Dina Katabi

Papers

• Artificial Intelligence-Enabled Detection and Assessment of Parkinson's Disease using Nocturnal Breathing Signals
  2022 · Nature Medicine 2022

  This Nature Medicine study built an AI model that detects Parkinson's disease and tracks its progression from breathing signals recorded during sleep. Evaluated on 7,671 people from several US hospitals and public datasets, it detected the disease with AUC 0.90 on held-out data and 0.85 on external data, and its severity estimates matched the MDS-UPDRS rating scale (R = 0.94). Breathing can be captured without contact at home from radio waves reflected off the body.

  • Published: Nature Medicine, 2022
  • Cohort: 7,671 individuals
  • Signals: nocturnal breathing (incl. radio-wave sensing)
• Monitoring Gait at Home with Radio Waves in Parkinson's Disease: a Marker of Severity, Progression, and Medication Response
  2022 · Science Translational Medicine 2022

  This Science Translational Medicine study tracked gait speed at home with a radio device that senses radio waves reflected off people's bodies. Fifty people with and without Parkinson's disease were monitored for up to a year, giving more than 200,000 gait speed measurements. Home gait speed correlated strongly with MDS-UPDRS scores, tracked progression more sensitively than the rating scale and captured responses to medication.

  • Published: Science Translational Medicine, 2022
  • Cohort: 50 participants, up to 1 year
  • Sensing: in-home radio waves (contactless)
• SimPer: Simple Self-Supervised Learning of Periodic Targets
  2022 · arXiv preprint

  SimPer is a contrastive self-supervised method for learning periodic signals. It uses custom augmentations, similarity measures and a generalized contrastive loss, and beat other self-supervised methods on real-world tasks in behaviour analysis, environmental sensing and healthcare, with better data efficiency and robustness.

  • Published: arXiv preprint, 2022
  • Method: contrastive SSL with periodicity-aware augmentations and loss
  • Domains: human behaviour, environmental sensing, healthcare
• Delving into Deep Imbalanced Regression
  2021 · arXiv preprint

  This paper addresses regression problems where some target values have far fewer examples than others. The authors propose smoothing both the label and feature distributions so that nearby target values inform each other, which calibrates learned features for continuous labels.

  • Published: arXiv preprint, 2021
  • Problem: imbalanced regression (continuous targets)
  • Method: label distribution smoothing + feature distribution smoothing

Co-authors