Machine Learning for Precision Medicine
We are using machine learning and precision medicine to help us see patterns in complex data to improve the diagnosis, care, and treatment of children and youth with NDDs.
Improving the accuracy and timeliness of NDD diagnosis is a key research priority for people with NDDs and their caregivers. A missed or late diagnosis of an NDD can have significant negative impacts on an individual, including higher incidence of depression, anxiety, and other psychiatric disorders, increased social, emotional, and behavioral challenges, such as self-harm, and decreased quality of life. Conversely, diagnostic clarity is associated with improved mental health and self-esteem into adulthood. Additionally, early and accurate diagnosis of an NDD allows for timely access to therapeutic supports such as evidence-based early intervention. One of the primary barriers to improving diagnostic accuracy and timeliness is the heterogeneity of NDDs. There is also significant overlap between many neurodevelopmental and psychiatric disorders, and these disorders commonly co-occur.
This creates significant challenges within the current diagnostic pathway, in which NDD diagnoses are made clinically by a specialized physician or psychologist based on symptoms that are mapped onto a diagnostic tool such as the Diagnostic and Statistical Manual of Mental Disorders (DSM-V, 2013). Currently, there are no biomarkers or other investigations that reliably confirm a diagnosis of autism.
Collaborators:
The PN Lab Advisory Council
Dr. Nils D. Forkert PhD, Professor, Radiology, University of Calgary