Current position (Nov 2025 -)
Current I am a senior postdoc at ICAI Applied AI Accelerator (A3) lab of UMC Groningen. I am in the Predictive Analytics and Computer Vision focused wing of this brand new lab, which is embedded in the Dept. of Orthopaedics. I have the same research focus as what I found for myself during my TU/e days, but trying to add more of image data analysis tools in my arsenal.
Postdoc position (June 2023- Oct 2025)
While working as a postdoc at M&CS, TU Eindhoven, as a part of ITEA4 DAIsy project, I found my research “calling”/ the reason I am sticking around in academia: (pseudo) Causal ML and Uncertainty Quantification. I gained experience in project and stakeholder management while co-leading the workpackage of this project that focused on development of AI solutions for Major depressive disorder and Eating disorder.
Postdoc position (Sep 2021-May 2023)
I worked jointly at the Institute of Risk Assessment Science (IRAS) in Utrecht University and at UMC Utrecht. I am learned about exposome and cardiovascular risks, and used interpretable ML models to find urban exposomes which increased risks of mortality.
PhD research
During my PhD I worked on interpretable supervised machine learning approaches to deal with real world medical data, with the final goal of having computer aided clinical decision support system for medical professionals , and knowledge extraction from provided datasets.
Here you can find a summary of my academic journey till now.
Publications
-
All in the Name of Artificial Intelligence: A Commentary on Linardon (2025) – an invited commentary for International Journal of Eating Disorder – Pia Burger and Sreejita Ghosh
-
Interpretable modelling and visualization of biomedical data – Sreejita Ghosh, Elizabeth S. Baranowski, Michael Biehl, Wiebke Arlt, Peter Tino, Kerstin Bunte
-
A prototype-based model for set classification –Mohammad Mohammadi and Sreejita Ghosh
-
Review of Machine Learning solutions for Eating Disorders –Sreejita Ghosh, Pia Burger, Mladena Simeunovic Ostojic, Joyce Maas, Milan Petkovic
-
Stacking multiple prediction models to optimise performance in local settings: exemplars in cardiometabolic disease (Preprint) –Sreejita Ghosh, Jasmine Gratton, Roel C.H Vermeulen, Folkert W Asselbergs, Jelle J. Vlaanderen, Amand Floriaan Schmidt
-
Intrinsically Interpretable Machine Learning In Computer Aided Diagnosis (PhD thesis)
-
Visualisation and knowledge discovery from interpretable models –Sreejita Ghosh, Peter Tino, Kerstin Bunte
-
Positive and negative parenting in conduct disorder with high versus low levels of callous–unemotional traits -Ruth Pauli, Peter Tino, Jack C. Rogers, Rosalind Baker, Roberta Clanton, Philippa Birch, Abigail Brown, Gemma Daniel, Lisandra Ferreira, Liam Grisley, Gregor Kohls, Sarah Baumann, Anka Bernhard, Anne Martinelli, Katharina Ackermann, Helen Lazaratou, Foteini Tsiakoulia, Panagiota Bali, Helena Oldenhof, Lucres Jansen, Areti Smaragdi, Karen Gonzalez-Madruga, Miguel Angel Gonzalez-Torres, Maider Maider Gonzalez de Artaza-Lavesa, Martin Steppan, Noortje Vriends, Aitana Bigorra, Reka Siklosi, Sreejita Ghosh, Kerstin Bunte, Roberta Dochnal, Amaia Hervás, Christina Stadler, Aranzazu Fernandez-Rivas, Graeme Fairchild, Arne Popma, Dimitris Dikeos, Kerstin Konrad, Beate Herpertz-Dahlmann, Christine M. Freitag, Pia Rotshtein, Stephane A De Brito
-
Comparison of strategies to learn from imbalanced classes for computer aided diagnosis of inborn steroidogenic disorders –Sreejita Ghosh, Elizabeth S. Baranowski, Rick van Veen, Gert-Jan de Vries, Michael Biehl, Wiebke Arlt, Peter Tino, Kerstin Bunte
Sreejita Ghosh 