Field Notes
Methodology, observations, and limits of a computational dermatology engine. Substantive pieces, dated and signed. What the engine does, how it measures itself, where the limits sit — published openly, including the unflattering results.
How Mela works
What the engine does, how it reads timing, and where it stays alongside medical care. →
Watch · the demonstrationsSee the method run
Five recorded demonstrations on synthetic data, one at a time — the interactive arm of these notes. →
-
Skin is a state, not a type
A methodology note. Why the oily-or-dry label you were assigned is a snapshot of a moving target, what makes skin shift across the day, the month, the season, and the decade, and why the honest read follows the state you are in now rather than a fixed type.
2,158 words 11 min read 5 citations -
Skin is a lagging indicator
A methodology note. Why the skin you see today is a slow readout of the past several weeks, why the newest change in your routine is the least likely explanation for what you see, and what that lag means for reading skin honestly.
2,258 words 11 min read 6 citations -
One day is not a signal
A limits note. Why a single day's read of your skin cannot tell a real change from normal fluctuation, what the noise is actually made of, and the hard limit that places on any tracker, Mela included.
1,762 words 8 min read 7 citations -
It's the irritation, not the purge
A category critique with the evidence. Why "purging" has become the default explanation for almost any early breakout, when the one defensible version of it is narrow and the popular version cannot be told apart from plain irritation in the two weeks people use to decide.
2,159 words 10 min read 5 citations -
It's the season, not the serum
A category critique with the evidence. Why the most common "my routine stopped working this fall" story is, more often than not, a seasonal shift wearing the timing of whatever product changed, and what it takes to tell the two apart.
2,305 words 11 min read 7 citations -
It's the cycle, not the serum
A category critique with the evidence. Why the most common "my new product broke me out" story is, for roughly half of women, a premenstrual flare wearing the serum's timing, and what it takes to tell the two apart.
2,288 words 11 min read 8 citations -
The wrong measurement problem
A literature review and category critique. Six layers of skin physiology the basic-science evidence treats as the signal, and what consumer skincare is failing to operationalize from them.
2,932 words 13 min read 8 citations -
How Mela sorts cause from coincidence
A worked example: causal-discovery procedure walked through synthetic 30-day skin data with a known ground-truth edge, showing where the procedure recovered the truth, where it found a spurious pattern, and how the hedging in user-facing copy is calibrated.
2,948 words 12 min read 10 citations