Physiologist · Researcher · Builder
I research bioinformatics/omics and physiology tech, build tools at the intersection of physiology and machine learning, and write about training, metabolic health, and how the science actually plays out in a life. Funspan is the framework tying it together.
What I'm Building
Company
CPET interpretation software for performance and clinical labs. Reinterprets raw breath-by-breath data into a defensible clinical report — thresholds, substrate use, glycogen modeling, economy. In pilot at Hybl Performance Center.
aevox.health →Products
Coach-first longitudinal physiology dashboard. Metabolic efficiency, economy, and fatigue resistance tracked over time.
funspan.health →Personalized endurance fuel — dual-source carbs and electrolytes formulated from your CPET data. Your numbers on the label.
Research Tools
Predicting metabolic substrate use — VO₂, RER, fat and carbohydrate oxidation — from consumer wearable signals. Physiology-grounded ML.
More →135 biomarkers, 519 evidence cells linking labs to mortality, CVD, dementia, frailty. Citation-backed, open source.
GitHub →Selected Research
A sex-dimorphic thermodynamic-framework analysis of the MoTrPAC rat endurance training dataset. 85 redox-relevant genes, 42,770 observations across 19 tissues, 5 omic layers, 4 training time points. Redox buffering scales significantly sub-linearly with electron transport system expansion in both sexes — with distinct quality-control architectures (mtUPR / mitophagy in males, AMPK in females).
First published independent validation of the MGC Meridian, and the first MGC-vs-Douglas comparison during maximal treadmill running. Nine athletes, 17 paired observations, Bland–Altman across VE, VO₂, VCO₂, RER. Headline: the cart overestimates VO₂ by 6.5% (p<0.001) and underestimates RER by 4.6% (p<0.001) at maximal effort — a non-trivial bias for any lab using MGC for VO₂max-based decisions.