AritmoLab · Policlinico San Donato

Role of AI in the Analysis of Unstructured Clinical Databases

How we turned a mix of structured and free-text clinical records into a research data platform — the AritmoLab platform experience.

AritmoLab A clinical data platform hosting cardiology data and analysis tools

Dr. Marco Pancotti - MultiPhysixLab Dr. Sara Paratico - I.R.C.C.S. Policlinico San Donato

“Multidimensional Characterization of Cardiac Arrhythmias: Role of Electrocardiology in the Artificial Intelligence Era”

San Donato Milanese, Milan, Italy · 2–3 October 2026

Good morning everyone, and thank you for being here. I'm Marco Pancotti, and with my colleague Dr. Sara Paratico we work on the clinical data platform of AritmoLab at Policlinico San Donato. Today I want to talk about a problem that every hospital knows very well. The most valuable clinical information we have — the diagnosis, the patient's history, the outcome of a test — is written in plain free text, inside systems that were never designed to make that text usable. Over the next twelve minutes I'll show you how we used artificial intelligence, in three different roles, to transform twenty years of cardiology records into a database that researchers can actually query — and that clinicians can verify. My colleague Dr. Sara Paratico will join me to show how we read the clinical text itself.

AritmoLab · Policlinico San Donato

Twenty years ago

Four islands and two missing pieces

MISSINGNo Health Intelligencenothing usable to analyse historical data

MISSINGNo ML-ready datamartsnothing ready for predictive statistics or machine learning

▸ click a system: how it was used — and what held it back

Before I show you what we built, let me take you back twenty years. Cardioref, our electrophysiology database, had twenty years of clinical records: as a management tool for patients, daily activity and planning it was — and still is — excellent. But for research it was almost unusable, because most of the clinical knowledge was written in free text, outside the structured fields. The genetic data lived in its own system, which produced Excel sheets, with no connection to Cardioref. Our first Omics Portal was a promising idea, still embryonic and not integrated with anything. And a constellation of ECG subsystems that could only hand you a CSV file, on request. On top of that: no health intelligence on the historical data, and no platform to extract datamarts for predictive statistics or machine learning. Four islands, two missing pieces. Click any system and I'll show you exactly what held it back. And here is what we built.

AritmoLab · Policlinico San Donato

The plan

What we wanted to build

One platform, two destinations: the 360° patient portal and a research-ready warehouse. Built on open-source pillars, with AI coding agents wherever they helped. This talk follows the hardest piece — the unstructured data.

What existed

Cardiorefcardiology records · procedures · letters

Genetic datalabs · variants · nomenclature

ECGsignals · device follow-up

+Future sourcesnew subsystems can be connected as sources

→

What we built

Stagingraw replica of the sources

→

Integrationcleaned, normalized, deduplicated

AI reads the clinical text: pathologies, procedures, drug-challenge outcomes

→

Star schemadimensional transformation

→

Datamartsresearch-ready marts

AI builds them on demand from plain-English questions (ThothII)

→

AritmoLab Data Warehousequeried for research

AritmoLab Portalmanagement & exploration

AI coding agents — Anthropic · OpenAI — used wherever they helped, 360° in the code Airflow · orchestration Superset · dashboards Django · portal scaffolding Authentik · auth — GSD LDAP

Here is the whole project on one slide. On the left, what already existed: three hospital data sources — Cardioref, our electrophysiology records; the genetic data coming from the labs; and the ECG signals. On the right, what we built in AritmoLab: a staging replica, an integration layer where the data is cleaned and normalized, a star-schema warehouse, and the research datamarts — delivered through the data warehouse and a management portal. Everywhere you see the brain symbol, that's where AI works for us — click each brain and its contribution card opens, tied to the brain by a red line. At integration, AI reads the clinical text. At the end, AI builds the datamarts on demand from plain-English questions. And the mappings that bring the sources in were themselves drafted by AI, then revised by humans. That was the plan. And to build it, we used AI everywhere it helped — drafting configs, reading clinical text, and at the very end, producing the datamarts themselves. This talk follows the hardest piece of that plan: the unstructured data. My colleague Dr. Paratico will show you exactly how the text reading works. But first, the first step of the climb: the mappings.

AritmoLab · Policlinico San Donato

Mappings as code

LLM agents draft it. Humans review it. Git versions it.

Staging → integration mappings are declarative YAML: schema-validated, reviewed, versioned
LLM agents authored them from prompts (etl/prompts/fill_integration_yaml.md)
The same file wires the runtime text mining: analysis_function + version_function per enrichment
Every extracted row records its pattern-library version — reproducible by design

etl/config/integration-map.yaml19,764 lines · 42 mappings

text_cascade_enrichments:
- source_columns:
  - cr_diagnosi
  - cr_anamnesi_cardio
  - cr_anamnesi_extra_cardio
  analysis_function: get_letter_pathologies_cascade
  version_function: get_letter_pathology_version
  integration_table: cr_lettera_dimissione_diagnosi
  output_columns:
  - column: patologia
    postgres_type: TEXT NOT NULL

AritmoLab · Policlinico San Donato

From free text to a research platform

The clinical truth lives in unstructured columns

“Il paziente riferisce sincope ricorrente; ECG basale con sopraslivellamento ST in V1–V3; test provocativo con flecainide positivo per pattern Brugada.” One sentence from a discharge letter (example) — diagnosis, history and test outcome, all in free text

SourcesCardioref · SQL Server
Kokoro · PostgreSQL

→

Stagingraw replica

→

Integration3NF · text miningAI

→

Data Warehousestar schema

→

Martsdbt · Superset

↑

AIThothII — natural-language → SQL over the DWH, builds the final datamarts

AritmoLab · Policlinico San Donato

What the text mining produced

Deterministic AI, audited numbers

58,438discharge letters readfree-text fields, bilingual IT/EN patterns

73,389pathologies extractedtwo-tier clinical ontology

10,908drug-challenge tests parsedflecainide · ajmaline · adrenaline · isoprenaline

2,307Brugada patients identifiedconfirmed by clinical review on dashboards

Every row carries its pattern-library semver (pattern_version) · quality gate: ≥95% accuracy on 100 manual reviews.

AritmoLab · Policlinico San Donato

Clinical NLP

Reading clinical text is not keyword matching

Negation — “fibrillazione atriale esclusa”, “non FA”: the rule scans a window around every match before deciding
Family ≠ patient — “padre con FA” is attributed to the family member, not to the patient
Two languages — every pattern matches IT and EN forms: fibrillazione atriale / atrial fibrillation
Abbreviations & noise — FA, f.a., “TA 140/90” (blood pressure, not a diagnosis)
One field, many statements — the text is split into clauses before matching

what the rules seeexamples from the corpus

“padre con fibrillazione atriale”
  → patologia: FA · attribuzione: familiare

“fibrillazione atriale esclusa”
  → patologia: FA · negato

“test provocativo con flecainide
  positivo per pattern Brugada”
  → test: flecainide · esito: POSITIVO

AritmoLab · Policlinico San Donato

The clinical ontology

Two tiers, one clinical order

TIER 1 · arrhythmic

FABrugadaFlutterTATRNWPW / TPSVTVFVExtrasistolia V.SincopeQT lungo

TIER 2 · structural

Blocco AVBlocco di brancaCardiomiopatiaScompensoValvulopatia

Order encodes clinical precedence — “Brugada” is matched before “TV”, so “substrato per TV” can't mask a Brugada pattern
Synonyms live inline — FA / f.a. / fib. atriale / atrial fibrillation → one canonical label
Versioned like software — semver per pattern library, pattern_version on every extracted row

AritmoLab · Policlinico San Donato

Validation

Trusting the text is a process, not a promise

Quality gates — ≥95% procedure classification, ≥85% pathology detection, validated on 100 manually reviewed records
Clinical review — the extracted Brugada cohort was validated by clinicians on Superset dashboards
Feedback loop — ~893 Brugada false positives found and removed in pattern-library v1.3.1
Nothing is silently dropped — negated and family-attributed findings are stored too, filtered only at the mart layer

Quality gateAn extraction is accepted only after 100 manual reviews confirm the agreed accuracy — the same standard for every new pattern release.

AritmoLab · Policlinico San Donato

The portal, today

AritmoLab — a quick tour

screenshot

[MP: 6-7 real screenshots of the portal, anonymized or demo data]

AritmoLab · Policlinico San Donato

All good? Not yet.

The warehouse speaks SQL. Research needs more.

Clinicians and researchers don't write SQL — a star schema is built for analysts, not for the ward
Health Intelligence — to present the past, the Unit needs ready-made aggregates: volumes, incidence, outcomes
Predictive research — multivariate analysis and ML models need clean, wide, cohort-shaped tables
Hand-made datamarts are the bottleneck — even with coding agents, each one takes hours of careful work

The gapTwenty years of data, one warehouse — and no fast road from a research question to an answer.

AritmoLab · Policlinico San Donato

Role 3 — AI for analysis

Ask the warehouse in plain English

“How many Brugada patients had an effective ablation?” a researcher, in natural language

NL → SQLAI writes the query over the star schemaAI

→

Human reviewthe researcher checks every proposed query

→

Datamartcurated, research-ready martsAI

→

Supersetstatistics & dashboards

The session is a conversation: refine the question, iterate on the datamart — every step reviewable.

AritmoLab · Policlinico San Donato

ThothII, step by step

From question to datamart — the app

screenshot

[MP: 6-7 real screenshots of ThothII — ask, review SQL, datamart, dashboard]

AritmoLab · Policlinico San Donato

From datamart to discovery

One datamart — many questions answered

Multivariate analysis[SVG chart — next step]

Machine learning[SVG chart — next step]

[Illustrative data, modeled on published arrhythmology predictors — Brugada focus]

AritmoLab · Policlinico San Donato

Questions?

Thank you

Want the deep dives? The technical walkthroughs of the text miner, the mapping agents and ThothII are coming as videos on our Substack.

Dr. Marco Pancotti - MultiPhysixLab Dr. Sara Paratico - I.R.C.C.S. Policlinico San Donato