Publications & Patents
First author and co-author on peer-reviewed publications in npj Digital Medicine and other PubMed-indexed journals, with a focus on multimodal machine learning (video, audio, and language) for clinical measurement — and on rigorous validation of what these models can and cannot detect.
Recent Publications
Multimodal machine learning for video based single question mental health assessment
Machine learning approach for mental health assessment using video-based single question responses, combining multimodal signals for clinical screening.
Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence
Development and validation of a production AI system for screening tardive dyskinesia from clinician-labeled video data.
Cross-Dataset Evaluation of an Automated Video-Based Model for Detecting Tardive Dyskinesia Using the Clinician's Tardive Inventory: Validation Study
External-dataset validation of the video-based vision-transformer tardive-dyskinesia model (TDtect) against the Clinician's Tardive Inventory — testing how the model generalizes beyond its training distribution.
Multimodal Acoustic–Linguistic Machine Learning for Postpartum Depression Screening
Multimodal model fusing acoustic (voice) and linguistic signals to screen for postpartum depression.
PHQ-V/GAD-V: Assessments to identify signals of depression and anxiety from patient video responses
Video-based assessment tools for detecting depression and anxiety signals from patient responses using multimodal machine learning.
Remote monitoring and AI for detecting tardive dyskinesia and improving patient outcomes
Remote monitoring systems using artificial intelligence for movement disorder detection and patient outcome improvement.
Patents
Machine learning classification of video for determination of movement disorder symptoms
System and method for using machine learning to classify video data for automated detection and assessment of movement disorder symptoms.
Methods, devices, and systems for remotely controlling a communication device
Systems and methods for controlling communication systems for the hearing impaired. The invention includes a portable communication device that connects to and controls multiple communication devices, with a user interface that enables transferring calls between devices.
Earlier Research — Imaging & Connectomics
Image-analysis and large-scale scientific-visualization work from my time at the University of Utah's SCI Institute (the foundation of my image-processing background):
- Anderson JR, Grimm B, et al. Exploring the retinal connectome. Molecular Vision, 2011.
- Anderson JR, et al. The Viking viewer for connectomics: scalable multi-user annotation and summarization of large volume data sets. Journal of Microscopy, 2011.
- Anderson JR, et al. Automatic mosaicking and volume assembly for high-throughput serial-section transmission electron microscopy. Journal of Neuroscience Methods, 2010.
Research Contributions
Contributed to NIH-funded research in movement disorder assessment and digital health applications. Lead and mentor data science and labeling teams, setting validation standards, safety checks, and quality gates across deployed systems.