Clinical analytics · used by doctors

An analytical portalfor one.

One patient. Every blood, urine and stool marker they have ever had, mapped against researched reference ranges, known disease clusters and the trends running the wrong way, across nineteen clinical specialties, on every visit.

The job is to see what one person cannot.

It reports what is present, what is genuinely ruled out, and what has never been looked at. It holds pharmacology, botanicals and nutrition at the same time, reads the record longitudinally rather than one panel at a time, and every claim it makes carries a source you can open.

Coverage64 M · 258 markers · 8 years
Hypervitaminosis D
285.3 nmol/L Here
Iron overload
One test away
Pancytopenia
WBC 5.0 · Hb 147 Ruled out
Impaired hepatic synthesis
alb 47 2024-03 On an old value
Central hypothyroidism
Never checked
Illustrative · no patient data

What it reports

Every question gets an answer, and the answer says how it knows.

NeXXum runs 305 cited condition patterns against the whole record, every draw rather than just the panel in front of it, and reports what it finds with the values, the dates and the source behind each one.

Including the negatives. Where the deciding criteria are declared, it also says which conditions were genuinely ruled out, which rule-outs are resting on a value too old to trust, and which were never checked at all. A documented negative is a clinical finding in its own right, and it is the one thing a lab report never gives you.

Here
The constellation is present, with the values and dates behind it.
Ruled out
The data was there, it was current, and the pattern isn’t. A documented negative finding, and the thing no lab report gives you.
On an old value
The rule-out rests on a result older than it should be. Named, dated, and queued for re-testing rather than quietly trusted.
One test away
Something abnormal is already present and a single named test would settle it.
Never checked
The deciding test has never been drawn. The silence means nothing, and now it says so.

What it reads

Nineteen specialties, held in one reading.

A haematologist reads the blood count. A hepatologist reads the liver. NeXXum reads all of it at once, each result against every other, on every visit. That is where the findings that only appear in combination live.

Red cell & ironWhite cell & plateletLiverEndocrine, renal & electrolyteCardiometabolicCardiologyUrology & prostateMetabolic & hormonalGynaecologyRheumatology & autoimmuneDigestive & absorptionFatigue, pain & sleepBone & mineralNeurologyMental healthAllergy & immunologyObstetricsInfectious diseaseLaboratory medicine
305
cited condition patterns, each with its threshold, its source and what would rule it out
283
of them read the record directly; the other 22 name the test that would settle the question
278
markers recognised, canonicalised and banded on every upload. 239 blood, 17 urine, 22 stool, and sex-aware, age-aware and unit-aware across labs

Functional medicine

The whole-person read, with the analysis attached.

Read the whole person, over time, look upstream, intervene early. That is the premise, and NeXXum is built to carry it. Every range it applies is sourced, every supplement it names is graded, every connection it draws states the finding it rests on.

Same ambition, with the working shown. Each claim arrives with its threshold, its source and what would rule it out.

  • 170 written monographs across the 203 botanicals and nutrients it can suggest: what it is, how it works, who it is for, and the honest read on where the evidence is thin or negative.
  • 55 markers carry a published biological-variation figure, so it can say how much a repeat draw must differ by before the change means anything. Eleven more are recorded as having none, with the reason.
  • Where no defensible range exists, it says sorather than banding anyway. A marker with nothing behind it reads “not assessed”, never “normal”.

Longitudinal

A result means one thing. A decade of them means something else.

Most software reads the panel in front of it. NeXXum reads every draw a patient has ever had: the direction, the rate, the moment a value started drifting while still inside the reference range, and whether two numbers were even measured close enough together to be compared.

That is where early detection actually lives: not in a red flag, but in a slope nobody plotted and a constellation nobody assembled.

A real record, published with the consent of the person whose it is · four years, drawn to scale. Each of these is a percent or two over on its own. Read together, across every draw, they are the finding.

And here is what it wrote about them.

Unedited, from the assessment generated for that same record on 24 August 2026. It is written to one clinician by another, the reasoning is shown, the numbers carry their dates, and the sources are named so they can be opened and checked.

It separates the worry from the finding
The three things he has been most worried about are, on close reading, the three most reassuring: the “iron retention” is a single borderline transferrin saturation sitting on top of a normal ferritin; the “UTI” was adjudicated as a contaminated specimen; and the “gut inflammation” rests on one stale zonulin of uncertain validity.
It finds the quiet ones instead
The signals that genuinely deserve attention are quieter: a persistent atherogenic particle burden he is under-treating because he is under-dosing the tools already prescribed; a fasting glucose climbing steadily across four years; a PSA that is both pharmacologically suppressed and drifting upward with a low free-to-total ratio; and, added since this panel, three self-started injectable peptides whose safety profile intersects with the prostate question.
It agrees with reasons, and says when to do nothing
This is sound and I agree with it on the evidence, not just deferentially: nitrite plus leukocyte esterase in an asymptomatic non-pregnant adult does not meet a threshold to treat, and treating asymptomatic bacteriuria drives resistance without benefit (Nicolle LE et al., IDSA 2019). Urine blood, protein and glucose were all negative on 2026-07-28, which is consistent with contamination rather than infection. Nothing to do.

Where the knowledge came from

Named sources, not a claim to have read the literature.

The library was built from guideline bodies, classification criteria and primary papers, each one recorded against the entry it supports. This is the short version; the app carries 112 reading sources and a citation on every claim it makes.

What that is, and what it isn’t. Nineteen fields, none of them thinner than a dozen conditions, every one carrying its source. That is not the depth a haematologist has in blood or a hepatologist has in liver, and it does not replace either. It is the breadth of all nineteen held at the same time, on every patient, on every visit, which is the part no one person does.

Cardiology & lipids
ACC/AHA 2026 dyslipidaemia · Canadian Cardiovascular Society (Pearson, Can J Cardiol 2021) · PREVENT (Khan, Circulation 2023) · EAS consensus on Lp(a) (Eur Heart J 2022) · Braunwald’s Heart Disease
Metabolic & diabetes
Diabetes Canada 2018 and 2024 · harmonised metabolic-syndrome definition (Circulation 2009) · HOMA-IR (Matthews, Diabetologia 1985)
Liver
AASLD/EASL MASLD nomenclature (Rinella 2023) · ACG abnormal liver chemistries (Kwo 2017) · FIB-4 (Sterling, Hepatology 2006) · ACG haemochromatosis (Kowdley 2019) · Sherlock’s Diseases of the Liver
Kidney
KDIGO CKD 2024 and 2017 · EMPA-KIDNEY and FLOW (NEJM) · Brenner & Rector’s The Kidney
Thyroid & endocrine
ATA hypothyroidism (Jonklaas 2014) and hyperthyroidism (Ross 2016) · European Thyroid Association · Endocrine Society testosterone (Bhasin 2018) · Pituitary Society · Williams Textbook of Endocrinology
Haematology
Anaemia of inflammation (Weiss & Goodnough, NEJM 2005) · hepcidin and iron regulation (Nemeth & Ganz, Annu Rev Med 2023) · iWCLL criteria (Blood 2018) · Wintrobe’s Clinical Hematology
Rheumatology & autoimmune
ACR/EULAR classification criteria. Rheumatoid 2010, lupus 2019, Sjögren 2017, systemic sclerosis 2013, myositis 2017, ANCA vasculitis 2022
Gynaecology & menopause
International PCOS guideline (Teede 2023) · NAMS 2022 · STRAW+10 staging (Harlow 2012) · ESHRE premature ovarian insufficiency 2024 · SOGC · ASRM
Urology & prostate
AUA early-detection 2026 · ERSPC 16-year follow-up (NEJM 2022) · free/total PSA (Catalona, JAMA 1998) · Campbell-Walsh-Wein Urology
Pharmacology
FDA prescribing information via openFDA · Health Canada product monographs (DPD) · LiverTox for drug-induced liver injury · the trial and label data behind each drug’s lab effects, interactions and monitoring
Supplements & botanicals
Cochrane reviews and PubMed meta-analyses for effect sizes · NatMed Pro · NIH Office of Dietary Supplements · Memorial Sloan Kettering About Herbs · NCCIH · Examine, with negative and null trials kept rather than filtered out
Naturopathic & integrative
Pizzorno & Murray, Textbook of Natural Medicine · Hechtman, Clinical Naturopathic Medicine · Rakel, Integrative Medicine · NatMed Pro · NIH Office of Dietary Supplements · Memorial Sloan Kettering About Herbs · LiverTox · Examine

Evidence

Every claim carries a source you can open.

Not a model’s recollection. Guidelines, meta-analyses and primary papers, each one resolved against PubMed and the answer written down: author and year against what we wrote, in a ledger that ships with the code. A citation that fails is kept and marked, not quietly dropped, because a row that vanishes and a row that was checked look identical afterwards.

That check exists because it caught things. Twelve citations named one paper while their link pointed at another. That is the hardest kind to see, since the sentence reads correctly. One cited a phase 2 trial registration for a myopathy risk the trial never studied.

Keeping it current means checking where the answer changes first. PubMed shows what has been published; the trial registry shows what is underway. Three compounds this library graded “no published human evidence” turned out to have phase 2 trials recruiting: true of the literature, and out of date about the world. Every one of those entries now carries the registration and the date the registry was checked, so the claim to be current is a falsifiable one.

678
citations resolved against PubMed, each recorded, so “nobody checked” can never pass as “checked and fine”
113
markers banded against a range we cite ourselves, rather than borrowing the one the lab printed
0
numbers in a generated assessment that don’t match the record

Interactions

It reads the supplement and the prescription as one list.

The patient is already on medication before anyone recommends anything. So every drug entry leads with what that drug does to a lab result, then what it interacts with, including the botanicals and nutrients on the same shelf, which is the half most software does not hold at all.

What the drug does to the result

A 5-alpha-reductase inhibitor HALVES the PSA, so the number must be doubled before it is read. An ACE inhibitor raising creatinine up to 30% is the drug working, not kidney injury. High-dose biotin is an assay artifact that can falsely lower a troponin.

What the supplement does to the drug

St John’s wort induces the enzymes that clear a contraceptive, a transplant drug and an anticonvulsant. Calcium, magnesium, iron and zinc bind a fluoroquinolone into treatment failure. DIM lowers endoxifen in a woman on tamoxifen.

And it can subtract. Reading that one list lets it say what should come off: an over-the-counter product whose active constituent is the prescription drug beside it, several agents stacking one hazard, the same nutrient arriving from two bottles, a dose above the licensed maximum. A patient on eighteen things is the common case, and almost no tool will tell a clinician to remove one.

  • Red yeast rice is lovastatin. Beside a statin it is a second statin, and it is the one nobody reconciles because it arrives from the supplement shelf.
  • One nutrient, two products. A combination formula and a standalone capsule are counted once each by the patient and twice by the body.
  • Above the licensed maximum. Recorded doses are checked against the label ceiling, with the age-specific ones encoded, because those are the ones missed.
159
pharmacology entries, drugs and drug classes, each leading with its lab effect and what to monitor
203
supplements and botanicals with studied dose, effect size and honest negatives
132
curated drug–supplement interactions. It never declares a combination safe

How it cannot invent

The findings are decided by code. The language is the model’s.

A language model will produce a plausible number. In a clinical document a plausible number is the whole problem, and a disclaimer does not fix it because nobody reads disclaimers. So the two jobs are separated: deciding what is true, and saying it well.

The pattern engine runs first
Marker combinations are checked against thresholds from cited guidelines before the model sees anything: transferrin saturation above 45% with a raised ferritin, and so on. Only what the engine found is passed on, and the model is forbidden from adding a pattern it did not detect. It cannot report a finding that was never there, because it is narrating a list rather than composing one.
Clinical numbers belong to code
Doses, effect sizes, reference ranges and retest intervals are looked up from a verified library and written into the document after the model has finished. It is not asked to remember them and it is not trusted to.
Every figure is re-checked afterwards
Once written, each number in the prose is compared against the record it came from, and anything that does not match is printed in the document rather than quietly corrected. Across every assessment on file, that check currently finds none.
The plan is listed by code, not by recall
Every agent the patient is already taking appears on the page whether or not the assessment discusses it, and the ones it did not discuss are marked as such. A silent omission and a considered dismissal are different things, and they must not look the same.
The non-diagnostic notice is not editable
It is stored outside the document body and drawn by the page itself, so neither the clinician nor the model can remove it, not by editing, not by rewriting, not by accident.

And the identifiable record never leaves the country

A report is de-identified on the clinician’s own machine, and she is shown exactly what was removed before anything is sent. On confirmation the server does not trust that result: it goes back to the stored original, re-extracts and re-de-identifies independently, and discards what the browser produced. If an identifier survives, the send is refused outright rather than flagged. A scanned report is read by an OCR service inside Canada, so the image itself never crosses a border. Only anonymous text does.

Limits

What it doesn’t do.

Written down, because a tool that only lists its strengths is asking to be taken on faith.

  • It doesn’t diagnose, prescribe, or replace your judgement. It’s read by a clinician, never by a patient.
  • It can only answer questions that have been described precisely. Where a pattern hasn’t been, it stays silent and says so rather than guessing.
  • A rule-out is only as good as the test behind it, so it says which value and which date it rests on, and flags when that value is too old to trust.
  • It cannot see what was never drawn. That’s the point: it tells you what’s missing instead of pretending the record is complete.