MedAddWise · Clinical care coordination

A digital ecosystem for safe medication treatment — powered by AI.

Support for a person across the entire medication journey — from choosing and checking medicines, to organizing intake, to reaching a doctor.

The problem

Medication harm is one of medicine's largest solvable problems — and it hides between appointments.

Every prescription is written by someone who sees only part of the picture. The family doctor doesn't see the cardiologist's changes. The pharmacist sees one prescription at a time. The leaflet is written for lawyers. The patient — taking five medicines from three doctors — is the only one holding the full list, with no tools to check it.

$42B
Global annual cost of medication errors
WHO · Medication Without Harm
1 in 20
Patients affected by preventable medication harm; a quarter of cases are severe or life-threatening
BMJ Quality & Safety, 2023
~1 in 3
Adults 65+ take five or more medicines every day — the polypharmacy zone where interaction risk compounds
OECD countries, national surveys
№1
Medication safety is the WHO's flagship Global Patient Safety Challenge
WHO, 2017 →

“The data to prevent most of this harm already exists — in leaflets, interaction databases and the patient's own records. It has simply never been assembled around the patient.”

The platform

One safety ecosystem, gathered around the patient.

Everything stands on one structured health profile — conditions, medicines, lab results read straight from scanned reports. Three defining capabilities live on top of it and reinforce each other. MedAddWise shortens the path from spotting a medication question to getting qualified help.

01

Safety checks wherever medicines appear

One engine — pairwise interactions, whole-regimen assessment, disease and lab risks — can be invoked at every significant step: reviewing the profile, browsing the catalog, reading search results, weighing a basket before purchase, or previewing a new drug with “what if I add…”.

02

Consulting: AI first, a licensed human one tap away

The AI assistant answers instantly, seeing only what the patient chose to disclose. When a human should decide, the case — transcript and consented context included — goes to verified doctors and pharmacists who bid with their own price, protected by escrow.

03

AI intake scheduler

One tap turns the medication list into a day plan drafted from each drug's official leaflet — dose times, food constraints, spacing between interacting medicines — with every line citing its source. The patient accepts the plan; their phone reminds them.

Health profile Safety engine at every step AI help → human specialist
Product tour

Built and working today — not a concept deck.

Nearly every screen below is live in the product: a web application backed by a production API, a populated clinical knowledge graph, and real payment rails. Two aren't screenshots at all — they're the live engine, embedded in this page; type into them. The final two are the layers switching on next.

01 · Interaction checker · live — try it

Any combination of medicines, checked in seconds — with the mechanism, not just a verdict.

Patients and clinicians enter 2–10 drugs (and even foods). The engine traverses a clinical knowledge graph to find interaction pathways, then explains each one in plain or clinical language. MedAddWise doesn't stop at flagging an interaction: the system explains why it matters and helps move to the right action — adjust the intake plan, clarify the details, or take it to a doctor. This is not a mockup — the widget beside this text calls the same production API our users rely on.

  • Multi-hop discovery: catches interactions that share an enzyme, transporter or effect — not just known pairs
  • Convergence alerts when 3+ drugs load the same pathway
  • Every claim cites its source leaflet section
  • Try a classic: aspirin + warfarin, or add ibuprofen on top
Interaction checker live engine
add at least 2 medicines

The check typically takes 5–20 seconds: the engine resolves each medicine, traverses the knowledge graph and writes a grounded explanation. Educational information, not medical advice.

02 · Regimen safety

The whole regimen, judged against the whole patient.

One tap assesses every active medicine against every active condition, recent labs and pregnancy status — and flags what a pairwise checker can't see: disease-modified metabolism and stacked toxicity.

  • “What if I add…” — preview a new drug's impact before taking it
  • Personal risk badges: the same drug scores differently for a different patient
  • Simple or clinical wording — one toggle for patients and professionals
  • The same engine is callable from the catalog, search results or basket — one check, every doorway
Regimen assessment · 4 medicines · 2 conditions
Metformin
1000 mg · twice daily
Low risk
Lisinopril
10 mg · morning
Low risk
Spironolactone
25 mg · added yesterday
Personal risk
Alert Lisinopril + spironolactone with eGFR 54 → hyperkalemia risk. Recheck potassium within 1 week.
What if I add ibuprofen? → “triple whammy” kidney alert
03 · Consultations

Free AI answer first. A licensed human one tap away.

Questions start with the AI assistant — instant, profile-aware, first replies free. When it matters, the case hands off to the marketplace: verified doctors and pharmacists see the question (and consented health context) and bid with their own price. Payment is held in escrow and released on completion.

  • AI transcript travels with the handoff — no repeating yourself
  • Specialists are license-verified before they can answer
  • Competitive offers keep prices honest
Consultation · AI → specialist handoff
YouCan I take my painkiller while breastfeeding?
AI assistant · freeIbuprofen is generally considered compatible with breastfeeding at standard doses. Given the codeine in your regimen, though, I'd recommend confirming with a specialist.
3 offers from verified specialists
ОК
Dr. Olena K.
pediatrician · license verified · ★ 4.9
₴ 450
ІМ
Ihor M.
clinical pharmacist · license verified · ★ 4.8
₴ 300
Escrowfunds held on acceptreleased on completion
04 · Intake schedule & reminders

A day plan for the whole regimen — planned by the engine, explained line by line.

One tap turns the medication list into an optimal daily schedule: the LLM reads each drug's leaflet and distributes doses across the day — respecting dosing frequency, with-or-without-food requirements, and spacing between interacting drugs. Even a complex regimen — several medicines with different doses, intervals and intake conditions — becomes one coherent, personal plan the patient's phone reminds them about.

  • Every line carries a "Why this time?" rationale sourced from the leaflet
  • Weekly-cadence drugs handled too — methotrexate lands on one day, not seven
  • When the regimen changes, the plan flags itself as outdated and offers a re-plan
My intake schedule · accepted
Reminder · 08:00
Time for Metformin 1000 mg — take with breakfast
08:00breakfast
Metformin1000 mgwith food
Lisinopril10 mganytime
19:00dinner
Metformin1000 mgwith food
23:00bedtime
Atorvastatin20 mg
Why this time?Statins are most effective taken at night, when the body's cholesterol synthesis peaks. Based on the medication leaflet.
Outdated Your medications changed — this plan may be out of date. Re-plan now →
05 · Smart search · live — try it

Search that understands symptoms — in Ukrainian — and answers with safety, not ads.

A hybrid semantic pipeline (lexical + embedding retrieval, reranking, intent detection) built for Ukrainian medical language. Results carry safety verdicts sourced from official leaflets — for a logged-in user, “safe” means safe for them. Describe a symptom the way a patient would; every stage is reported live by the engine, not animated.

  • Understands “болить голова і нудить”, not just brand names
  • Red-flag triage: emergency symptoms surface hotlines, not products
  • Clarifying questions when the query is ambiguous
Semantic search live engine

Searches the live medication catalog. Results are informational and ranked by leaflet evidence; logged-in users additionally get personalized safety signals.

06 · Lab results

A photo of a lab report becomes structured, trending data.

Patients upload lab PDFs or photos; our OCR pipeline extracts each analyte, normalizes names and units to LOINC/UCUM, and plots it over time against its reference range — the medical history that usually lives in a drawer.

  • Out-of-range values flagged automatically
  • Trends feed the safety engine — kidney and liver function adjust drug risk in real time
  • Pharmacogenomic markers supported (clinical dosing guidelines)
Lab trends · from scanned reports
Hemoglobing/L · LOINC 718-7 ↑ +12% / 6 mo
160 120 108 ↓ 135 01.24 05.24 11.24
reference range measured values ✓ extracted by OCR from 3 uploaded reports
07 · Data sharing

The patient's data, shared on the patient's terms.

Access to the health record is granted per person, per data category, with an expiry date — by email, phone or a QR code shown in the clinic. Revocation is instant, and access tied to a consultation ends with it automatically.

  • Scoped grants: conditions, medications, labs — each shared separately
  • Read-only or managing access (for caregivers and family)
  • Consent-first architecture — the trust foundation of the marketplace
Shared access
Dr. Olena K. — cardiologist
conditions medications labs
read-only · expires in 14 days
Maria B. — daughter, caregiver
medications labs
managing access · no expiry · revocable anytime
08 · Pharmacies & delivery

From safety check to the medicine in hand.

The catalog shows live availability across partner pharmacy networks: the patient reserves the product at the nearest pharmacy on the map, or orders delivery. The fulfillment layer — offers, stock, geolocation — is already built into the platform; it switches on with pharmacy-network partnerships.

  • Per-pharmacy availability with price and distance
  • Map-based reservation or courier delivery
  • One tap checks the basket against the patient's regimen before checkout
Availability nearby
Ibuprofen 400 mg · 20 tablets
ibuprofenum · M01AE01
Khreshchatyk St Instytutska St
«Central Pharmacy», Khreshchatyk 22
350 m · in stock · pickup in 30 min
₴ 87
«Pharmacy №12», Velyka Vasylkivska 40
1.2 km · in stock
₴ 82
Reserve for pickup Order delivery
09 · Clinic appointments · next up

When chat isn't enough — book the doctor's office.

The next layer we switch on: after an online consult — or instead of one — the patient books an in-person visit with the exact specialist they already trust from the marketplace. The clinic address is provided and verified during specialist onboarding and appears as a pin on the map. The rails underneath — verified specialists, escrow payments, the same geo layer that powers pharmacy availability — are already live.

  • A named specialist, booked directly — not an open queue
  • Clinic location verified at onboarding, shown on the map with distance
  • The same escrow protection as online consultations
Clinic appointment
ОК
Dr. Olena K.
pediatrician · «Family Clinic on Pechersk», Klovskyi Descent 9
₴ 600
Klovskyi Descent clinic · 1.4 km
Wed · 15 July
09:30 12:00 14:00 16:30
Book the visit · ₴ 600

Escrow-protected like every consultation: funds are held on booking and released after the visit.

Where AI fits

AI where it helps. Evidence underneath.

No language model on this platform is asked to be the source of truth. Retrieval is deterministic, verdicts are structured, and every generated sentence stands on leaflet text and knowledge-graph evidence — or the system refuses to answer. Below is the graph it all stands on.

Grounded safety narration

Interaction and regimen explanations are written only from retrieved evidence — official leaflet passages and knowledge-graph paths. The output is a structured verdict: safety level, reasoning, recommendations — in patient or clinical wording. With no evidence, the model declines rather than improvises.

grounded · cited · refuses without evidence

Intake scheduling

The scheduler reads each drug's official dosing sections and drafts a schema-validated day plan; every slot carries a leaflet-cited rationale. The patient accepts or edits — the AI proposes, the person decides.

structured output · leaflet-cited

Consult assistant

Instant answers that use only the health categories the patient chose to disclose — undisclosed data never reaches the model. A soft paywall, and a warm handoff that turns the conversation into a specialist consultation.

consent-scoped context

A deliberately small role in search

Retrieval and ranking are deterministic — lexical and semantic retrieval with cross-encoder reranking. The LLM only plans ambiguous queries, asks clarifying questions and re-ranks the top results for safety, with red-flag escalation.

deterministic core · LLM at the edges

Reading lab reports

A dedicated OCR model reads the scan; an LLM extracts the readings into structured, unit-normalized tests that become time series in the profile. Extraction, not invention.

OCR + structured extraction
Inside the knowledge graph

Why two everyday drugs shouldn't be taken together — traced through the molecules.

A pairwise lookup table sees "clopidogrel + omeprazole" and shrugs. Our graph walks the biology: a blood-thinner that only works once an enzyme activates it, and a common heartburn drug that shuts that enzyme down. This is one real path, straight from the production graph.

Clopidogrel + Omeprazole
35 connections found · showing the decisive one
Knowledge graph path Clopidogrel needs the enzyme CYP2C19 to form its active metabolite; omeprazole inhibits CYP2C19, so the active metabolite is not formed and clopidogrel loses its effect. needs activation by forms inhibits blocked Clopidogrel INGREDIENT · antiplatelet Omeprazole INGREDIENT · PPI CYP2C19 ENZYME Thiol metabolite H4 METABOLITE · active form ✕ not formed
⚠ Major · avoid
Omeprazole inhibits CYP2C19 — the very enzyme that converts clopidogrel into its active thiol metabolite. The blood-thinner is left unactivated, and its protection against clots quietly disappears. No single edge says this; the graph earns the warning by connecting four nodes across two drugs. Path confidence 0.90 · evidence: curated pharmacological databases + drug-label assertions · 1 of 35 discovered paths
Business model

Safety builds the audience. Two marketplaces monetize it.

The free safety tools solve a daily problem and create the health profile; the profile makes every consultation and every purchase decision more valuable. The platform takes a share of both — consultations and pharmacy fulfillment. The engine is built — revenue scales with users, not headcount.

01

Marketplace take rate

20% of every paid consultation. Specialists set their own prices and bid for patients; escrow-style holds (funds captured only on completion) protect both sides and are already live on Ukrainian payment rails.

02

Pharmacy fulfillment commission

The catalog shows which partner pharmacies stock a product; patients reserve at the nearest one on the map or order delivery, and the fulfilling pharmacy pays a per-sale commission — the pharmacy-aggregator model already proven at scale in this market. Offers, stock and geolocation infrastructure is built into the platform.

03

AI assistant subscription funnel

First AI replies are free; the soft paywall converts engaged users, and every AI conversation is a warm lead for a paid human consultation — a built-in upsell path.

04

Ukraine-first, built to travel

Launching in a market of millions of displaced and remote patients where telemedicine is normalized and competition is thin. The clinical engine is dataset-driven and language-portable — each new market is data and localization, not a rebuild.

05

Expansion surface

The same profile and safety engine extend naturally to insurers, clinics and supply-chain integrations — those layers already exist in the platform, switched off until the audience is there.

20%
platform share of every consultation
80% specialist20% MedAddWise
+ per-sale commission from partner pharmacies on every reservation and delivery — rates negotiated per network.
Escrow payment holds · specialist payouts to business or personal accounts · Apple IAP for the AI tier — all implemented and processing in UAH today.
Technology & moat

The hard parts are already built.

Under the product is several years of clinical-data engineering that a copycat can't shortcut — and that gets stronger with every user.

Clinical knowledge graph

A graph of drugs, enzymes, conditions and foods fused from curated biomedical datasets maintained by pharmaceutical research institutions and drug regulators. Finds multi-hop interaction paths no lookup table contains.

graph database · multi-hop traversal

Hybrid clinical search

A 9-stage pipeline: lexical + dense retrieval, cross-encoder reranking, intent classification and condition detection — engineered for Ukrainian morphology, where global players don't compete.

BM25 + embeddings + rerank

Structured leaflet corpus

Every official medication leaflet parsed into sections, chunked and embedded — the evidence base the narrator cites, the scheduler doses from, and search ranks by. A data asset that grows with the catalog.

section-level citations · proprietary parsing

Lab OCR & normalization

Scanned lab reports become structured, unit-normalized (LOINC/UCUM) time series, with learned aliases improving accuracy with every upload — proprietary structured health data.

OCR pipeline · self-improving

Verified-specialist trust layer

Every doctor and pharmacist submits a license and credentials reviewed before they can consult. Ratings, escrow and consent-scoped data access make the marketplace safe by construction.

license verification · escrow

Plugin platform architecture

Search, health records, consultations, commerce and supply-chain are independent modules on one core — new verticals and new markets switch on without re-architecting.

Swift/Vapor · PostgreSQL · Redis
Contact

Interested? Let's talk.

For investment inquiries, partnerships or a live walkthrough of the product — leave a note and it lands directly in the founder's inbox.

Or write directly: [email protected]

The button opens your email app with the message prefilled — nothing is sent or stored by this page.