNPs from the 17q21 locus reached p<0.5 x10^-8 for the association with leukocyte count. Since we also found a significant inverse relationship between insulin resistance and the 17q21 locus, both in the literature [28] and in our data, we decided to use the R262W polymorphism only.

DNA was extracted from peripheral blood cells and assigned to batches without regard to disease status or personal identity. Batches were genotyped using real-time polymerase chain reaction (PCR) with 2.5 ng DNA as PCR template for allelic discrimination on an ABI7900HT (Life Technologies, Carlsbad, CA, USA). Genotype calls were obtained using SDS 2.3 software (Life Technologies, Carlsbad, CA, USA) with manual inspection and curation of fluorescence intensity plots. The call rate was >90%. The Hardy-Weinberg equilibrium (HWE) was calculated using an online calculator (chi-2 = 3.42, df = 2, p = 0.06).

Subjects were categorized into sex-specific quartiles of leukocyte concentrations, i.e., four groups with the same proportion of men and women in each group. One-way analysis of variance (ANOVA) and logistic regression was used to assess cross-sectional relationships of leukocyte count to diabetes risk factors. A general linear model was used to adjust glucose and HbA_1c for potential confounding factors, in categories of the R262W polymorphism. Cox proportional hazards regression was used to examine hazard ratios (HR) with 95% confidence interval (CI) for incidence of diabetes by total and differential leukocyte counts (neutrophils, lymphocytes, and mixed cells) using the lowest quartile as the reference category. Time axis was follow-up time until death, emigration, incident diabetes or end of follow-up. The results were adjusted for age, sex, BMI and family history of diabetes in the basic model [17, 29]. Secondly, we also adjusted for waist circumference, systolic blood pressure, using of blood pressure- or lipid-lowering medication, history of cardiovascular disease, smoking habits, leisure physical activity, educational level and marital status. CRP was added to the covariates in an additional analysis in the MDC-CV sub-cohort. Possible interaction between leukocyte count and risk factors for diabetes was explored by introducing interaction terms in the fully adjusted multivariate model. The Kaplan-Meier curve was used to demonstrate incidence of diabetes in relation to total leukocyte count during the follow-up. The association between leukocyte count, fasting blood glucose and HbA1c, respectively, was analyzed using general linear model adjusted for age, sex and BMI. Model discrimination was estimated with Harrell’s C-statistics [30].

Sensitivity analyses were performed after excluding individuals having a cold or lung infection within two weeks before the baseline examination. We also explored the effect of non-steroid anti-inflammatory drug (NSAID) medication on the relationships between leukocytes and diabetes.

A Mendelian randomization analysis path diagram was presented in Fig 1. R262W was used as an instrumental variable for leukocyte count to study incidence of diabetes. Mendelian randomization analysis was performed with two-stage least squares regression (2SLS) using the ivreg2 command in STATA [31]. The genetic instrument was validated for association with total and differential leukocyte counts using linear or logistic regression models. A power analysis was performed for the association between R262W and incidence of diabetes. With α = 0.05, there was 64% power to detect a significant relationship, assuming a HR of 1.25 per standard deviation increment of leukocytes, i.e., the age and sex-adjusted HR in the present cohort.

All analyses were performed using IBM SPSS statistics (version 20; IBM Svenska AB, Stockholm, Sweden) and STATA12 (Stata Corp, College Station, TX, USA).

The mean total leukocyte count was 6.37±1.68 x10⁹ /L, and the proportion of neutrophils, lymphocytes, and mixed cells were 61%, 31% and 8%, respectively. The relationships between sex-specific quartiles of total leukocyte count and risk factors for diabetes are presented for all subjects in Table 1, and separately for men and women in S1 Table and S2 Table. Increased leukocyte count was associated with age, BMI, waist circumference, systolic blood pressure, antihypertensive- or lipid-lowering medication, prevalent cardiovascular disease, smoking habits, low physical activity, education level and being married. In addition, HbA_1c, glucose and insulin were positively and significantly associated with leukocyte count (p<0.001) in the subgroup, Table 1.

During a mean follow-up of 14 years, 2 946 subjects (1 521 men and 1 425 women, 7.87 per 1000 person-years) developed diabetes. Kaplan-Meier curves of diabetes free survival in relation to sex-specific quartiles of total leukocyte count is shown in Figs 2 and 3. Incidence of diabetes was significantly associated with total and differential leukocyte counts in the basic model 1, Table 2. After adjustment for potential confounding factors, the association remained significant for total leukocyte (4^th vs 1^st quartiles HR: 95% CI; 1.37; 1.22–1.53), neutrophil (1.33; 95% CI: 1.19–1.49) and lymphocyte (1.29; 95% CI: 1.15–1.44) counts, but not for mixed cells (1.04; 95% CI: 0.94–1.15, not shown in table). Male sex, family history of diabetes, high BMI and waist circumference, high systolic blood pressure, use of antihypertensive and lipid-lowering medications, current smoking and low education level were all significantly associated with incidence of diabetes in the final multivariate model. No significant interaction was observed between total leukocyte count and other risk factors for diabetes. Use of non-steroid anti-inflammatory drugs (NSAID) (n = 822) at baseline was added to the multivariable adjusted model in a sensitivity analysis, but the results were essentially unchanged. NSAID was not a significant risk factor for diabetes in the model.

We also performed a sensitivity analysis after excluding individuals who reported having a cold or lung infection within two weeks before the baseline examination (n = 20 906). After adjustment for potential confounding factors, the association remained significant for total leukocyte (4th vs 1st quartiles HR: 1.39; 95% CI; 1.22–1.58), neutrophil (1.37; 95% CI: 1.21–1.56) and lymphocyte (1.32; 95% CI: 1.16–1.50) counts, while mixed cells remained non-significant (1.03; 95% CI: 0.92–1.16).

In the MDC-CV subcohort, 736 subjects developed diabetes during the follow-up. The HR (95% CI) for total leukocyte count (4^th vs 1^st quartile) was 1.95 (1.55–2.46, P for trend <0.001) in the basic model, S3 Table. The HR was reduced to 1.53 (1.20–1.95; P for trend 0.004) taking possible confounders into account and remained significant also after adding CRP into the model (HR: 1.37; 1.05–1.77; P for trend 0.044). Among the leukocyte subpopulations, only neutrophils remained significantly associated with incidence of diabetes after adjustment for CRP (HR: 1.39; 1.08–1.78, P for trend 0.022), S3 Table.

The C-statistics value for a model with age, sex and BMI was 0.717 (0.708–0.726) and increased to 0.722 (0.713–0.731) when leukocyte count was added to the model. Leukocyte count significantly improved the discriminatory value (C-statistic) for incidence of diabetes with 0.005 (0.002–0.008) (p<0.001).

The association between the R262W polymorphism and leukocyte count is shown in Table 3. The frequency of the minor allele (T) of R262W was 48%. The T allele was strongly associated with increased leukocytes (0.11x10⁹ cells/l per T allele, p = 1.14 x10^-12, F statistics = 50.6), lymphocytes (p = 4.3 x10^-16), neutrophils (p = 8.0 x10^-6) and mixed cells (p = 3.0 x10^-6). There was no association between the R262W polymorphism and BMI (p = 0.154), waist (p = 0.495), systolic blood pressure (p = 0.231) and use of lipid-lowering medication (p = 0.723).

We found no statistically significant association between the R262W polymorphism and incidence of diabetes, fasting blood glucose or HbA_1c, Table 3. These relationships remained non-significant after full adjustment for potential confounding factors in multivariable Cox regression (diabetes) or general linear models (glucose, HbA_1c) (all p>0.288). For glucose, the IV estimator was -0.210 (95% CI: -0.723–0.302) (p = 0.421); for HbA_1c, the IV estimator was -0.201 (-0.558–0.157) (p = 0.272). For diabetes, the IV estimator was -0.005 (-0.047–0.057)(p = 0.837).

The strength of the study was the large numbers of subjects and events during a long follow-up period. A limitation of the present study is lack of information on type of diabetes. Participants were 45–73 years old and non-diabetic at the baseline examination. It can be assumed that almost all incident cases developed type 2 diabetes, since type 1 diabetes usually has an early onset, and were excluded from analyses as prevalent cases [42]. New cases of diabetes were identified from several independent sources. The registers of out- and in-patients cover all hospital visits in the country and the pharmaceutical register covers all filled prescriptions from all pharmacies in Sweden since 2005. The HbA_1c register covers the population in the city of Malmö. The relationship between leukocytes and diabetes was largely the same for each of the data sources. Diabetes can go undetected for several years and individuals that do not seek medical care will be missed. However, the coverage of the registers is very good and we have no reason to question the case validity. Lack of information about change of exposure during the follow-up (e.g. weight change, quitting smoking, new medication, etc.) was another possible limitation. A further limitation is the potential pleiotropy for the SH2B3 missense variant, which is associated with many traits. Although this would be more relevant in the context of a positive finding, it could be hypothesized that a pleiotropic effect could attenuate any association with diabetes. So-called canalization, i.e., compensatory mechanisms that counterbalance the effects of the genetic instrument, is another possibility that hypothetically could explain the negative results for the R262W polymorphism.

Although the leukocyte count significantly increased the model discrimination in terms of C-statistics, it is uncertain whether measurements of leukocytes could improve prediction of future diabetes in clinical practice. However, further studies are needed to confirm this. In conclusion, increased leukocyte counts are associated with incidence of diabetes. However, the negative findings for the R262W polymorphism suggest that the associations may not be causal, although limitations in statistical power and balancing pleiotropic effects cannot be excluded. Further studies are needed for replication of this finding in other cohorts.