More Like this

1. Obstructive Sleep Apnea (OSA) Events Classification by Effective Radar Cross Section (ERCS) Method Using Microwave Doppler Radar and Machine Learning Classifier

   https://doi.org/10.1109/IMBIoC47321.2020.9385028  

   Snigdha, Farjana; Islam, Shekh M; Boric-Lubecke, Olga; Lubecke, Victor (December 2020, 2020 IEEE MTT-S International Microwave Biomedical Conference (IMBioC))

   null (Ed.)

   In-home sleep monitoring system using Microwave Doppler radar is gaining attention as it is unobtrusive and noncontact form of measurement. Most of the reported results in literature focused on utilizing radar-reflected signal amplitude to recognize Obstructive sleep apnea (OSA) events which requires iterative analysis and cannot recommend about sleep positions also (supine, prone and side). In this paper, we propose a new, robust and automated ERCS-based (Effective Radar Cross section) method for classifying OSA events (normal, apnea and hypopnea) by integrating radar system in a clinical setup. In our prior attempt, ERCS has been proven versatile method to recognize different sleep postures. We also employed two different machine learning classifiers (K-nearest neighbor (KNN) and Support Vector machine (SVM) to recognize OSA events from radar captured ERCS and breathing rate measurement from five different patients' clinical study. SVM with quadratic kernel outperformed with other classifiers with an accuracy of 96.7 % for recognizing different OSA events. The proposed system has several potential applications in healthcare, continuous monitoring and security/surveillance applications. 

   more » « less
2. Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals

   https://doi.org/10.1038/s41591-022-01932-x  

   Yang, Yuzhe; Yuan, Yuan; Zhang, Guo; Wang, Hao; Chen, Ying-Cong; Liu, Yingcheng; Tarolli, Christopher G.; Crepeau, Daniel; Bukartyk, Jan; Junna, Mithri R.; et al (October 2022, Nature Medicine)

   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, P  = 3.6 × 10 –25 ). 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. 

   more » « less
3. Artificial intelligence-enabled detection and assessment of Parkinson’s disease

   Yuzhe Yang, Yuan Yuan (July 2022, Nature medicine)

   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, P = 3.6 × 10–25). 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. 

   more » « less
4. Multi-granularity Supervised Contrastive Learning with Online Adaptation for Contactless In-bed Posture Classification

   https://doi.org/10.1145/3729464  

   Song, Yingjian; Xiang, Haotian; Zeng, Zixuan; Chen, Jiayu; Zhang, Yida; Pitafi, Zaid Farooq; Yang, He; Lu, Qin; Zhang, Xiang; Phillips, Bradley G; et al (June 2025, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies)

   In-bed postures offer valuable information about an individual's sleep quality and overall health conditions, particularly for patients with sleep apnea. However, current in-bed posture classification systems lack privacy-friendly and easy-to-install options. Furthermore, existing solutions do not consider variations between patients and are typically trained only once, neglecting the utilization of time consistency and unlabeled data from new patients. To address these limitations, this paper builds on a seismic sensor to introduce a novel sleep posture framework, which comprises two main components, namely, the Multi-Granularity Supervised Contrastive Learning (MGSCL) module and the ensemble Online Adaptation (oa) module. Unlike most existing contrastive learning frameworks that operate at the sample level, MGSCL leverages multi-granular information, operating not only at the sample level but also at the group level. The oa module enables the model to adapt to new patient data while ensuring time consistency in sleep posture predictions. Additionally, it quantifies model uncertainty to generate weighted predictions, further enhancing performance. Evaluated on a dataset of 100 patients collected at a clinical research center, MGSCLoa achieved an average accuracy of 91.67% and an average F1 score of 91.53% with only 40 seconds of labeled data per posture. In a Phase 2 evaluation with 11 participants over 13 nights in home settings, the framework reached an average accuracy of 85.37% and a weighted F1 score of 83.59% using just 3 minutes of labeled data per common posture for each participant. These results underscore the potential of seismic sensor-based in-bed posture classification for assessing sleep quality and related health conditions. 

   more » « less
5. Identity Authentication of OSA Patients Using Microwave Doppler radar and Machine Learning Classifiers

   https://doi.org/10.1109/RWS45077.2020.9049983  

   Islam, Shekh M; Rahman, Ashikur; Yavari, Ehsan; Baboli, Meheran; Boric-Lubecke, Olga; Lubecke, Victor M. (January 2020, 2020 IEEE Radio and Wireless Symposium (RWS))

   null (Ed.)

   Non-contact home-based sleep monitoring will bring a paradigm shift to diagnosis and treatment of Obstructive Sleep Apnea (OSA) as it can facilitate easier access to specialized care in order to reach a much boarder set of patients. However, current remote unattended sleep studies are mostly contact sensor based and test results are sometimes falsified by sleep-critical job holders (driver, airline pilots) due to fear of potential job loss. In this work, we investigated identity authentication of patients with OSA symptoms based on extracting respiratory features (peak power spectral density, packing density and linear envelop error) from radar captured paradoxical breathing patterns in a small-scale clinical sleep study integrating three different machine learning classifiers (Support Vector Machine (SVM), K-nearest neighbor (KNN), Random forest). The proposed OSA-based authentication method was tested and validated for five OSA patients with 93.75% accuracy using KNN classifier which outperformed other classifiers. 

   more » « less