Schizophrenia is one of the most debilitating neuropsychiatric disorders, affecting about 1% of the global population. It presents a range of symptoms, including hallucinations, delusions (collectively known as psychosis), cognitive impairments, lack of motivation, and depression. Typically diagnosed in late adolescence, schizophrenia causes significant disruptions in an individual’s life, impacting educational achievements, employment opportunities, and social interactions. Over time, individuals with schizophrenia place considerable mental and financial strain on their families, often becoming isolated and dependent on state resources, thus imposing a societal financial burden.
Research has shown that early diagnosis of schizophrenia can lead to better treatment outcomes, a shorter duration of illness and functional decline, and a reduced risk of progressing from at-risk mental states to full-blown psychosis. Despite efforts to identify a biomarker for schizophrenia, there is a growing interest in the early identification and treatment of individuals at high risk of developing psychosis. Most biomarker research in psychiatry and clinical neuroscience has focused on individuals experiencing their first psychotic episode or those at high risk of psychosis. However, comparisons limited to these extremes may obscure our understanding of how psychosis develops in a small fraction of the general population.
This project aims to use machine learning to differentiate between at-risk and not-at-risk psychosis categories in healthy individuals based on brain alterations and cognitive scores. We will investigate how these patterns change over time and how they correlate with symptom changes. By utilizing the extensive dataset from the UK Biobank, which includes data from around half a million individuals, we aim to enhance the robustness and predictive power of our machine learning model.
Additionally, we plan to apply this model to an adolescent cohort to evaluate its effectiveness in identifying young individuals at increased risk of developing psychosis later in life.
The project is expected to span three years, during which we aim to make significant contributions to the biomarker research of schizophrenia and provide valuable neuropsychological insights for early psychosis risk prediction.