Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer
Dustin Scheinost1, Angeliki Pollatou2, Alexander J Dufford3
1Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut; Department of Biomedical Engineering, Yale University, New Haven, Connecticut; Department of Statistics and Data Science, Yale University, New Haven, Connecticut; Child Study Center, Yale School of Medicine, New Haven, Connecticut; Interdepartmental Neuroscience Program, Yale University, New Haven, Connecticut.
Insights
Predictive models in neuroimaging can now assess mental health risks in early childhood. This review guides researchers in using these tools for fetal, infant, and toddler (FIT) neuroimaging to predict developmental trajectories.
Area of Science:
- Neuroimaging
- Developmental Neuroscience
- Psychiatry
Background:
- Predictive models in neuroimaging are crucial for psychiatric risk stratification.
- Current models primarily focus on school-aged children, neglecting the critical fetal, infant, and toddler (FIT) period.
- Altered brain maturation in the FIT period is linked to later mental health issues.
Purpose of the Study:
- To facilitate the use of predictive models in FIT neuroimaging.
- To provide a primer and systematic review of methods in current FIT predictive modeling studies.
- To identify common practices, under-researched areas, and future directions.
Main Methods:
- Systematic review of over 100 studies in the past decade.
- Analysis of topics, neuroimaging modalities, and machine learning methods used in FIT research.
- Identification of ethical and future considerations for researchers.
Main Results:
- The review synthesizes common approaches and highlights under-researched areas in FIT predictive modeling.
- Identified trends in neuroimaging modalities and machine learning techniques.
- Ethical considerations and future research avenues are outlined.
Conclusions:
- The past decade of FIT research has established a foundation for predicting early-life mental health trajectories.
- Predictive modeling in FIT neuroimaging offers powerful tools for understanding developmental mechanisms.
- Further research is needed to accelerate the prediction of health and illness across the early developmental spectrum.
Abstract:
Predictive models in neuroimaging are increasingly designed with the intent to improve risk stratification and support interventional efforts in psychiatry. Many of these models have been developed in samples of children school-aged or older. Nevertheless, despite growing evidence that altered brain maturation during the fetal, infant, and toddler (FIT) period modulates risk for poor mental health outcomes in childhood, these models are rarely implemented in FIT samples. Applications of predictive modeling in children of these ages provide an opportunity to develop powerful tools for improved characterization of the neural mechanisms underlying development. To facilitate the broader use of predictive models in FIT neuroimaging, we present a brief primer and systematic review on the methods used in current predictive modeling FIT studies. Reflecting on current practices in more than 100 studies conducted over the past decade, we provide an overview of topics, modalities, and methods commonly used in the field and under-researched areas. We then outline ethical and future considerations for neuroimaging researchers interested in predicting health outcomes in early life, including researchers who may be relatively new to either advanced machine learning methods or using FIT data. Altogether, the last decade of FIT research in machine learning has provided a foundation for accelerating the prediction of early-life trajectories across the full spectrum of illness and health.
