RESEARCH TOPICS

With the growing penetration of electronic media and advancement in computational methodology including generative AI and Machine Learning, it is a golden opportunity to digitalize our approaches to different psychiatric disorders - from phenotyping to intervention. Researchers explore integrating artificial intelligence to screen out possible persons for early intervention and prevention. We have employed a wide range of computational techniques including multimodal sensing, natural language processing, speech analysis, computer vision and pattern recognition, and deep phenotyping in psychiatric research. Ecologically friendly digital platform is also utilized increasingly for psychoeducation and behavioral intervention, especially in the post-COVID era, when the unmet needs for mental health care could be safely bridged with digital tools that have become part of everyone’s daily life. We are aiming to develop a new generation of digital mental health interventions to make the treatment experience more engaging and interactive.

In parallel, computational psychiatry holds promise for bridging basic research and clinical practice in safeguarding mental health. We leverage advancements in computational psychiatry to develop data-driven models, fine-tune machine learning, and establish cross-species comparisons to deepen our understanding of the biophysiological mechanisms underlying psychiatric disorders. These computational analyses allow us to translate extensive genetic, cellular, and molecular knowledge from model organisms to map neural pathologies in humans. This approach builds a foundation for more precise classifications of psychiatric disorders and fosters the development of targeted interventions that address unique pathological profiles, ultimately leading to more personalised treatment strategies.