Richard Polzin

AI Researcher · JRC COMBINE · Aachen, Germany

I build models that notice an intensive-care patient going downhill before the numbers make it obvious.

Richard Polzin
Right nowPreparing an ICU oxygenation model for external validation, teaching version control to research groups, and building out a home lab for local inference work.

What I work on

  • Predictive modelling for intensive care

    Time-series models that forecast oxygenation deterioration up to 72 hours ahead — the subject of my PhD and my current paper.

  • Accessible high-performance computing

    Supporting clinical research groups who have the data but not the cluster experience, through the NHR4CES Simulation and Data Lab.

  • Open tools and materials

    Publishing the tools and teaching materials alongside the research, not only the papers.

Papers

first author

Predicting a sudden decrease in oxygenation in mechanically ventilated adult intensive care patients

Machine Learning: Health · 2026 · Polzin R, Fritsch S, Sharafutdinov K, Bickenbach J, Marx G, Schuppert A

Algorithmic surveillance of ICU patients with ARDS (ASIC): protocol for a multicentre stepped-wedge cluster randomised quality improvement strategy

BMJ Open · 2021 · Marx G, Bickenbach J, Fritsch SJ, et al. — one of ~45 co-authors

Where I've been

2024 →

Postdoc, JRC COMBINE

Continuing the ICU prediction work with Prof. Schuppert's group, focused on clinical applicability.

2018 – 24

Ph.D., JRC COMBINE

Six years on ARDS prediction for intensive-care patients, working with routine clinical data.

2016 – 18

M.Sc., Maastricht University

Natural language processing and machine learning — sentiment analysis, topic modelling, deep learning.

2013 – 16

B.Sc., Aachen

Computer science and mathematics, alongside a first developer role at a CNC simulation company.

Projects I'm part of

2023 →

EDITH CSA

Charting the road from single-organ models to whole-body digital twins.

2023 →

SDL Digital Patient

Bringing high-performance computing capability to healthcare research groups.

2023 →

CCLS

RWTH's push to bring computational methods to the life sciences.

2018 – 23

SMITH

The clinical data platform behind my PhD work on early warning for ARDS.

Workshops I've run

All materials are free to reuse — each entry opens the full slide deck.

Nov 2025

Version Control for Researchers

A practical introduction to version control for research code: branching, collaboration, and a history you can actually retrace.

Nov 2024

Synthetic Data in Medicine

When real patient data can't be shared — open-source tools for generating realistic medical datasets.

Nov 2024

HPC for Researchers

From SLURM fundamentals through to applying for time on national compute resources.

Oct 2024

LLMs at CCLS

Using large language models for research on CCLS infrastructure — worked examples and practical guidance.

Outside the lab

  • Home lab

    Self-hosted services, local LLM inference, and my own network infrastructure.

  • Coffee roasting

    Roasting my own beans at home.

  • Photography & gaming

    Photography around Aachen, and co-op gaming when there is time.

Get in touch

The quickest ways to reach me.

Emailmail@richardpolzin.com SignalStart a chat GitHubgithub.com/DeastinY
WhereAachen, Germany