Pre-visit brief design: why Helose never auto-interprets patient charts

Helose pre-visit briefs surface facts (labs, dates, deltas, verbatim notes), not AI diagnoses. Built for outpatient clinics that want HIPAA-safe patient texting and summaries without clinical overreach.

May 28, 2026

Most AI clinical tools in 2026 do the same thing. They read the chart, they read the labs, and they tell the doctor what they think is happening. “Patient likely has insulin resistance.” “Suggestive of subclinical hypothyroidism.” “Consider re-checking iron studies.”

Helose doesn’t.

That is not an oversight. It is the whole design, and it shapes how we build pre-visit brief software and automated patient texting for outpatient clinics.

What Helose surfaces

Helose puts facts in front of the physician. The 90-second pre-visit brief is built from items like:

A lab value, its date, the lab that ran it, and where it sits relative to both the lab-default reference range and the FM clinic’s target range
An arithmetic delta against the previous value of the same analyte (“TSH 4.2 to 1.8, 14 months”)
A verbatim quote from a prior encounter note, with the date and the author
A supplement start date from your dispensary, next to the lab values that bracket it in time
A medication start or stop date from your EHR, with the reason when the chart records one
A count, like “documented across 4 panels since 2024”

That is the vocabulary. Dates, numbers, ranges, deltas, verbatim quotes, counts.

What Helose deliberately won’t surface

The brief will not use the words “improving” or “worsening.” Both are interpretive verbs. A TSH that moved from 4.2 to 1.8 is a number that moved. Whether that is improvement depends on the clinical question, and that question belongs to the physician.

The brief will not infer causation. If a patient started Levothyroxine in March and their TSH dropped in October, Helose shows both events on the same time axis and stops there. It will not say the medication caused the change.

The brief will not infer adherence. Helose can show dispensary order dates and the gaps between refills, and it can pull the verbatim chart quote where the patient described their routine. It will not write “poor adherence” on top of those facts.

The brief will not call a patient “stable.” Stability is a clinical judgment that depends on the goal of care, and the goal of care is not in the data.

The brief will not suggest diagnoses, differentials, or treatment changes. It will not rank “concerns” or color-code “risk.” It will not say “X caused Y” or “X is responsible for Y” or “this looks like Y.” Those are the physician’s words. Helose is infrastructure for between-visit logistics (texts from your practice number, lab reminders, refill nudges) and for chart assembly before the visit. Not for practicing medicine by proxy.

Why this matters

Physicians do not trust tools that reach conclusions for them. Clinical judgment is the part of the job that took a decade to develop, and it is the part that pays. A tool that pretends to do it for them is either wrong (and the physician stops trusting it) or right (and the physician feels redundant). Neither is a product the doctor opens for a fourth visit.

What physicians do trust is preparation. A research assistant who pulls the right facts to the front of the chart, in the right order, with the dates straight, is a tool a physician will open every day. That is the role we wrote Helose to play.

The legal and regulatory exposure of an interpretive tool is different from an assembly tool. A product that surfaces a TSH value and its date is reporting data the lab already certified. A product that says “the patient appears euthyroid” is rendering a clinical opinion. The first is a record-assembly tool. The second has a much larger surface for liability, regulatory scrutiny, and the kind of FDA conversation we would rather not have at the wedge stage.

We are not opposed to that conversation existing. We are opposed to having it on the way in. The portfolio is what we want to build first, and the portfolio is a factual artifact.

When Helose is wrong about a fact, it is correctable. When it is wrong about an interpretation, it is hard to undo. If we mis-OCR a faxed lab and a value lands at 4.2 when it should be 1.2, the doctor sees it, fixes it, and the rest of the brief is intact. If we tell the doctor “this looks like Hashimoto’s” and the doctor reads it before reading the rest of the chart, the anchor is set. The next 60 seconds of attention bend toward confirming or refuting the suggestion rather than reading the evidence.

The first failure mode is mechanical and auditable. The second is cognitive and invisible. We do not want to put interpretive anchors into a physician’s head 90 seconds before the room.

Why clinics search for this distinction

Practice administrators comparing AI chart summary tools often ask the same question: will this create liability, alert fatigue, or staff distrust? Anti-interpretation is our answer. Coordinators can trust the SMS thread stays logistics-only. Physicians can trust the brief shows their data, not a model’s opinion.

What this means for the brief

The brief reads like a research assistant’s prep memo, not a diagnostic suggestion. Labs are dated and arranged. Supplements and meds sit on the same axis. Chart quotes are verbatim. Deltas are arithmetic. Deviations from target range are computed, but the meaning of those deviations stays with the physician.

The physician reads the brief in 90 seconds, forms a hypothesis, and walks into the room. Helose did the assembly. The doctor does the thinking.

That is the contract.