Medical conditions associated with coffee consumption: Disease-trajectory and comorbidity network analyses of a prospective cohort study in UK Biobank

Abstract

Background: Habitual coffee consumption has been associated with multiple health benefits. A comprehensive analysis of disease trajectory and comorbidity networks in relation to coffee consumption is, however, currently lacking.

Objectives: We aimed to comprehensively examine the health outcomes associated with habitual coffee consumption, through clarifying its disease trajectory and comorbidity networks.

Methods: Based on the UK Biobank cohort, we included 395,539 individuals with available information on coffee intake collected at recruitment between 2006 and 2010. These individuals were categorized as having low (<1 cup per day), moderate (1-3 cups), and high (≥4 cups) levels of coffee intake, and were followed through 2020 to ascertain 496 medical conditions. Cox regression was used to assess the associations between high-level coffee intake and the risk of medical conditions with a prevalence ≥0.5% in the study population, after adjusting for multiple confounders, using low-level coffee intake as the reference. Disease-trajectory and comorbidity network analyses were then applied to visualize the temporal and nontemporal relationships between the medical conditions that had an inverse association with high-level coffee intake.

Results: During a median follow-up of 11.8 years, 31 medical conditions were found to be associated with high-level coffee intake, among which 30 showed an inverse association (HRs ranged from 0.61 to 0.94). The inverse associations were more pronounced for women, compared with men. Disease-trajectory and comorbidity network analyses of these 30 conditions identified 4 major clusters of medical conditions, mainly in the cardiometabolic and gastrointestinal systems, among both men and women; 1 cluster of medical conditions following alcohol-related disorders, primarily among men; as well as a cluster of estrogen-related conditions among women.

Conclusions: Habitual coffee consumption was associated with lower risks of many medical conditions, especially those in the cardiometabolic and gastrointestinal systems and those related to alcohol use and estrogen regulation.

Keywords: alcohol-related disorders; caffeine; cardiometabolic diseases; coffee; estrogen-related conditions; gastrointestinal diseases.

FIGURE 1

Flowchart of the study population selection. *Severe diseases include myocardial infarction, congestive heart failure, peripheral vascular disease, cerebrovascular disease, dementia, chronic pulmonary disease, connective tissue disease, liver disease, diabetes mellitus (with or without chronic complications), hemiplegia, moderate or severe renal disease, any tumor, leukemia, lymphoma, and acquired immune deficiency syndrome. IBD, inflammatory bowel disease; IBS, irritable bowel syndrome.

FIGURE 2

RRs of subsequent medical conditions for high-level coffee consumption compared to low-level coffee consumption (n = 191,399). The outer ring shows the point estimates of HRs of identified medical conditions that were statistically significantly associated with high-level coffee consumption after correction for multiple testing (i.e., false discovery rate–adjusted P value < 0.05). HRs were derived from a Cox model, adjusted for age, sex, Townsend deprivation index, household income, BMI, tea intake, smoking status, alcohol drinking status, physical activity, and fruit and vegetable consumption. The red color indicates a higher risk (i.e., HR > 1) and the green color shows a lower risk (i.e., HR < 1). The degree of color represents the magnitude of the corresponding association. Detailed results are shown in Supplemental Table 4.

FIGURE 3

Disease-trajectory network of medical conditions with a lower risk in relation to high-level coffee consumption (n = 191,399). Each node represents a medical condition, with the color of the node representing the HR of the corresponding medical condition when comparing individuals with high-level coffee consumption to those with low-level coffee consumption, according to an adjusted Cox model. The width of the lines connecting 2 nodes represents the number of individuals with the corresponding disease trajectory.

FIGURE 4

Comorbidity network of medical conditions with a lower risk in relation to high-level coffee consumption (n = 191,399). Each node represents a medical condition and is labeled with its name and “phecode.” The size and color of each node indicate the prevalence and the category of the corresponding medical condition, respectively (see legend). The width of the link represents the strength of the comorbidity association, measured by ORs obtained from an adjusted logistic regression. The network is partitioned into 4 modules using a Louvain algorithm, and nodes belonging to the same module are grouped together and separated from other nodes using dashed lines.