Most blood work comes as a PDF from a lab, sometimes a digital document, sometimes a scan of a printed page, occasionally a photo taken with your phone. Your lab report contains dozens of numbers, units, and reference ranges. Manually reading, interpreting, and cross-referencing that information across multiple markers takes 30-60 minutes, even for someone who knows what they are doing.
GearCheck handles the whole thing from start to finish. You hand it a raw lab document, and it turns that into a structured, contextualized health analysis in under five minutes. Here's what actually happens in that window.
⚙️A blood work PDF is just a list of numbers. GearCheck turns it into a health story — one that accounts for your muscle mass, your training, your AAS protocol, and your individual history.
Step 1: Upload and Parsing
It starts with the file. Upload your lab PDF or image, and the system extracts the text immediately. But files aren't all the same, and the system handles each type differently:
Upload & Parsing
Digital PDFs are parsed directly using text extraction: marker names, values, and reference ranges are identified programmatically. No OCR needed, no quality loss. This is the fastest path through the pipeline.
Scanned PDFs and images go through OCR (optical character recognition) to convert the image into machine-readable text. The system detects when OCR is needed automatically and adjusts its parsing strategy.
A preflight check counts how many markers were extracted; if that count is too low, for example if you uploaded an image of a blood pressure log instead of a lab report, you're alerted before the analysis starts. This saves you from waiting five minutes only to get an error.
Your report gets processed within seconds. Every marker gets identified and structured into a standardized format, no matter which lab generated the original PDF.
Marker Extraction (Dual Engine)
Now the real work begins. The extracted text gets pushed through two parallel engines that run in sync, making sure no marker slips through the cracks.
Regex extraction: pattern-matching pulls out common markers with known naming conventions. This runs first and captures the low-hanging fruit: well-labeled panels from standard lab formats like "Comprehensive Metabolic Panel" or "Lipid Panel." It is fast, deterministic, and catches the most common markers instantly.
The Gemini AI extraction uses a large language model that reads the entire document in context, handling unusual panel names, non-standard layouts, foreign language reports (Dutch, German, French, Spanish, all common in European labs), and markers that do not match any pre-defined pattern. This catches everything the regex pass misses.
Both passes are cross-referenced. Markers found by both engines are flagged as high-confidence, while those found by only one pass are validated against known marker lists and typical units. The result is a structured dataset of every marker in your blood work, mapped to canonical names and values, regardless of how the original lab labeled them.
Quality Gate
Before anything else, the system verifies that your blood work is analyzable. This quality gate blocks analysis from proceeding on incomplete or implausible data:
Minimum marker threshold: a complete profile requires at least some markers from each key system: kidney, liver, cardiovascular, glucose metabolism. If too many systems are missing markers, the panel is flagged as incomplete.
Critical markers present: if too few markers are present across too few body systems, or the ones that specifically answer whether a given system is healthy are missing, the system flags the panel as insufficient rather than scoring a thin, unanswerable dataset as if it were a clean bill of health.
Value plausibility: extreme outliers that suggest transcription errors are flagged for review (e.g., a hematocrit of 85% is almost certainly a data error, not actual blood thickness). This catches OCR errors and lab typos before they reach your report.
Reference Comparison
Each extracted marker is now compared against GearCheck's reference database, but not the standard lab ranges your licensed medical professional uses. The system applies athletic reference ranges, meaning the comparison starts from a realistic baseline for someone who trains, eats a high-protein diet, and may use AAS:
Every marker gets a status. Optimal sits inside its athletic-adjusted band. Suboptimal is just outside it. Monitor is measurably outside and worth following across panels. Review is substantially outside, or escalated because neighbouring markers corroborate it. Context is outside the band but explained by a rule, like muscle-origin AST or an eGFR artefact. Descriptive is informative rather than risk-bearing, like suppressed LH on exogenous androgens. The last two are excluded from the score rather than penalised.
Trends from previous uploads are incorporated: a marker that has been stable for 6 months gets a different interpretation than one that spiked suddenly. This is where having multiple uploads pays off, because the system can distinguish your chronic state from acute changes.
A status is not the same as a verdict. A marker landing in Context or Descriptive isn't hidden from the report — it's shown, with the reasoning for why it's excluded from the score, so you can judge for yourself whether that reasoning actually holds for your situation rather than just taking the exclusion on faith.
Contextual Rule Engine (20+ Rules)
This is the step that makes GearCheck fundamentally different from every other blood work analyzer. It applies 20+ contextual rules tailored to athletes using AAS, and those rules prevent the false positives that athletes routinely get from standard medical interpretation:
The muscle leak rule: elevated AST/ALT with elevated CK and normal GGT = muscle origin, not liver damage. This is one of the most commonly misread patterns in athlete blood work generally.
The kidney adjustment rule: elevated creatinine with normal Cystatin C in high-muscle-mass individuals = artifact, not kidney impairment.
The AAS lipid rule: suppressed HDL under AAS is a pharmacological effect. The system shifts focus to ApoB and LDL particle count, which are better predictors of actual cardiovascular risk.
The hematocrit rule: hematocrit is interpreted with compound risk, blood pressure, and the athlete's baseline over time, not against a single population-based cutoff.
Report Assembly & Narration
All of it combines into one complete health analysis:
A Health Score is calculated as a single number from 0 to 100 that summarizes overall health status across all body systems, weighted by clinical significance.
The report is assembled by body system: kidney, liver, cardiovascular, hematology, hormones, metabolic, and electrolytes. Each section gives you the key markers, their values, their status, and what to do about them.
Narration is generated: each section includes a written analysis that explains what each marker means in your context, not just the number. The narration connects related markers, highlights patterns, and explains why certain values are expected given your protocol.
Key findings are highlighted: the most important patterns and changes across all systems, prioritized by clinical relevance.
The result is a comprehensive health analysis that would take a human specialist 45-60 minutes to produce, and it's delivered in under 5 minutes.
The Complete Pipeline — One Flow
Why the Pipeline Matters
Manual blood work analysis is not just time-consuming, it is error-prone. Humans miss trends, and a licensed medical professional without an athletic-population reference point tends to default to the general-population range they know. The pipeline addresses each of these failure modes systematically:
Speed
The pipeline handles a typical profile in under 5 minutes. Doing that same work manually eats up 30-60 minutes and still comes out less accurate.
Trend Tracking
Every upload adds to your history, letting the system detect trends across time that no single lab visit can show.
Context
Athletic reference ranges exist for a reason, and they work alongside 20+ contextual rules to keep you from chasing ghosts. Standard labs are built for the general population, not for guys running AAS, so they'll flag things that aren't actually problems. Those false positives get filtered out when you apply the right reference points and read the numbers in context.
Athlete-Calibrated Ranges
Your results are read against reference bands built for people who train and may use AAS, not the general-population ranges printed on the lab report. That distinction matters, because a guy running 500 mg of test a week with a heavy training load has a genuinely different normal than a sedentary office worker, and the standard range was calibrated on the latter.