News
Our ambition is to share major announcements, results and events on this page. While the website development is still in progress, sign up to our newsletter and read our previous newsletters. Also, you can find links to our SoMe accounts on our personal profile pages under the Team tab.
Previous Newsletters
Machine Learning & Clinical Prediction Journal Club
The MLCP journal club is a monthly, interdisciplinary journal club for anyone interested in machine learning and/or clinical prediction. We cover technical aspects, but the focus is ultimately on the practical, clinical use-cases of machine learning (e.g. for clinical prediction of cardiovascular disease), where we dissect pitfalls and limitations to cut through the hype. Anyone can join the journal club (e.g. students, clinicians, researchers from outside of Steno Aarhus), the only expectation is that you read the actual article before joining and come with an open mindset.
Upcoming sessions
2025 Spring Plan
Date, time May 5, 12-13
Location Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article Carrasco-Zanini et al. Multi-omic prediction of incident type 2 diabetes, Diabetologia. link
Date, time May 26, 12-13
Location Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article Kaufman et al. Linear effects of glucose levels on voice fundamental frequency in type 2 diabetes and individuals with normoglycemia, Scientific Reports. link
Date, time Jun 16, 12-13
Location Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article Wildcard // To be decided. Stay tuned…
Past Sessions
See past sessions
Date, time: Mar 24, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Kapoor & Narayanan. Leakage and the reproducibility crisis in machine-learning-based science, Patterns. Link
Date, time: Feb 24, 12-13
Location: Spektrummet (A401-111), Steno Diabetes Center Aarhus (see Contact page)
Article: Kim et al. Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data, arXiv. Link
Date, time: Jan 27, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Helmink et al. Lifetime and 10-year cardiovascular risk prediction in individuals with type 1 diabetes: The LIFE-T1D model, Diabetes, Obesity & Metabolism. Link
Date, time: Dec 16, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Zhou et al. A foundation model for generalizable disease detection from retinal images, Nature. Link
Date, time: Nov 25, 12-13
Location: Spektrummet (A401-111), Steno Diabetes Center Aarhus (see Contact page)
Article: Groh et al. Deep learning-aided decision support for diagnosis of skin disease across skin tones, Nature Medicine. Link
Date, time: Oct 28, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Maris et al. Ethical use of artificial intelligence to prevent sudden cardiac death: an interview study of patient perspectives, BMC Medical Ethics. Link
Date, time: Sep 23, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Jiang et al. Health system-scale language models are all-purpose prediction engines, Nature. Link
Date, time: Aug 26, 12-13
Location: Mellemrummet (A201-247), Steno Diabetes Center Aarhus (see Contact page)
Article: Hughes et al. A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease, npj Digital Medicine. Link
Date, time: Jun 24, 12-13
Location: Hjerterummet (A201-248), Steno Diabetes Center Aarhus (see Contact page)
Article: Deng et al. Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients, npj Digital Medicine. Link
Date, time: May 27, 12-13
Location: Krearummet (A301-100), Steno Diabetes Center Aarhus (see Contact page)
Article: Tang et al. Evaluating large language models on medical evidence summarization, npj Digital Medicine. Link
The program for the next five to six months is unveiled around the end of each semester. Feel free to suggest topics or papers you would like to see a session on.