Silvia Grazioli

Psychologist and statistician, lecturer in the undergraduate program at SFU Milano, and doctoral candidate in Computational Psychotherapy at SFU Vienna.

In 2016, she earned a Master’s degree in Clinical and Developmental Psychology and Neuropsychology from the University of Milano-Bicocca. Subsequently, in 2022, she obtained a Master’s degree in Biostatistics from the same university.

She served as a research consultant at the Laboratory of Developmental Psychopathology of the Scientific Institute IRCCS E. Medea – Associazione La Nostra Famiglia, Bosisio Parini (LC). In this Institute, she contributed to research projects focusing on the developmental trajectories of neurodevelopmental and psychopathological disorders. Additionally, she engaged in research initiatives concerning the development of predictive Machine Learning models to support diagnostic processes at the SmartLab (Digital Innovation Laboratory for Clinical and Applied Research in Developmental Psychopathology).

She conducted clinical practice for the European Institute for the Study of Human Behavior (IESCUM) at the Policlinico Hospital in Milan, specializing in children with neurodevelopmental and externalizing disorders.

Since 2022, she has been a lecturer for Statistics I and Experimental Psychology I in the undergraduate program at SFU Milano. Simultaneously, she pursues her doctoral research at SFU Vienna. At SFU, her research focuses on the application of predictive Machine Learning models and technological development to support clinical activities in psychotherapy. This work is conducted in collaboration with the Psychotherapy School Studi Cognitivi and the InTherapy psychotherapy service.

She collaborates with the AIDA (Artificial Intelligence and Data Analysis) and MeThe (Metacognitive Theory and Therapy) Research Laboratories.

Research interests

Computational Psychometrics and Psychotherapy: Application of traditional statistics and Machine Learning (Artificial Intelligence) for clinical purposes.

Methodological focus:

  • Supervised Machine Learning: Prediction of therapy outcomes based on socio-anamnestic data and clinical questionnaires.
  • Unsupervised Machine Learning and clustering: Identification of homogeneous patient phenotypes using bio-psycho-social data.

Clinical areas of interest:

  • Quality of psychotherapy services and intervention effectiveness.
  • Therapy dropout.
  • Attention Deficit Hyperactivity Disorder (ADHD), autism spectrum.
  • Trajectories of psychopathological symptoms from childhood to adulthood.


Silvia Grazioli – Google Scholar