In this comment I want to focus in the following claim and explore how well its supported in the article.
It is probably unhealthy to be vegan.
Let’s go one by one.
Vegans often show up as healthier in studies than other groups, but correlation is not causation. For example, famously Adventists are vegetarians and live longer than the average population. However, vegetarian is importantly different from vegan. Also, Adventists don’t drink or smoke either, which might explain the difference.
Wouldn’t it be great if we had a similar population that didn’t smoke or drink but did eat meat to compare?
We do! The Mormons. And they live longer than the Adventists.
I don’t know the source you used for this. So I showed Claude the quote above and asked “Are there any studies comparing the health of Mormons vs. Adventists?”
Great question — this is a claim that circulates in nutrition debates, so let me search for what the research actually shows.This is a really interesting question, and the claim you’ve quoted doesn’t hold up well under scrutiny. Here’s what the research actually shows:
Yes, there are direct comparisons — and they don’t support the claim that Mormons outlive Adventists.
The key study to know about is Grundmann (1992), published in Archives of Anatomy, Cytology, and Pathology, which directly compared cancer mortality between US Mormons and Seventh-day Adventists. Life expectancy was generally elevated by 2–4 years in both Mormons and Seventh-day Adventists compared to the general population. The study found them broadly comparable, not that Mormons clearly outlived Adventists.
The numbers, side by side:
The UCLA “Mormon Longevity Study” (Enstrom & Breslow, 2008) followed ~9,800 religiously active California Mormon couples from 1980–2004. Mormon males had a life expectancy of 84.1 years, about 9.8 years longer than US white males, and Mormon females had a life expectancy of 86.1 years, about 5.6 years longer.
The Adventist Health Study-1, covering ~34,000 California Adventists, found that AHS-1 men lived 7.3 years longer and women 4.4 years longer than other Californians. But crucially, when looking specifically at vegetarian Adventists, men lived 9.5 years longer and women 6.1 years longer — essentially matching or slightly exceeding the Mormon figures.
Why the naive comparison is misleading:
The quote you shared makes several errors worth flagging.
First, these studies used different methodologies, reference populations, time periods, and selection criteria. The Mormon study focused on the most devout subset (“High Priests”), while the Adventist studies included a broader church membership. Active Mormons, defined as High Priests and Seventies, abstain almost completely from tobacco, alcohol, coffee, and tea — so the Mormon study was already selecting for maximal compliance. Comparing a highly selected Mormon subgroup to all Adventists and concluding meat-eating is fine is a classic apples-to-oranges problem.
Second, the claim that diet is the key variable being tested ignores that both groups share many health-promoting behaviors: no smoking, no alcohol, strong community ties, regular church attendance, strong family structures. Among a study of 34,192 faithful Seventh Day Adventists, researchers found that this way of life also conferred an extra 10 years of life. The social and lifestyle confounders are massive.
Third, and most relevant to your interest in veganism specifically: the Adventist Health Study-2 (AHS-2) provides the best data we have, because it compares vegetarians, vegans, pesco-vegetarians, and meat-eaters within the same religious community, controlling for all those shared lifestyle factors. Compared with nonvegetarians, vegetarians had lower risks of overall mortality, and specifically from renal failure, infectious disease, diabetes, cardiac causes, and ischemic heart disease. Compared to lacto-ovo-vegetarian diets, vegan diets seem to offer additional protection for obesity, hypertension, type-2 diabetes, and cardiovascular mortality.
That said, higher cause-specific neurologic mortalities were observed among older vegetarians, specifically for stroke and dementia, so the picture isn’t uniformly favorable at advanced ages.
Bottom line: The claim that “Mormons live longer than Adventists, therefore meat-eating is fine” is a significant oversimplification. The studies don’t clearly show Mormons outliving Adventists at all — and within Adventists, where you can actually control for lifestyle confounders, vegetarians (including vegans) consistently show lower mortality than meat-eating Adventists. The quote you shared is a rhetorically effective argument but not a scientifically sound one.”
There was that RCT showing that creatine supplementation boosted the IQs of only vegetarians.
Calcium is one of the only nutrients we know of that can reduce the mood symptoms of PMS for women and it is practically impossible to get enough calcium from real food from vegan sources (you’re stuck taking medicine for it in the form of supplements or eating artificially fortified sources, like soy milk).
I agree with the general claim that its harder to consume high amounts of calcium on a vegan diet, but not clear by what you mean by “high enough”.
Its more complicated than that? The linked paper is a meta-analysis and that result is only based on two studies that assessed depression as a categorical variable:
“(...) vegetarians and vegans had a higher risk of depression when depression was assessed as a categorical variable (...), but heterogeneity among studies was high (...). In addition to the significant heterogeneity between the 2 studies, conclusions are tentative because the analysis only included 2 studies.”
Regarding the studies that assessed depression as a continuous variable:
(...) no statistically significant differences were found between vegetarian or vegan diets and omnivores regarding the incidence of depression (...). Heterogeneity among studies for depression was very high(...). Subgroup analysis showed a statistically significant higher incidence of depression in vegetarians/vegans under 26 years of age(...), and in studies with higher quality assessment scores (...). Subgroup analyses of sex (...), the length of time the diet was followed (...), the type of diet (vegan vs vegetarian (...)), or the instrument used for assessment (...) did not show any significant differences between vegetarians/vegans and omnivores. Heterogeneity was more pronounced in those over 25 years of age (...), in studies that included mainly women (...), in short-term studies ((...), in studies that included vegans (...), in studies that used instruments other than the Depression Anxiety Stress Scales tool (...), and in lower-quality studies (...).
The same meta-analysis also shows lower anxiety scores for vegetarians/vegans.
The authors also speculate about the possibility of reverse causation.
“One possible explanation for these associations is a reverse causal relationship between vegetarianism or veganism and mental health outcomes. Individuals who have psychosocial disorders may be more eager to follow a vegetarian or vegan diet in order to improve their mental health. In a German study, the age at which a diet is adopted showed that a vegetarian diet was adopted after the onset of mental disorders, thus confirming the possibility of reverse causation.42 Still, 1 intervention study reported an improvement in depression, anxiety, and mood after adoption of a vegan diet,17,20 while another found improvements in stress but no significant changes in depression, anxiety, or mood in omnivores who adopted a vegetarian diet for 2 weeks.19”
After eyeballing the study / asking Claude to summarise it, this checks out. Something interesting is that the higher risk of fracture was still significant for vegans even when the analysis was restricted to people meeting the guidelines for calcium and protein consumption!
Some interesting comments from Claude after I asked it to summarise the study
Why you should be very cautious about this study:
The fundamental problem is the ecological fallacy — which the authors themselves acknowledge but then largely brush aside. This study compares countries, not individuals. Countries that eat more meat are also wealthier, have better healthcare systems, cleaner water, better sanitation, more stable governments, and countless other advantages that extend life. While they control for GDP and urbanization, these are crude proxies that can’t capture the enormous complexity of what makes populations in wealthy countries live longer than those in poor ones.
To illustrate: the correlation they’re finding is essentially that Norway, Japan, Australia, and France eat more meat and live longer than Chad, Niger, and Sierra Leone. This is true, but the causal interpretation — that meat is why they live longer — is an enormous leap. GDP alone explains over 50% of the variance in life expectancy in their own regression (R² change = 0.509), and meat only adds about 3% explanatory power on top of that. The authors frame this 3% as important, but given the massive residual confounding inherent in cross-country comparisons, it could easily be capturing unmeasured aspects of development and wealth.
Other methodological concerns:
The food data are supply figures, not actual consumption — they don’t account for food waste, which varies enormously between rich and poor countries. The study is cross-sectional, comparing countries at one time point, yet the relationship between diet and longevity is inherently longitudinal. The confounders controlled for are quite limited — they don’t include healthcare expenditure, access to clean water, infectious disease burden, political stability, inequality, or dozens of other factors that differ systematically between high-meat and low-meat countries.
The discussion section also reveals a fairly strong pro-meat agenda. The authors make evolutionary arguments about human adaptation to meat eating, dismiss vegetarianism studies as flawed, and cite the NutriRECS guidelines (which were themselves highly controversial in the nutrition community). They claim their findings “unequivocally” indicate that meat eating benefits life expectancy — language far too strong for an ecological correlation study.
Such neurological symptoms have been documented in vegans who forego B₁₂ supplements for years. They are often reversible with B₁₂ therapy if caught early, but can be permanent if prolonged
Yeah. Unfortunately the whole recommended B12 daily-dose situation is confusing:
“It should be noted that a once-daily dose of this nutrient at the Reference Nutrient Intake level (the level typically found in multivitamin supplements, including some of those marketed toward vegans, whereas single nutrient supplements of vitamin B12 often contain considerably higher levels) may not be sufficient for maintaining adequate B12 status 52(https://pmc.ncbi.nlm.nih.gov/articles/PMC4844163/#bb0260). The rate of absorption of vitamin B12 is limited by the capacity of ileal receptors for phagocytosis of vitamin B12–intrinsic factor complex and decreases along with increasing amounts of this vitamin in a single meal or a single supplement administration 33(https://pmc.ncbi.nlm.nih.gov/articles/PMC4844163/#bb0165)”
Meaning a lot of people might be taking daily B12 supplements but still be deficient. I agree that getting vegan supplements right might be hard to a lot of people.
A small study found 26.5% menstrual irregularity in vegetarians vs 4.9% in non‑vegetarians. Low B₁₂ and iron can lead to anemia and ovulatory problems; low zinc may disrupt menstrual cycles; inadequate iodine or selenium can affect thyroid function, which is crucial for fertility.
Right. Its a small study, though and one that has the potential to have a selection bias (vegetarian women were recruited from Seventh-day Adventist church newsletters and non-vegetarians through newspaper ads). I wouldn’t make any life changes just based on this one.
Hi, KatWoods. Thanks for this post. 🙂
In this comment I want to focus in the following claim and explore how well its supported in the article.
Let’s go one by one.
I don’t know the source you used for this. So I showed Claude the quote above and asked “Are there any studies comparing the health of Mormons vs. Adventists?”
Great question — this is a claim that circulates in nutrition debates, so let me search for what the research actually shows.This is a really interesting question, and the claim you’ve quoted doesn’t hold up well under scrutiny. Here’s what the research actually shows:
Yes, there are direct comparisons — and they don’t support the claim that Mormons outlive Adventists.
The key study to know about is Grundmann (1992), published in Archives of Anatomy, Cytology, and Pathology, which directly compared cancer mortality between US Mormons and Seventh-day Adventists. Life expectancy was generally elevated by 2–4 years in both Mormons and Seventh-day Adventists compared to the general population. The study found them broadly comparable, not that Mormons clearly outlived Adventists.
The numbers, side by side:
The UCLA “Mormon Longevity Study” (Enstrom & Breslow, 2008) followed ~9,800 religiously active California Mormon couples from 1980–2004. Mormon males had a life expectancy of 84.1 years, about 9.8 years longer than US white males, and Mormon females had a life expectancy of 86.1 years, about 5.6 years longer.
The Adventist Health Study-1, covering ~34,000 California Adventists, found that AHS-1 men lived 7.3 years longer and women 4.4 years longer than other Californians. But crucially, when looking specifically at vegetarian Adventists, men lived 9.5 years longer and women 6.1 years longer — essentially matching or slightly exceeding the Mormon figures.
Why the naive comparison is misleading:
The quote you shared makes several errors worth flagging.
First, these studies used different methodologies, reference populations, time periods, and selection criteria. The Mormon study focused on the most devout subset (“High Priests”), while the Adventist studies included a broader church membership. Active Mormons, defined as High Priests and Seventies, abstain almost completely from tobacco, alcohol, coffee, and tea — so the Mormon study was already selecting for maximal compliance. Comparing a highly selected Mormon subgroup to all Adventists and concluding meat-eating is fine is a classic apples-to-oranges problem.
Second, the claim that diet is the key variable being tested ignores that both groups share many health-promoting behaviors: no smoking, no alcohol, strong community ties, regular church attendance, strong family structures. Among a study of 34,192 faithful Seventh Day Adventists, researchers found that this way of life also conferred an extra 10 years of life. The social and lifestyle confounders are massive.
Third, and most relevant to your interest in veganism specifically: the Adventist Health Study-2 (AHS-2) provides the best data we have, because it compares vegetarians, vegans, pesco-vegetarians, and meat-eaters within the same religious community, controlling for all those shared lifestyle factors. Compared with nonvegetarians, vegetarians had lower risks of overall mortality, and specifically from renal failure, infectious disease, diabetes, cardiac causes, and ischemic heart disease. Compared to lacto-ovo-vegetarian diets, vegan diets seem to offer additional protection for obesity, hypertension, type-2 diabetes, and cardiovascular mortality.
That said, higher cause-specific neurologic mortalities were observed among older vegetarians, specifically for stroke and dementia, so the picture isn’t uniformly favorable at advanced ages.
Bottom line: The claim that “Mormons live longer than Adventists, therefore meat-eating is fine” is a significant oversimplification. The studies don’t clearly show Mormons outliving Adventists at all — and within Adventists, where you can actually control for lifestyle confounders, vegetarians (including vegans) consistently show lower mortality than meat-eating Adventists. The quote you shared is a rhetorically effective argument but not a scientifically sound one.”
See this comment.
I agree with the general claim that its harder to consume high amounts of calcium on a vegan diet, but not clear by what you mean by “high enough”.
Its more complicated than that? The linked paper is a meta-analysis and that result is only based on two studies that assessed depression as a categorical variable:
From the paper:
“(...) vegetarians and vegans had a higher risk of depression when depression was assessed as a categorical variable (...), but heterogeneity among studies was high (...). In addition to the significant heterogeneity between the 2 studies, conclusions are tentative because the analysis only included 2 studies.”
Regarding the studies that assessed depression as a continuous variable:
(...) no statistically significant differences were found between vegetarian or vegan diets and omnivores regarding the incidence of depression (...). Heterogeneity among studies for depression was very high(...). Subgroup analysis showed a statistically significant higher incidence of depression in vegetarians/vegans under 26 years of age(...), and in studies with higher quality assessment scores (...). Subgroup analyses of sex (...), the length of time the diet was followed (...), the type of diet (vegan vs vegetarian (...)), or the instrument used for assessment (...) did not show any significant differences between vegetarians/vegans and omnivores. Heterogeneity was more pronounced in those over 25 years of age (...), in studies that included mainly women (...), in short-term studies ((...), in studies that included vegans (...), in studies that used instruments other than the Depression Anxiety Stress Scales tool (...), and in lower-quality studies (...).
The same meta-analysis also shows lower anxiety scores for vegetarians/vegans.
The authors also speculate about the possibility of reverse causation.
“One possible explanation for these associations is a reverse causal relationship between vegetarianism or veganism and mental health outcomes. Individuals who have psychosocial disorders may be more eager to follow a vegetarian or vegan diet in order to improve their mental health. In a German study, the age at which a diet is adopted showed that a vegetarian diet was adopted after the onset of mental disorders, thus confirming the possibility of reverse causation.42 Still, 1 intervention study reported an improvement in depression, anxiety, and mood after adoption of a vegan diet,17,20 while another found improvements in stress but no significant changes in depression, anxiety, or mood in omnivores who adopted a vegetarian diet for 2 weeks.19”
Basically, its messy.
See this comment.
After eyeballing the study / asking Claude to summarise it, this checks out. Something interesting is that the higher risk of fracture was still significant for vegans even when the analysis was restricted to people meeting the guidelines for calcium and protein consumption!
Some interesting comments from Claude after I asked it to summarise the study
Why you should be very cautious about this study:
The fundamental problem is the ecological fallacy — which the authors themselves acknowledge but then largely brush aside. This study compares countries, not individuals. Countries that eat more meat are also wealthier, have better healthcare systems, cleaner water, better sanitation, more stable governments, and countless other advantages that extend life. While they control for GDP and urbanization, these are crude proxies that can’t capture the enormous complexity of what makes populations in wealthy countries live longer than those in poor ones.
To illustrate: the correlation they’re finding is essentially that Norway, Japan, Australia, and France eat more meat and live longer than Chad, Niger, and Sierra Leone. This is true, but the causal interpretation — that meat is why they live longer — is an enormous leap. GDP alone explains over 50% of the variance in life expectancy in their own regression (R² change = 0.509), and meat only adds about 3% explanatory power on top of that. The authors frame this 3% as important, but given the massive residual confounding inherent in cross-country comparisons, it could easily be capturing unmeasured aspects of development and wealth.
Other methodological concerns:
The food data are supply figures, not actual consumption — they don’t account for food waste, which varies enormously between rich and poor countries. The study is cross-sectional, comparing countries at one time point, yet the relationship between diet and longevity is inherently longitudinal. The confounders controlled for are quite limited — they don’t include healthcare expenditure, access to clean water, infectious disease burden, political stability, inequality, or dozens of other factors that differ systematically between high-meat and low-meat countries.
The discussion section also reveals a fairly strong pro-meat agenda. The authors make evolutionary arguments about human adaptation to meat eating, dismiss vegetarianism studies as flawed, and cite the NutriRECS guidelines (which were themselves highly controversial in the nutrition community). They claim their findings “unequivocally” indicate that meat eating benefits life expectancy — language far too strong for an ecological correlation study.
See this comment.
Yeah. Unfortunately the whole recommended B12 daily-dose situation is confusing:
“It should be noted that a once-daily dose of this nutrient at the Reference Nutrient Intake level (the level typically found in multivitamin supplements, including some of those marketed toward vegans, whereas single nutrient supplements of vitamin B12 often contain considerably higher levels) may not be sufficient for maintaining adequate B12 status 52(https://pmc.ncbi.nlm.nih.gov/articles/PMC4844163/#bb0260). The rate of absorption of vitamin B12 is limited by the capacity of ileal receptors for phagocytosis of vitamin B12–intrinsic factor complex and decreases along with increasing amounts of this vitamin in a single meal or a single supplement administration 33(https://pmc.ncbi.nlm.nih.gov/articles/PMC4844163/#bb0165)”
Meaning a lot of people might be taking daily B12 supplements but still be deficient. I agree that getting vegan supplements right might be hard to a lot of people.
Right. Its a small study, though and one that has the potential to have a selection bias (vegetarian women were recruited from Seventh-day Adventist church newsletters and non-vegetarians through newspaper ads). I wouldn’t make any life changes just based on this one.