
Data Science for Digital Psychiatric Phenotyping
ABOUT EVENT
In-Person Registration: https://forms.gle/suttgW6QHUW1N4Z56
Virtual Registration: http://go.hawaii.edu/VvS
Seminar Abstract:
Early childhood is the most efficacious opportunity to impact long-term health and learning. However, there are major bottlenecks to care which have resulted in a massive shortage of clinicians for diagnosis and treatment. These gaps in healthcare access disproportionately affect underserved and marginalized populations. My talk discusses novel data science methods for developing a streamlined system for continuously phenotyping children with potential developmental delays by leveraging distributed non-expert crowd workers in conjunction with machine learning algorithms. This involves collecting diagnostically rich information from children and their parents in a secure and trustworthy manner, curating a reliable and capable crowd workforce for precisely extracting behavioral features, and training behavioral computer vision classifiers for automatic detection of neurodevelopmental concerns. Throughout my talk, I will highlight the opportunities for further methodological data science innovations in quantifying human behavior more broadly.
Speaker Bio
Dr. Peter Washington is a PhD candidate in Bioengineering at Stanford University, where he is a Stanford Interdisciplinary Graduate Fellow. Previously, Dr. Washington completed an MS in Computer Science at Stanford University and his BA in Computer Science at Rice University. Dr. Washington is interested in interdisciplinary data science problems at the intersection of health informatics, machine learning, and human-computer interaction. His long-term research goal is to make neuropsychiatric and mental healthcare more accessible and effective through the development of data science methods which span the entire data science pipeline: trustworthy data capture paradigms, precise data labeling algorithms, robust machine learning models, and real-world application of the resulting models and analyses. He also enjoys teaching data science, including as a lead instructor for Inspirit AI.