Pejman Shojaee

Quantitative models for questions that start in the clinic

I am a mathematical biologist and systems medicine researcher. My work sits where biological and clinical questions get turned into something quantitative — mechanistic models where the biology is understood, statistical and machine learning models where it is not, and careful uncertainty quantification to keep the difference honest.

I am currently a postdoctoral researcher at Universitätsklinikum Carl Gustav Carus Dresden and TU Dresden, on the Präzisionsmedizin und Molekulare Prävention (PräMo) project. The question driving it: can changes in the immune system and in blood proteins reveal the early signs of metabolic disease — particularly type 2 diabetes — long before a clinical diagnosis? I work with large-scale cohorts such as the UK Biobank alongside in-house data, using machine learning to trace immune–metabolic connections over time. I am also affiliated with the German Center for Diabetes Research (DZD) and the IRTG 3019: MEDIS graduate school.

Before that, my doctoral research in the Center for Interdisciplinary Digital Sciences (CIDS) at TU Dresden asked when and where a glioblastoma comes back. I built hybrid in-silico models of tumour–macrophage interaction and coupled them with radiomic features from clinical imaging to predict time to relapse — and to work out which biopsies actually carry predictive information. I completed the PhD in Mathematics in 2025 under the supervision of Prof. Haralampos Hatzikirou.

My background is in biomedical and mechanical engineering, and I enjoy the parts of this work that involve mentoring PhD students and helping projects from study design through to analysis and writing.