getbased can read lab reports from virtually any provider worldwide. Drop a PDF on the dashboard and the AI extracts every result, maps it to a known biomarker, and shows you a preview before saving anything. Your personal information is stripped before the file reaches your AI provider.Documentation Index
Fetch the complete documentation index at: https://docs.getbased.health/llms.txt
Use this file to discover all available pages before exploring further.
Before you start
You need an AI provider configured in Settings → AI Provider. Manual entry does not require AI, but PDF import does.Import a PDF
Open the dashboard
Navigate to the getbased dashboard. You can import from here at any time — you do not need to be in a specific view.
Drop or select your file
Either drag your PDF anywhere onto the dashboard, or click the import button (document icon, bottom-right corner) to open a file picker.
Wait for AI analysis
getbased processes the file locally, strips personal information, then sends the anonymized text to your AI provider. This typically takes 5–20 seconds.
Review the import preview
Before anything is saved, you see exactly what the AI found. Review each row and exclude anything you don’t want by clicking the × button. The button toggles to + so you can re-include rows.
Pre-flight checks
Before analysis begins, getbased runs two automatic checks:- Model mismatch — if you have changed your AI model since your last import, a warning explains that different models may assign different internal keys to the same marker. You can continue or switch back to your previous model.
- PII scan — a notification confirms that personal information (name, address, date of birth, ID numbers) will be stripped before the file is sent to your AI provider.
Understanding the import preview
The preview table shows each result the AI found, the value, the lab’s reference range, and how it was mapped. Each row has one of three status colors:- Green — Matched: the marker was recognized and mapped to a known biomarker (e.g., glucose, TSH, ferritin).
- Blue — New: the marker is not in the built-in list. getbased creates it automatically as a custom marker with an AI-suggested name, unit, and reference range.
- Yellow — Unmatched: the AI found a result but could not confidently map it. Review these rows manually before confirming.
Reference range adoption
When the reference ranges on your PDF differ from getbased’s stored ranges, a toggle appears below the preview table: “Update reference ranges from this report (N markers)”. This is checked by default. Accepting it saves the lab’s own ranges — including open-ended ranges like eGFR >59 — as per-marker overrides that apply going forward.Unit normalization
Enzymes reported as IU/L (ALT, AST, ALP) are automatically mapped to U/L. No manual correction is needed.Batch import
To import multiple PDFs at once — for example, several years of annual blood work — select or drag multiple files at the same time. getbased processes them one at a time, showing you the preview for each file in sequence. A counter tells you which file you are on (e.g., “File 2 of 5”). For each file you can Confirm to save or Skip to discard and move on. If a file fails due to a network error, getbased retries it once automatically before offering the option to skip. The dashboard refreshes once at the end of the batch rather than after every file.Back up your data before a large batch import using Settings → Backup & Restore or by exporting a JSON snapshot first.
Scanned PDFs and image imports
Most lab PDFs contain selectable text. If your PDF is a scanned image, getbased detects this automatically and switches to image mode, rendering each page as a screenshot for the AI to read visually. You can also import lab reports saved as photos or screenshots directly — JPG, PNG, and WebP files go through the same image pipeline as scanned PDFs.Specialty lab detection
getbased automatically detects non-blood tests in your PDF — OAT, DUTCH, HTMA, fatty acid panels, and more. The AI identifies the test type and routes markers through the specialty pipeline, using the reference ranges from your lab report rather than built-in defaults. See Import specialty lab panels for details.Privacy during import
Your PDF is processed locally first. Personal information is stripped before anything is sent to your AI provider. See the Privacy guide for full details on how PII obfuscation works.What gets extracted
getbased tracks 300+ biomarkers across 17 categories, including:- Biochemistry — glucose, liver enzymes, kidney markers, electrolytes
- Hormones — testosterone, estradiol, cortisol, DHEA, insulin
- Lipids — cholesterol, triglycerides, LDL, HDL, ratios
- Hematology — CBC, red and white cell indices
- Thyroid — TSH, T3, T4, antibodies
- Body Composition — body fat %, lean mass, visceral fat (from DEXA scans)
- Bone Density — BMD, T-scores, Z-scores (from DEXA scans)
Common questions
Can I import the same PDF twice? If you import a report for a date that already has data, the new values are merged with the existing ones. Existing values are not overwritten. In Settings → Data, hover over a date that shows “2 files” to see which filenames contributed. What about below-detection-limit values like<0.5?
These are imported at the detection limit value itself (<0.5 becomes 0.5). The data point is preserved and shows that the marker was tested.
Can I undo an import?
Not directly after confirming, but you can use Settings → Backup & Restore to roll back to an automatic snapshot taken before the import.