Abstract

---

There are currently no effective biomarkers for diagnosing Parkinson’s disease (PD) or tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD and track its progression from nocturnal breathing signals. The model was evaluated on a large dataset comprising 7,671 individuals, using data from several hospitals in the United States, as well as multiple public datasets. The AI model can detect PD with an area-under-the-curve of 0.90 and 0.85 on held-out and external test sets, respectively. The AI model can also estimate PD severity and progression in accordance with the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (R= 0.94). The AI model uses an attention layer that allows for interpreting its predictions with respect to sleep and electroencephalogram. Moreover, the model can assess PD in the home setting in a touchless manner, by extracting breathing from radio waves that bounce off a person’s body during sleep. Our study demonstrates the feasibility of objective, noninvasive, at-home assessment of PD, and also provides initial evidence that this AI model may be useful for risk assessment before clinical diagnosis.

Paper

---

Talks

---

Core AI/ML Techniques & Breakthroughs

---

Press

---

• MIT News: Artificial intelligence model can detect Parkinson’s from breathing patterns
• CSAIL News: Artificial intelligence model can detect Parkinson’s from breathing patterns
• Forbes: See How This AI Analyzes Breathing Patterns For Early Detection Of Parkinson’s
• NVIDIA Technical Blog: AI Remotely Detects Parkinson’s Disease During Sleep
• The Washington Post: A new algorithm could spot Parkinson’s early. Will it help?
• Medscape News: AI Uses Nocturnal Breathing Patterns to Detect Parkinson's Disease
• Stat News: In early research, an AI model detects signs of Parkinson’s using breathing patterns
• New Atlas: AI detects Parkinson’s disease by tracking your breathing patterns
• University of Rochester: At-Home Sensors Can Spot Parkinson’s Disease
• Boston Globe: MIT device senses breathing patterns to spot Parkinson’s disease
• Yahoo: This Bot Detects Parkinson’s by Listening to You Breathe
• Futurity: Sensor Detects Parkinson’s During Sleep
• AzoRobotics: AI Assessment of Breathing Pattern Aids in Parkinson’s Diagnosis
• BioSpace: Newly Developed AI could Lead to Effective Biomarker for Parkinson's
• Parkinson's News Today: Device May Help Diagnose Parkinson’s From Breathing Patterns
• and other media outlets.

Citation

---

@article{yang2022artificial,
  title={Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals},
  author={Yang, Yuzhe and Yuan, Yuan and Zhang, Guo and Wang, Hao and Chen, Ying-Cong and Liu, Yingcheng and Tarolli, Christopher G and Crepeau, Daniel and Bukartyk, Jan and Junna, Mithri R and others},
  journal={Nature Medicine},
  volume={28},
  number={10},
  pages={2207-2215},
  year={2022},
  publisher={Nature Publishing Group}
}

Related Works

---

Monitoring Gait at Home with Radio Waves in Parkinson's Disease: a Marker of Severity, Progression, and Medication Response
Yingcheng Liu*, Guo Zhang*, Christopher Tarolli, Rumen Hristov, Stella Jensen-Roberts, Emma Waddell, Taylor Myers, Meghan Pawlik, Julia Soto, Renee Wilson, Yuzhe Yang, Timothy Nordahl, Karlo Lizarraga, Jamie Adams, Ruth Schneider, Karl Kieburtz, Terry Ellis, Ray Dorsey, Dina Katabi
Science Translational Medicine (2022)
[Project Page]  •  [Paper]  •  [Code]  •  [MIT News]  •  [Video]

Contactless In-Home Monitoring of the Long-Term Respiratory and Behavioral Phenotypes in Older Adults With COVID-19: A Case Series
Guo Zhang*, Ipsit Vahia*, Yingcheng Liu*, Yuzhe Yang, Rose May, Hailey V. Cray, William McGrory, Dina Katabi
Frontiers in Psychiatry (2021)
[Paper]  •  [MIT CSAIL News]  •  [Video]

---