How Wearables and Biology Work Better Together
Wearables show what life looks like from the outside. Biology helps show what may be changing on the inside. BioTwin brings those two layers together.
Founder and editorial stories, scientific publications, white papers, and plain language explanations.
Wearables show what life looks like from the outside. Biology helps show what may be changing on the inside. BioTwin brings those two layers together.
Population averages can be useful, but they do not always capture what is normal for one individual. BioTwin is designed to understand change relative to your own baseline.
BioTwin does not use the phrase 30,000 biomarkers to sound impressive. It matters because deeper biological measurement creates a richer picture of what is happening inside the body.
BioTwin's virtual twin is designed to support clearer longitudinal health understanding today, while broader medical and clinical capabilities remain in development.
A simple explanation of what a human virtual twin is, why it matters, and how BioTwin uses biology, behavior, and time to build a more useful picture of health.
A one-time result can be helpful, but it cannot fully explain how your biology is changing. BioTwin is built around trajectories, not snapshots.
Scientific overview of BioTwin's medical research methodology, validation approach, and clinical development pathway.
Scientific overview of BioTwin's non-medical virtual twin technology, including longitudinal biomarker tracking, personal baseline modeling, and wellness-only interpretation.
A blood test is a snapshot. A human body is a film. The founding idea behind BioTwin: a person should be understood as a trajectory, not a single measurement.
A blood test is a snapshot. A human body is a film. The founding idea behind BioTwin: a person should be understood as a trajectory, not a single measurement.
One word covers too many biological realities. BioTwin's fatigue work treats fatigue as a measurable state space, not a single symptom.
Cancer prevention is personal before it is scientific. Why preventive health needs to move from isolated detection events to continuous biological context.
A diet change is easy to declare and harder to verify. How longitudinal metabolomics shows what actually appeared in the body when the founder went vegan.
The body does not respond to intention. It responds to inputs. Why a virtual twin turns nutrition from a belief system into a learning system.
The body keeps receipts. Why caffeine and alcohol are personal pharmacology hiding inside everyday habits, and what longitudinal data reveals.
A flight is not one event in the body. It is a sequence. Your itinerary says when you arrived. Your biology says when you recovered.
Wearables are useful. They are also incomplete. When devices disagree about the same body, which one should you believe?
Effort is not the same thing as capacity. The most dangerous number in performance is not the workout you completed. It is the debt you did not know you created.
The most useful comparison in health may not be you versus everyone else. It may be you versus you. The Me vs. Me thesis behind every BioTwin score.
Biological age is often presented as a verdict. It is also incomplete. A body is not a static number. It is a trajectory.
The founder dataset is not the finish line. It is the stress test. How a single dense individual case becomes the architecture for population-scale preventive medicine.
A comprehensive overview of BioTwin's virtual twin methodology, how multi-omics data, machine learning, and longitudinal tracking combine to create individualized health models.
How metabolomic profiling captures real-time biological state, and why it's essential for meaningful health prediction beyond genomics alone.
How tracking biomarkers over time reveals health trajectories invisible to single-point assessments, and what this means for preventive care programs.
Preprint by Anctil, Hauguel, and Noel showing that untargeted metabolomics from a single dried blood spot detects breast cancer across 2,734 participants, with performance that is robust across six classifier families.
Why it matters: Demonstrates that BioTwin's same-lab dried blood spot LC-MS protocol, the one validated for individual identification, carries enough signal to detect breast cancer at scale, with batch-aware validation that avoids the optimistically biased estimates common in the field.
Preprint by Hauguel, Anctil, and Noel demonstrating that metabolomic profiles from dried blood spots are stable enough to identify individuals across 18,288 samples and 134 analytical batches.
Why it matters: Establishes the methodological foundation for personal-baseline interpretation of longitudinal biomarker data, the core mechanic behind BioTwin's virtual twin model. The same-lab DBS LC-MS protocol and the GroupKFold batch-aware validation standard introduced here underpin all of BioTwin's downstream disease classification work.
Preprint by Hauguel, Noel, and Anctil quantifying how poorly four consumer wearables agree with each other across an N-of-1 dataset spanning more than 2,400 days, and how much a harmonization layer can recover.
Why it matters: Wearable signals are a core input to the virtual twin, so knowing exactly where two devices disagree, and by how much, is a prerequisite for combining them. This work shows that identical metric labels do not guarantee comparable measurements and that device-specific recalibration is often needed.
Peer-reviewed open-access study (Digital Twin, 2024) by Fradin, Noel and colleagues, the foundational BioTwin work showing that untargeted metabolomics from dried blood spots can profile and identify individuals across 277 volunteers.
Why it matters: This is BioTwin's foundational, peer-reviewed publication. It first demonstrated that a self-collected dried blood spot carries enough metabolomic signal to profile and identify an individual, the proof of concept that the large-scale 1,257-participant identification preprint and the disease-detection work were later built on.
Scientific documents explaining BioTwin's validation work, research methodology, and how the virtual twin technology is developed and evaluated.
Scientific overview of BioTwin's medical research methodology, validation approach, and clinical development pathway.
Scientific overview of BioTwin's non-medical virtual twin technology, including longitudinal biomarker tracking, personal baseline modeling, and wellness-only interpretation.
Wearables show what life looks like from the outside. Biology helps show what may be changing on the inside. BioTwin brings those two layers together.
Population averages can be useful, but they do not always capture what is normal for one individual. BioTwin is designed to understand change relative to your own baseline.
BioTwin does not use the phrase 30,000 biomarkers to sound impressive. It matters because deeper biological measurement creates a richer picture of what is happening inside the body.
BioTwin's virtual twin is designed to support clearer longitudinal health understanding today, while broader medical and clinical capabilities remain in development.
A simple explanation of what a human virtual twin is, why it matters, and how BioTwin uses biology, behavior, and time to build a more useful picture of health.
A one-time result can be helpful, but it cannot fully explain how your biology is changing. BioTwin is built around trajectories, not snapshots.