Neuroimaging increasingly exploits machine learning techniques in an attempt to achieve clinically relevant single-subject predictions. We will discuss the rationale behind a computational approach to neuroimaging-based single-subject inference, focusing on its potential for characterising disease mechanisms in individual subjects and mapping these characterisations to clinical predictions.
We will review computational neuroimaging strategies for single patient predictions. This will include generative models for inferring individual disease mechanisms in psychiatry and neurology, mapping inferred mechanisms to clinical predictions by Bayesian model selection and generative embedding. Finally we will make a link to a mechanistic model-based approach to statistical perspectives by machine learning.
Questions we will tease:
What is single-subject research? How does it differs from other types of neuroimaging research?
What are case studies? What are some of their strengths and weaknesses?
When and why use single-subject research?
LEARNING OBJECTIVES:
Describe the basic elements of a single-subject research design.
Design simple single-subject studies using reversal and multiple-baseline designs.
Explain how single-subject research designs address the issue of internal validity.
Interpret the results of simple single-subject studies based on the visual inspection of graphed data.