Skip to main content
4 min read

Why aiomics for referrer management

A referrer portal that never grades practices and leaves the analysis with the hospital — in pilot preparation, and named as such. What it will do, who can start today, and where we do not fit.

Dr. Sven Jungmann

Dr. Sven Jungmann

CEO

Editorial collage: a practice passes documents through a window to a hospital board; between the two, a clear partition through which only narrow status cards travel

If you want to improve referrer management with software, the most important design question is what the practice is allowed to see: with aiomics, referrers (Zuweiser — referring physicians) see the document status and the procedural stage of their request — never a substantive assessment, never a grade. Honesty includes the status: the referrer portal is in pilot preparation; there is no mass rollout yet. What is live is the hospital-side admission board the portal builds on — anyone who wants to bring order to their referral intake today starts there.

aiomics is the verification layer on top of hospital IT: the system ingests unstructured documents, verifies every statement against its source, and gives the hospital a substantiated, structured record. The referrer portal is the entrance to this layer: it collects the documents where they originate — in the practice.

At a glance

  • What it does: gives referring practices a workspace for the entire referral process — submission via drag and drop (the extraction types, the practice confirms), immediate feedback on the completeness of documents, real-time status tracking, one-click responses to follow-up requests.
  • Status: in pilot preparation — a prototype has been demonstrated to physicians in private practice; production operation begins with selected pilot partners. The hospital-side admission board is live in production.
  • Security: ISO 27001 (TÜV Nord), processing exclusively in the EU; notifications contain no patient data by schema.
  • Integration: KIS-agnostic (KIS — the hospital information system); transmission to payers remains with the hospital's own system. Fax remains a permanently equal intake channel.
  • Evidence: independent evaluation at Charité (ongoing).
  • Who it is for: hospitals with high referral volume — and the practices that refer to them, free of charge for those practices.

The problem we solve

At one rehabilitation site, 1,000 to 2,000 faxes arrive each month, five to forty pages per transmission, frequently incomplete. Every missing document starts a follow-up loop lasting days; meanwhile the practice does not even know whether its request has arrived. One hospital we are talking to counts around 9,000 referral requests for around 900 admissions a year — ten requests for one admission. We described the mechanics in How ten requests become one admission.

The distribution is steep: 20 to 30 practices generate over 80 percent of the volume at a single site. Whoever noticeably eases the work of those few practices changes a hospital's entire intake.

How aiomics builds referrer management

All of the following mechanisms are at pilot-preparation stage: a prototype exists and has been demonstrated to physicians in private practice; none of it has been rolled out at scale. We lay the design decisions open anyway — they are the standard pilot partners can measure us against.

First: the two-axis firewall. Referrers see exclusively which documents are on file and which procedural step the request is in. Every substantive analysis — plausibility, exclusion criteria, quotas — stays on the hospital side; the portal services have no read path to this data, and exactly that is tested automatically with every release. For the practice, this means: it is not being rated. For the hospital: its decision-making basis stays in the house.

Second: notifications without patient data. In the schema of the push and e-mail messages there are no fields for patient data — what travels is a reference number and a status class, nothing more. Even a compromised delivery channel would expose no patient data.

Third: respect instead of a points tally. There are no referrer scores, no badges, no leaderboards. No one who entrusts patients to a hospital should feel graded by its software.

Fourth: fax stays. Portal and fax requests land on the same hospital-side board and are treated the same. The portal wins practices through usefulness — immediate feedback on completeness, status without a phone call — or not at all. What can be extracted from faxes in structured form is shown in our field report on data extraction.

Fifth: free of charge for practices, paid by the receiving hospital. Onboarding is designed without an IT project; from invitation to first submission, only a few minutes should pass — that is a goal of the pilot phase, not a measured value. A success message appears only once the submission has been confirmed as stored server-side.

What you can measure us against

  1. Have the firewall shown to you: there is no configuration switch that shows referrers exclusion criteria, ratings, or hospital-internal analyses.
  2. Inspect a notification in plain text: reference number and status class — fields for patient data do not exist in the schema.
  3. Look for scores or leaderboards: they do not exist.
  4. Send a fax in parallel: it lands with equal standing on the same hospital-side board.
#hospital referrer portal#rehab referral portal#referrer management software#digital patient registration instead of fax

The referrer portal is in pilot preparation; a prototype has been demonstrated, and production operation begins with selected pilot partners. The hospital-side admission board is in production.

Keep reading

Editorial collage: a quarterly report whose figures are connected by threads to queries and control charts, a watermark across the page

Why aiomics for QM reports and quality analytics

A QM report in which every figure resolves to its query and the language model never sees individual data. All of it is planned — and we are laying the architecture open now anyway, so you can measure us against it.

Dr. Sven JungmannCEO
A physician stands at a wall-mounted clinic terminal in late-afternoon corridor light, one hand on the mouse, shoulders slightly dropped at the end of a long shift.
Reflections

The 4 p.m. Hazard: When Bad Software Becomes a Clinical Risk

We regulate how long a doctor may work, but not how hard the day grinds down their judgement. The most dangerous fatigue in a hospital is not in the legs. It is in the part of the mind that makes careful decisions — and clumsy software spends it for free.

Dr. Sven JungmannCEO
A physician stands at a cluttered clinical workstation, several monitors layered with records and alerts, pausing with eyes closed for a moment before the next decision.
Reflections

The Value of AI Isn't Prediction. It's Cognitive Ergonomics.

We keep debating whether AI will replace doctors. The real threat is quieter: a data environment so noisy it stops clinicians from thinking at all. A case for tools that curate the evidence rather than predict the answer.

Dr. Sven JungmannCEO

This analysis comes from the people behind Visite.

Our weekly newsletter on AI in medicine. Every Friday, rigorously checked.

By signing up you agree to receive Grand Rounds by email. Unsubscribe anytime. More in our privacy policy.

Want to see this in your hospital?

30 minutes. Your questions. Our physician-founder shows you the platform personally.

Book a demo

No commitment. No sales pitch. Physician to physician.