Application of computational models to ADHD

This project will use precision medicine to improve treatment of childhood Attention Deficit Hyperactivity Disorder (ADHD). Methylphenidate is the first-line pharmacological treatment but there is wide individual variation in outcomes: 30% of children will have no clinically meaningful response. There is currently no validated objective, quantitative method for predicting who will ultimately respond. We propose to use neurally informed computational models derived from behaviour and electroencephalography to decompose medication effects on distinct neural mechanisms. Tasks will be gamified to maintain engagement. Interrogating this immense amount of data will be solved by using computational model parameters as inputs into machine learning algorithms. The goal will be to identify neurocognitive processes predicting who will respond clinically to methylphenidate. 

 The successful candidate will have a background in engineering, computer science or a cognate discipline, an outstanding academic record and demonstrate a strong commitment to PhD research. They will register as a full-time PhD student in the School of Psychology, in March 2022 (a later start is not possible). The candidate will have responsibility for acquisition & analysis of mobile EEG data during gamified test validation and testing & refinement of computational model methods using simulated data. The student will also be expected to publish outputs both in journals and as open-source software.

For more information, including application process see: http://www.whelanlabtcd.org/computational_models_adhd_tcd_phd/