Dr. Vai is a psychologist and psychotherapist. During her Ph.D. she studied the impact of childhood stress on the neural correlates of psychiatric disorders. In her current research, she integrates specific knowledge of clinical neuroscience, computational psychiatry, artificial intelligence, and biology to identify clinical and biological signatures to improve the prevention and treatment of mental disorders through precision medicine approaches. Dr. Vai has published in international scientific journals such as Lancet Psychiatry, and she is the recipient and key researcher in national and international grants. She received several awards from the European College of Neuropsychophrmachology, where she is a core member of the Immuno-NeuroPsychiatry Network.

BRIEf INTRODUCTION

The burden of mental disorders is constantly growing despite the availability of new therapeutics, defining a severe concern in terms of public health. Nowadays, the diagnosis and treatment of psychiatric disorders are mainly based on the collection of signs and symptoms, not on biological, environmental, and psychological factors involved in etiopathogenesis. However, in most cases, patients show a mixed clinical picture, suggesting an underlying heterogeneity, which often leads to a no-treatment response, forcing several attempts before identifying an effective treatment. A tremendous need exists to identify reliable biomarkers and tools to prompt more rapid and effective clinical management. In recent years, we observed an impressive increase in sophisticated bioinformatic techniques to analyze large amounts of biological information and the development of large biobanks. This has created an unprecedented opportunity to develop a more precise dimensional stratification of psychiatric disorders and more effective treatment strategies.

RESEARCH ACTIVITY

Dr. Vai's research focuses on integrating different biological and clinical data, including genetics, multimodal neuroimaging, immunoinflammatory factors, and environmental and psychological variables, to stratify psychiatric patients and predict their outcomes, such as differential diagnosis, prognosis, treatment response, or comorbidity risks. Using several approaches in artificial intelligence, machine learning, and bioinformatics, she looks at recurring patterns in participants' datasets to enhance early detection methods, develop more effective intervention strategies, and understand the factors involved in the etiopathogenesis of mental health disorders. 

22 H-index – Scopus (1/6/2023)

Click here to see our publications.