I am currently working as a postdoc, jointly at the Institute of Risk Assessment Science (IRAS) in Utrecht University and at UMC Utrecht. The research is still anthropocentric. I am learning about exposome and cardiovascular risks, and trying to use interpretable ML models for improving causal discovery.
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.
Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets (Preprint)
Sreejita Ghosh, Elizabeth S. Baranowski, Michael Biehl, Wiebke Arlt, Peter Tino, Kerstin Bunte
Intrinsically Interpretable Machine Learning In Computer Aided Diagnosis (PhD thesis)
Visualisation and knowledge discovery from interpretable models
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