The Predictive Society and AI (PSAI) Lab conducts interdisciplinary research at the intersection of data science and artificial intelligence (AI). Our work focuses on developing and applying high-dimensional, often network-based methods, primarily in medicine and health. Additionally, we explore applications in financial markets and engineering. To achieve explainable models, we balance data-driven and model-based approaches, leading to the development of digital twins.
Our data-driven research leverages diverse data sources across various domains. In the biological domain, we analyze high-throughput genomic data, such as gene expression, methylation, and RNA-seq data generated by next-generation sequencing (NGS) technologies. Our primary focus is on medical and health-related questions concerning complex disorders and their underlying biological mechanisms. We have extensive experience working with data from various cancer types, including breast, colon, and prostate cancer, as well as conditions such as cystic fibrosis, asthma, and diabetes. Additionally, we address text mining challenges, particularly those involving electronic health records (EHR), to automate clinical prediction tasks. All of our studies are conducted in close collaboration with clinicians.
In addition, we also analyze data from financial markets, social media, and marketing, with a particular focus on forecasting system behavior, such as stock prices, consumer behavior, and human personality. To achieve this, we often employ network-based approaches within a statistical framework. Examples for industrial partners are Nokia (Finland), Cargotec (Finland), Elisa (Finland), and Hughes insurance (UK).
For a very brief overview and an introductory video of our research see here.
created with
Website Builder .