Zu den Inhalten springen

Data-driven medicine from routine data

Dozent:PD Dr. Nadine Binder
Vorbesprechung:Donnerstag, 23.07.2026 um 13:00 Uhr, IMBI HS, Stefan-Meier-Str. 26
Vorbesprechung: Dienstag, 06.10.2026 um 16:30 Uhr, IMBI HS, Stefan-Meier-Str. 26
Datum: Blockseminar: 07.12.2026 und 14.12.2026
VLVZ:04LE58S-Allg-Data-FA

Description

The seminar is a journal‑club style meeting where we critically read and discuss recent papers that use routine health‑care data. You’ll dissect the statistical or computational models, incl. survival analysis, causal‑effects methods, or machine learning, that turn raw diagnoses, labs, or medication records into clinical insights. You’ll work individually or potentially in pairs with medical students to prepare a presentation that summarizes the study, evaluates its methodology, and reflects on how the mathematics could be refined or applied elsewhere. The seminar format will allow you to sharpen your ability for interpreting quantitative research, bridge theory with practice, and experience the interdisciplinary dialogue that drives modern evidence‑based medicine.

 

Date

Time

Presenter

Topic

02.11.202610:15 - 12:00Nadine BinderIntroduction into the seminar topic
07.12.20269:00 - 10:15Leixian WangBaneshi et al. (2024). Comparison of seven models for the progression patterns of multiple chronic conditions in longitudinal studies. BMJ Public Health, 2(2), e000963. https://doi.org/10.1136/bmjph-2024-000963
07.12.202610:30 - 11:45Ding WangUrbut et al. (2024). MSGene: A multistate model using genetic risk and the electronic health record applied to lifetime risk of coronary artery disease. Nature Communications, 15(1). https://doi.org/10.1038/s41467-024-49296-9
07.12.202612:45 - 14:00Yiqing ZhangQiu et al. (2025). Deep representation learning for clustering longitudinal survival data from electronic health records. Nature Communications, 16(1). https://doi.org/10.1038/s41467-025-56625-z
07.12.202614:15 - 15:30Yu-Hsuan TungXian et al. (2025). Transformer patient embedding using electronic health records enables patient stratification and progression analysis. npj Digital Medicine, 8(1). https://doi.org/10.1038/s41746-025-01872-z
07.12.202615:45 - 17:00Yujia LiuLee et al. (2025). Clinical decision support using pseudo-notes from multiple streams of EHR data. npj Digital Medicine, 8(1). https://doi.org/10.1038/s41746-025-01777-x
14.12.20269:00 - 10:15Jingxian LeiGadd et al. (2026). SurvivEHR: A competing risks, time-to-event foundation model for multiple long-term conditions from primary care electronic health records. npj Digital Medicine, 9(1). https://doi.org/10.1038/s41746-026-02709-z
14.12.202610:30 - 11:45Jana WentgesMakarov et al. (2025). Large language models forecast patient health trajectories enabling digital twins. npj Digital Medicine, 8(1). https://doi.org/10.1038/s41746-025-02004-3
14.12.202612:45 - 14:00Michaela MayerManzini et al. (2025). Deep survival analysis of longitudinal EHR data for joint prediction of hospitalization and death in COPD patients. arXiv. https://arxiv.org/abs/2511.05960 
14.12.202614:15 - 15:30Jakob KailerLangbein et al. (2025). Gradient-based explanations for deep learning survival models. Proceedings of the 42nd International Conference on Machine Learning (ICML), PMLR 267, 32492–32522. 
14.12.202615:45 - 17:00Yuhuan LiPickard et al. (2026). EHR-MPC: Inference-time control for sepsis treatment with generative patient digital twins. arXiv. https://arxiv.org/abs/2607.08793

 

Contact:

PD Dr. Nadine Binder, nadine.binder@uniklinik-freiburg.de 

Institute of General Practice, Medical Center, University of Freiburg

Freiburg Center for Data Analysis, Modelling and AI (FDMAI)

CRC 1597 Small Data, https://www.smalldata-initiative.de

 

 

 

Kontakt

Klicken Sie hier um zu unserer Kontaktseite zu gelangen.