Vitamin D and human health: evidence from Mendelian randomization studies
Eur J Epidemiol. 2024 May;39(5):467-490. doi: 10.1007/s10654-023-01075-4
PDF behind paywall Can be viewed in DeepDyve
Aiping Fang 1 2, Yue Zhao 1, Ping Yang 3 4, Xuehong Zhang 2 5, Edward L Giovannucci 6 7
We summarized the current evidence on vitamin D and major health outcomes from Mendelian randomization (MR) studies. PubMed and Embase were searched for original MR studies on vitamin D in relation to any health outcome from inception to September 1, 2022. Nonlinear MR findings were excluded due to concerns about the validity of the statistical methods used. A meta-analysis was preformed to synthesize study-specific estimates after excluding overlapping samples, where applicable. The methodological quality of the included studies was evaluated according to the STROBE-MR checklist.
A total of 133 MR publications were eligible for inclusion in the analyses.
The causal association between vitamin D status and 275 individual outcomes was examined. Linear MR analyses showed genetically high 25-hydroxyvitamin D (25(OH)D) concentrations were associated with reduced risk of
- multiple sclerosis incidence and relapse,
- non-infectious uveitis and scleritis,
- psoriasis,
- femur fracture,
- leg fracture,
- amyotrophic lateral sclerosis,
- anorexia nervosa,
- delirium,
- heart failure,
- ovarian cancer,
- non-alcoholic fatty liver disease,
- dyslipidemia, and
- bacterial pneumonia,
but increased risk of Behçet's disease, Graves' disease, kidney stone disease, fracture of radium/ulna, basal cell carcinoma, and overall cataracts.
Stratified analyses showed that the inverse association between genetically predisposed 25(OH)D concentrations and multiple sclerosis risk was significant and consistent regardless of the genetic instruments GIs selected. However, the associations with most of the other outcomes were only pronounced when using genetic variants not limited to those in the vitamin D pathway as GIs. The methodological quality of the included MR studies was substantially heterogeneous. Current evidence from linear MR studies strongly supports a causal role of vitamin D in the development of multiple sclerosis. Suggestive support for a number of other health conditions could help prioritize conditions where vitamin D may be beneficial or harmful.
What are Mendelian randomization studies? Asked Perplexity AI July 2024
Answer
Mendelian randomization
Method using genes to examine causal effects in epidemiology
Definition Method using measured genetic variation to examine causal effect of an exposure on an outcome in epidemiology
Purpose To identify modifiable causes of health outcomes and diseases of public health concern
Significance Provides unbiased estimates of the effects of assumed causal variables without conducting traditional randomized controlled trials
Mendelian randomization (MR) studies are a type of epidemiological study that use genetic variants as instrumental variables to investigate causal relationships between modifiable risk factors and health outcomes. Here are the key points about Mendelian randomization studies:
- Purpose:
MR studies aim to determine if an observed association between an exposure (risk factor) and an outcome is causal.
They help overcome limitations of traditional observational studies like confounding and reverse causation. - Methodology:
MR uses genetic variants associated with the exposure of interest as proxies or "instruments" for that exposure.
It relies on the principle that genetic variants are randomly allocated at conception, similar to randomization in a clinical trial. - Key assumptions:
The genetic variant is associated with the exposure
The genetic variant is not associated with confounders
The genetic variant only affects the outcome through the exposure (no pleiotropy) - Types:
One-sample MR: Uses a single dataset containing genetic, exposure and outcome data
Two-sample MR: Uses separate datasets for genetic associations with exposure and outcome - Advantages:
Helps establish causality from observational data
Less susceptible to confounding and reverse causation than traditional epidemiological studies
Can be conducted using publicly available summary statistics from genome-wide association studies - Limitations:
Requires valid genetic instruments
Assumptions can be difficult to verify fully
May be affected by population stratification or pleiotropy - Applications:
Investigating causal effects of modifiable risk factors on diseases
Drug target validation
Exploring potential side effects of interventions - Recent developments:
Methods to test for and account for pleiotropy (e.g. MR-Egger, weighted median)
Multivariable MR to account for multiple related exposures
Bidirectional MR to assess direction of causality
Mendelian randomization has become an increasingly popular and powerful tool in epidemiology and medical research for strengthening causal inference from observational data.
10+ VitaminDWiki pages have MENDELIAN in the title
The list is automatically updated
15 of 284 studies that had Mendelian and vitamin D in the title - Google Scholar July 2024
- Vitamin D and Multiple Health Outcomes: An Umbrella Review of Observational Studies, Randomized Controlled Trials, and Mendelian Randomization Studies - July 2022 FREE PDF
- "The results indicated that vitamin D supplementation is a promising strategy with long-term preventive effects on multiple chronic diseases and thus has the potential to decrease all-cause mortality. However, the current vitamin D supplementation strategy might not be an efficient intervention approach for these diseases, suggesting that new strategies are highly needed to improve the intervention outcomes."
- Health Effects of Vitamin D Supplementation: Lessons Learned From Randomized Controlled Trials and Mendelian Randomization Studies Oct 2023, behind paywall Can be viewed in DeepDyve
- A putative causality of vitamin D in common diseases: A mendelian randomization study- August 2022 FREE PDF
- "Conclusions: Our findings indicate a potential causal role of vitamin D in common diseases, which needs further validation."
- The causal role of circulating vitamin D concentrations in human complex traits and diseases: a large-scale Mendelian randomization study - January 2021 FREE PDF
- Phenome-wide Mendelian randomization study evaluating the association of circulating vitamin D with complex diseases - March 2023 FREE PDF
- Mendelian randomisation and vitamin D: the importance of model assumptions - Jan 2023 FREE PDF
- The association of vitamin D and digestive system cancers: a comprehensive Mendelian randomization study - July 2023 PDF behind paywall Can be rented in DeepDyve NO
- Non-linear Mendelian randomization analyses support a role for vitamin D deficiency in cardiovascular disease risk - May 2022 FREE PDF
- Vitamin D and brain health: an observational and Mendelian randomization study - Aug 2022 FREE PDF Dementia YES, Stroke NO
- Associations between vitamin D and autoimmune diseases: Mendelian randomization analysis - Oct 2023, 152238 FREE PDF
- Odds Ratio: psoriasis 0.91,systemic lupus erythematosus 0.84;
- Non-linear Mendelian randomization: detection of biases using negative controls with a focus on BMI, Vitamin D and LDL cholesterol - May 2024 FREE PDF
- The causal role of circulating vitamin D concentrations in human complex traits and diseases: a large-scale Mendelian randomization study Jan 2021 FREE PDF
- "...we found limited evidence in support of a causal effect of 25(OH)D on anthropometric traits, obesity, cognitive function, sleep behavior, breast and prostate cancer, and autoimmune, cardiovascular, metabolic, neurological and psychiatric traits and diseases, and blood biomarkers"
- Vitamin D Levels and Risk of Male Factor Infertility: A Mendelian Randomization Study - Jan 2023 doi: 10.5534/wjmh.220109 FREE PDF YES
- Vitamin D-associated genetic variants in the Brazilian population: Investigating potential instruments for Mendelian randomization. - 2024 10.7705/biomedica.6972 FREE PDF
- Vitamin D and human health: evidence from Mendelian randomization studies META-ANALYSIS - May 2024 PDF behind paywall Can be rented in DeepDyve
- "Current evidence from linear MR studies strongly supports a causal role of vitamin D in the development of multiple sclerosis."