— Living knowledge base

Road to CEPAS 2026

A 26-week public series on AI and neonatal sepsis prediction, built toward a 20-minute talk in Lyon on 31 October 2026. Twelve essays. One growing literature base. One honest argument.

Episode 01 of 12 · Updated 8 May 2026

Prediction is not the same as clinical utility.

The field can predict late-onset sepsis in preterm neonates reasonably well. It has been able to for years. There is no shortage of models with respectable ROC curves, and our group has contributed to that pile.

What no one has done is build the bridge from prediction to clinical utility. We have models. We do not have validated response protocols. We do not have implementation data at scale. We do not have answers to the question that follows every alarm: now what?

That gap is the subject of this series, and the central argument of the talk in Lyon.

Twelve essays through October. One postscript from Lyon.

01
The Honest Problem
Framing & argument · the gap between prediction and action
Published 13 May
02
Searching the Evidence — Live
PubMed MCP search, on screen, queries archived
Upcoming
03
A Field Full of ROC Curves
Data extraction & cross-study comparison table
Upcoming
04
Our Own Work — Warts and All
Critical self-appraisal of the 2023 LOS prediction paper
Upcoming
05
What Does "Works" Even Mean?
Clinical utility frameworks · NNT, decision-curve analysis, alarm fatigue
Upcoming
06
The Omics Layer
Literature synthesis · where omics meets ML in NICU sepsis
Upcoming
07
Doing a Mini Systematic Review with AI
Full PICO → search → screen → extract → synthesize pipeline
Upcoming
08
Big Data in the NICU — What Actually Exists
Data landscape mapping · registries, EHRs, monitor streams
Upcoming
09
HeRO and Friends — The Commercial Reality
MDR/CE marking, regulatory landscape, what's on the market
Upcoming
10
Building the Evidence Website
How this knowledge base was built · the meta-episode
Upcoming
11
The Presentation Takes Shape
Slide logic, narrative structure, the final argument
Upcoming
12
See You in Lyon
Final teaser · what to expect on stage
Upcoming
13
From the Stage
Slides, recording, audience Q&A · post-congress
After CEPAS

Every search, every paper, every choice — archived here.

From Episode 02 onwards, the evidence work behind every essay lives on this page. PubMed queries with their results. Extraction tables with their data. Methodological choices with their reasoning. By the time of the talk, you should be able to see the full chain of reasoning from raw literature to final slide — and copy the workflow if it helps you.

— First entries arrive with Episode 02

The series begins with framing. The literature base begins with the search.

A research method, made visible.

The series is built with Claude as a research and writing partner. Not as decoration — as the actual working method. PubMed searches, paper extraction, evidence tables, regulatory mapping, slide logic.

Every essay includes a "How I used Claude" section showing exactly where the AI helped and where it didn't. The methodology is the second deliverable. If you want to replicate it for your own field, everything you need will be here by October.

Lyon, 31 October 2026.

— The talk

Big data, AI and sepsis prediction opportunities in the NICU

A 20-minute talk for the Omics in Sepsis session at CEPAS 2026 — the first Congress of the European Paediatric Academic Societies.

CongressCEPAS 2026 · 1st of its kind
Dates28–31 October 2026
VenueCentre de Congrès, Lyon
SessionOmics in Sepsis · Sat 31 Oct, 10:30–11:30 CET