This is what happens when VoloAthlete and world-champion Jordan Stolz visits the office.
We may or may not be practicing crossovers between conference rooms...
The connection between speedskating and data science?
Full story on our latest Vitality Vision podcast: https://t.co/oxKwaaYqoK
@danielDaniel Hammack was our first intern back in 2011. We met at his high school science fair where he was presenting a natural language processing project.
Offered him an internship right on the spot. He had to search what a hedge fund was.
Spoiler alert: He said yes.
Fifteen years later, he's on our executive team.
In our latest Vitality Vision podcast, Daniel and I talk about that journey, but also about something bigger: what happens when you apply rigorous data science to problems that matter.
The conversation reminded me why we built this firm the way we did: find the best problem solvers, give them hard challenges, and let the data guide the conclusions.
Nobody expected cheese to be the winner…
When we analyzed dietary patterns across large health databases, most findings confirmed what we suspected: less red meat, better outcomes.
But cheese? The pattern went the opposite direction. More cheese consumption correlated with lower prevelance of diseases.
Now, this doesn't mean cheese is the answer. Correlation does not imply causation, and it means dietary science is far more complex than most headlines suggest.
We jokingly call it the "cheegan diet": mostly plant-based whole foods, plus cheese and maybe some red wine.
Is it the cheese itself? The lifestyle factors that come with moderate cheese consumption? The type of cheese? We don't know yet. But that's exactly why we need better data analysis.
More insights here: https://t.co/bghPqkLDlq
What does your grip strength say about your health?
More than you might think.
In our latest Vitality Vision episode, we explore with Dr. Tommy Wood the fascinating connection between grip strength and overall health, especially brain health.
The research is clear: grip strength is a powerful biomarker that reveals insights about our physical and cognitive well-being.
Check out the full episode: https://t.co/siYO4ggSi6
The data agrees… it’s never too late to quit smoking.
The long-term risk curves show something encouraging: the benefits of quitting are substantial regardless of how long someone has smoked.
Even someone who’s smoked a pack a day for 40 years can reduce their lung cancer risk by 75%.
Let data be a motivator for better outcomes.
Check out the full presentation to learn more about what data is saying about health: https://t.co/t6mTXegd0S
What would healthcare look like if it truly used data? Not dashboards. Not medical records filled with noise. Real, outcome-focused, personalized data.
Three fundamental shifts would happen:
- Decisions would be evidence-based. You'd know which markers actually predict your outcomes, not just population averages
- Personalization would be possible. In a data-driven system, it means understanding your complete biological signature, genetics, biomarkers, behaviors, and how they interact to shape your risk profile.
- Transparency would be the default. Patients would understand why they're being told what they are, rather than reconciling contradictory advice.
We have the technology. We have the data. The challenge is to build systems that integrate information at scale and with precision.
For more insights on how we are approaching this, check out our full presentation at Eudemonia: https://t.co/t6mTXegd0S
$20~ can go a long way toward predicting a cardiac event...
Cystatin C, one of the most underrated markers, consistently ranks among the top predictors of health outcomes.
Most people never test it.
Most doctors don’t order it until there’s already evidence of kidney damage.
And by then, we may have missed years of early warnings.
Overlooking a top predictor simply because it isn’t “standard practice” leaves meaningful signals on the table. If we want to move healthcare from reactive to proactive, we need to measure the biomarkers that truly tell the story, not just the ones we’ve historically paid attention
It was a pleasure having Amy R. Mack on the Vitality Vision by Volo podcast to discuss how functional medicine is shaping the future of preventative health.
An insightful conversation with someone who’s leading real change in how we think about health and wellness.
Check out the full conversation: https://t.co/vA1ZOYigVL
At @EudemoniaSummit I had the chance to share some of the patterns we’ve uncovered in our research. Specifically, how predictive certain biomarkers can be long before a diagnosis ever appears.
The takeaway is simple, but one that I often repeat.
If you want a clearer, more accurate picture of your health, add these five biomarkers to your routine blood work:
• HbA1c
• Cystatin C
• CRP (C-Reactive Protein)
• ApoB (particularly because of the LDL/ApoB ratio)
• GGT (Gamma-Glutamyl Transferase)
The point isn’t to overwhelm people with data, it’s to start asking better questions and measuring what actually matters. When we do that, we move from reactive care to proactive insight.
Grateful to everyone who contributed to such thoughtful conversations at Eudemonia.
One of the most encouraging patterns we’ve seen in our work is how quickly metabolic health can improve when you identify the indicators quickly.
We’ve seen individuals clearly on the path toward type 2 diabetes, with elevated fasting insulin, steadily increasing A1C, and an inability to lose weight easily. By identifying these patterns early, they have been able to reverse course and improve their metabolic scores in as little as six months.
It’s about shifting from reactive to proactive care, while change is still possible. This is why measuring the right biomarkers matters.
When we talk about long-term health, most of the focus goes to the heart. We measure cholesterol, we track blood pressure, and we ask our doctors about cardiac risk.
Yet, our models have found that kidney health predicts mortality more strongly than cardiac health itself.
One finding stood out:
Among 70-year-olds, those with the healthiest kidneys had a 30% lower risk of mortality than those in the top 5% for cardiac health.
Despite this, kidney function markers like Cystatin C, aren’t part of most standard blood panels. And awareness around kidney health remains low, even though it quietly influences risk for cardiovascular disease, dementia, and overall longevity.
If we want to move from reactive to proactive care, kidney health needs to be part of the conversation.
Explore our Biomarker Reference Guide to see where kidney markers rank across diseases: https://t.co/41MJPuSXoI
I often get asked: Which biomarkers should I add to my routine blood tests to get a clearer picture of my health?
In addition to the standard panel, which typically includes lipid levels, a comprehensive metabolic panel (CMP), and a complete blood count (CPC), adding just six more biomarkers allows you to capture 95% of the predictive value of our models.
Here are the six most predictive biomarkers that are often missing from routine bloodwork, and can provide a much deeper, data-driven view of your health:
HbA1C
Cystatin C
CRP (C-Reactive Protein)
ApoB (specifically because the LDL/ApoB ratio is highly predictive, as we’ve seen in our Biomarker Reference Guide)
GGT (Gamma-Glutamyl Transferase)
Insulin (coming soon)
Has your health ever been misrepresented because of your BMI?
My analysis show that waist circumference is not only more predictive of outcomes than BMI, but also far less biased.
BMI is calculated by dividing weight by height squared, which systematically disadvantages shorter individuals and advantages taller ones. It’s a formula that was never designed to capture the complexity of human health, yet it’s still widely used as a gold standard.
Waist circumference, on the other hand, offers a direct and consistent signal. It may represent visceral fat distribution, a major driver of metabolic and cardiovascular risk, without the structural biases baked into BMI.
It’s time we re-examine the metrics we’ve taken for granted. Data gives us the opportunity to replace outdated measures with better, more predictive ones—and waist circumference is a strong candidate.
Check out our latest episode: https://t.co/xQxXGEMnDs
When we ranked the TOP biomarkers for predicting major diseases, one pattern really surprised us:
High LDL cholesterol did not make the list.
Across outcomes like heart disease, kidney failure, liver disease, and mortality, LDL didn’t even rank in the top 10 according to our predictive models.
The one exception?
Dementia. And even there, the stronger signal wasn’t high LDL, it was low LDL.
For heart disease, LDL ranked 22nd.
This doesn’t mean LDL isn’t relevant. It means that if we want a clearer picture of risk, we have to look beyond a single marker and consider the broader network of biomarkers
This is the shift we’re working toward: moving from single-marker thinking to multi-biomarker models that better reflect the complexity of human health.
One of the most powerful aspects of predictive modeling is not just seeing where your health is today, but where it’s heading, and how that trajectory can change.
In this example from our research, we looked at the data of a 55-year-old. Today, their risk might not seem especially high. But if their biomarkers continue on the same path to age 70, the model shows a substantial rise in risk.
The encouraging part? We can test hypothetical changes, for example:
Quitting smoking
Reducing BMI from 30 to 23
Improving kidney function (tracked through cystatin C, one of our top predictors)
The model shows how each of these shifts improves the trajectory of health.
For individuals, this kind of feedback can be motivating. Your numbers aren’t fixed, and neither is your future risk. For practitioners, it offers a more precise way to guide interventions, grounded in data.
When it comes to cardiovascular health, most doctors and studies look at one marker (LDL cholesterol) and one outcome (cardiac events).
But is that the whole picture?
When we analyzed individuals with no prior conditions—no cancer, no heart attacks, no metabolic or kidney disease—we saw something striking:
Those in the “lucky” 5% with LDL within the “typical healthy range” (LDL lower than 100) had about a 20% reduction in cardiac events compared to the average.
Important, yes.
But when we broadened the lens, we found that those lucky folks whose LDL was “in range” saw a meaningful increased risk across multiple outcomes, including respiratory disease, liver disease, dementia, kidney failure, and even all-cause mortality.
So why aren’t we looking at those, too?
Why are we limiting our understanding of risk to just one marker and one outcome, when health is clearly more complex?
In our work, expanding beyond single markers has revealed patterns that traditional approaches often miss. This shift is essential if we want to move from treating disease to truly predicting and preventing it.
This year, I spoke at the INSTITUTE FOR FUNCTIONAL MED Annual Conference. Here are three takeaways from my talk at IFM, looking at health through a data science lens:
1. The health system needs to utilize data.
We have the tools to track and model disease risk with greater precision than what’s used in standard care. But decisions are still being made on incomplete information.
2. The top predictors aren’t the ones most people track
Across major disease outcomes, the two most predictive biomarkers we’ve found are Cystatin C and A1C. Both are inexpensive to test yet rarely included in standard panels. They are worth asking your doctor about.
3. LDL is not telling us the full story.
Cholesterol matters, but our data shows that markers like HDL cholesterol can offer a more accurate view of risk than LDL, when interpreted in context.
The big picture: If we want to prevent disease, we need to broaden what we measure and shift how we use that data to guide decisions.
Watch the full presentation: https://t.co/jsKzRMibJs
Pleased to announce that Voloridge Health has invested in Molecular You, a company advancing the frontier of precision health through rigorous science and data-driven discovery.
By moving beyond traditional blood biomarker panels into metabolites and proteomics, they’re uncovering earlier and stronger signals of disease and mapping the molecular pathways that drive those health outcomes.
Their comprehensive approach is deeply aligned with our work at Voloridge Health. Both teams share a commitment to following the data to better understand health trajectories and improve disease prediction.
This investment aligns with our mission to move from reactive to proactive healthcare.
https://t.co/HbzPDMNl1D
We recently added a new category to our Biomarker Reference Guide!
Nutraceuticals include dietary supplements and functional foods, vitamins, minerals, and bioactive compounds like fish oil, garlic, glucosamine, folic acid, zinc, and vitamin D, used to support health beyond basic nutritional needs. Nutraceuticals are common interventions in preventive and functional medicine, yet their impact on biomarkers is rarely tracked in a systematic way.
Supplement data provides critical context when interpreting labs. For example, nutraceutical use can influence biomarkers like CRP, triglycerides, or homocysteine.
The Biomarker Reference Guide is a free resource we created to map how over 50 biomarkers correlate with health issues such as cardiovascular disease, kidney failure, dementia, and more. It’s designed to make predictive data more accessible to practitioners and individuals alike.
Explore the latest update here: https://t.co/tW4Wd2ZYTg
When I turned 40, I decided to take my health more seriously.
Routine bloodwork showed my LDL cholesterol was out of range. So, I did what most of us would do: I started working out more. I worked out five times a week. I cut out sugary drinks and fast food, switched to whole foods, and felt fitter, stronger, healthier…
But my LDL? Still the same.
As a data scientist, that was the moment I realized, we’re missing something.
The way we measure health is too narrow. We rely on single markers and static ranges when we should look at patterns across systems—and use data science to analyze them.
If we apply data science to health care, we can:
·Identify the markers that truly predict long-term outcomes
·Personalize decisions based on patterns, not population averages
·Empower people with a clearer picture of their risk and how to change it.
This is the shift we’re building toward. And it starts with rethinking what we measure, and why.