DrNazanin Zounemat Kermani

Dr. Nazanin Zounemat-Kermani is a computational methodist—a scientist who designs original mathematical frameworks and algorithms—dedicated to generating clinical knowledge from multi-faceted biomedical data. At Imperial College London, her innovative methodology integrates genomics and medical imaging to pioneer precision medicine for complex respiratory diseases.

She holds an MSc in Multimedia & Intelligent Systems from the University of Amsterdam and a PhD in Biomedicine from Imperial College London, where her research focused on data mining for systems medicine and spectroscopic profiling. Her PhD was supervised by Professors Zoltan Takats, Yike Guo, and Jeremy Nicholson.

Dr.  Zounemat-Kermanicompleted her postdoctoral training at the Data Science Institute and the National Heart & Lung Institute, Imperial College London. During this time, she developed machine learning methods for the integration of multi-omics datasets to support the endotyping of respiratory diseases. She also led the development of a data management platform for RASP-UK, a consortium bringing together clinical and academic leaders from UK universities and the pharmaceutical industry to address refractory asthma.

She has contributed to PIONEER, an Innovative Medicines Initiative (IMI) funded project, where she worked on federated machine learning approaches for health data aimed at tackling prostate cancer using big data.

Currently, Dr.  Zounemat-Kermani is working on computational methods for genomics data integration and AI-driven projects focused on respiratory health, including PRISM-UK and AI-RESPIRE. She is also an active member of the U-BIOPRED consortium, applying machine learning and systems medicine approaches to one of Europe's largest severe asthma cohorts to uncover disease mechanisms. Her work is supported through the IMI and EFPIA.

Dr. Kermani has authored and co-authored over 60 scientific publications and is committed to advancing precision medicine through the application of AI and integrative data science.