Synthetic data only. Never enter patient information; nothing is sent or stored. For clinicians. Not FDA cleared.For licensed clinicians. Educational demonstration on synthetic data. Never enter real patient identifiers or protected health information: everything runs in your browser and nothing is sent or stored. Clinical decision support only; not FDA cleared; physician review is required.
Biod clinical tools
Test the algorithm. Read every rule. See every step.
11 deterministic Clinical Pattern Engines, open to physicians: move the values, watch the pattern change, and open the rule that decided it.
One result, fully traced
- 1TSH 18.4 · FT4 0.6 · Anti-TPO 720inputs, with your lab's own reference ranges
- 2PR-HT-01 firedTSH above and FT4 below the range
- 3Overt primary pattern + autoimmune etiologytwo separate answers, never merged
- 4Physician adjudication requiredalways
Pick an engine
Each engine is a published specification: rules, thresholds, evidence and a synthetic test suite.
Endocrine
CPE-001 · v1.1.0
Thyroid Function Pattern Engine
Functional state from TSH and FT4, kept separate from etiology. Central disease and decompensation never hide.
7 rules · 15 scenarios
Open the playground →
CPE-006 · v1.0.0
Male Hypogonadism Pattern Engine
Symptoms plus low testosterone on two morning samples. The engine classifies, flags cautions, and never recommends starting therapy.
20 rules · 25 scenarios
Open the playground →
CPE-008 · v1.0.0
Adrenal Insufficiency Pattern Engine
Morning cortisol bands, ACTH and stimulation results, glucocorticoid exposure and the adrenal-crisis situations that cannot wait.
19 rules · 24 scenarios
Open the playground →
CPE-010 · v1.0.0
PCOS Pattern Engine
Two of three criteria in adults, irregular cycles plus hyperandrogenism in adolescents, and PCOS only after other causes are excluded.
22 rules · 26 scenarios
Open the playground →
Cardiometabolic
CPE-002 · v1.0.0
Insulin Resistance–Associated Metabolic Pattern Engine
Guideline criteria for glycemia and metabolic syndrome. Insulin resistance itself is never diagnosed from one number.
37 rules · 21 scenarios
Open the playground →
CPE-007 · v1.0.0
Cardiovascular Risk Pattern Engine
ACC/AHA categories applied to a risk you enter, with risk enhancers, Lp(a), apoB, calcium score and the 2022 LDL-C thresholds.
20 rules · 26 scenarios
Open the playground →
Hematology and nutrition
CPE-004 · v1.0.0
Iron Deficiency Pattern Engine
Iron status from ferritin and transferrin saturation, read correctly when inflammation, heart failure or kidney disease changes the rules.
29 rules · 25 scenarios
Open the playground →
CPE-009 · v1.0.0
Vitamin B12 and Folate Pattern Engine
Serum B12, MMA and homocysteine read together, folic acid never ahead of B12, and neurologic involvement kept in front.
17 rules · 26 scenarios
Open the playground →
CPE-011 · v1.0.0
Anemia Classification Pattern Engine
WHO thresholds, MCV, reticulocyte production index, and etiologic patterns that fire or stay quiet. No scores, no ranking by probability.
21 rules · 24 scenarios
Open the playground →
Built to be argued with
What makes these engines different from a black-box score.
Deterministic
Same input, same output. No training data, no drift, no surprises in clinic.
Every rule is public
Conditions, thresholds, outputs and the evidence behind them, one page per rule.
Safety first
Acute and emergent gates run before any classification. Urgent always outranks the pattern.
Checkable
257 synthetic scenarios replay through the same code. Re-run them in your browser.
Start with a case worth arguing about
Four synthetic cases that show where pattern recognition earns its keep.
FX-007
Fatigue after a head injury, with a normal TSH
Why a normal TSH can still hide central hypothyroidism.
CKD-FX-003
A single low eGFR
Why one abnormal result is not CKD.
CPE002-FX-006
Normal glucose, metabolic syndrome anyway
Three of five components without a glycemic criterion.
CKD-FX-004
Creatinine jumps in 48 hours
Safety gates run before any CKD staging.
IRON-FX-05
Ferritin of 85 that is not normal
Inflammation changes how ferritin is read.
ADR-FX-12
Hypotension in a patient with adrenal insufficiency
An emergency the engine will not make wait.
B12-FX-04
Macrocytic anemia with folic acid ordered
Why B12 comes first.
Questions physicians ask first
What are Biod's Clinical Pattern Engines?
They are deterministic, rule-based engines that turn structured laboratory data and documented clinical context into a named clinical pattern, with the rule that fired and the evidence behind it. This site hosts 11 engines: thyroid, metabolic, kidney, iron, liver, testosterone, cardio, adrenal, b12, pcos, anemia.
Are they artificial intelligence or machine learning?
No. The engines are transparent logic: the same input always gives the same output, and no model is trained on data. That is deliberate. A physician can read every rule, challenge it, and see exactly why a result appeared.
Can I enter real patient data?
No. The tools are an educational demonstration with synthetic cases. Never enter identifiers or protected health information. Everything is computed in your browser; nothing is sent to a server or stored.
Do the engines diagnose or recommend treatment?
No. They identify patterns and safety considerations for physician review. They never output a probability, a dose or an automatic treatment, and every result states that physician adjudication is required.
How do I know the engines behave as described?
A validation suite of 257 synthetic scenarios replays through the same code you use here, and you can re-run it in your own browser on the validation page. The rules are published in full, with their evidence, so specialists can check them. 56 scenarios come from the reviewed acceptance suites of the thyroid, metabolic and kidney engines; the rest were written by Biod for the newer engines and reviewed by Dr. Vinicius Amaral, D.O.
Is this FDA cleared?
No. These tools are clinical decision support for licensed clinicians and an educational demonstration. They are not FDA cleared and are not for patient-facing use.
Clinical review: Dr. Vinicius Amaral, D.O., Medical reviewer, 2026-10-03.
Try Biod in your practice
The Clinical Intelligence Layer — transforming fragmented clinical information into structured intelligence for clinician review and action.