Accepted · WellComp 2026 01
ReliaGate
When should a wearable stress model surface a prediction—and when should it withhold one?
+10.1 pp coverage −5.6 pp accepted risk 4 public datasets
Dartmouth College · Computer Science
Jaden Moon
Reliable machine learning for health.
I study when AI systems should answer, defer, or trigger human review, with research in selective prediction, uncertainty quantification, distribution shift, multimodal health sensing, and medical imaging.
I am a computer science student at Dartmouth College, where I work with Prof. Andrew T. Campbell in the HealthX Lab. At Mayo Clinic, I am advised by Wei Liu, Ph.D. Earlier, I worked closely with Nicholas C. Jacobson, Ph.D. and Michael V. Heinz, M.D. on AI for mental health.
HealthX Lab Prof. Andrew T. Campbell · Dartmouth College
Mayo Clinic SURF Wei Liu, Ph.D. · Radiation oncology
4 public wearable datasets Subject-disjoint, validation-locked evaluation
Featured research
Methods, evidence, and failure modes.
Each project is organized around the question, the evaluation design, and the evidence—not a generic technology list.
Accepted · INTERSPEECH 2026 02
Multimodal Reliance Diagnostics
Does a quality-aware fusion model actually use its reliability signals at inference time?
25 runs / dataset 2 multimodal datasets
Ongoing · Mayo Clinic 03
Radiotherapy Segmentation QA
How can an AI system identify autosegmentations that require human review under asymmetric clinical risk?
59.4% low-risk coverage 99.91% NPV 0.936 AUROC
Ongoing follow-on work 04
ReliaGate++
Extending static routing into validation-locked temporal emission control and episode-level reliability auditing.
Cue precision Subject reach Episode coverage
Updates
Recent news.
Jul 29, 2026
My first-author paper, “ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction,” was accepted to WellComp 2026, an UbiComp/ISWC 2026 workshop.
Jun 16, 2026
I started the Mayo Clinic Summer Undergraduate Research Fellowship, working with Prof. Wei Liu on reliable AI for radiation oncology.
Jun 03, 2026
My first-author paper, “When Does Quality-Aware Multimodal Fusion Matter?”, was accepted to INTERSPEECH 2026.
Interested in reliable ML for health?
The best way to reach me is via my Dartmouth email.