Wrist-worn accelerometers can detect sleep onset and wake. Various algorithms classify sleep-wake using wrist acceleration data. Deep learning techniques show promise in accurately classifying sleep stages using accelerometer data. Algorithms utilize features to improve sleep detection and staging. Performance has been compared to polysomnography. Deep learning algorithms outperform other algorithms in sleep-wake classification. Overall, wrist-worn accelerometers with deep learning provide a promising approach for accurately detecting sleep onset and wake.
\n1. \"Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality\"
\n2. \"Evaluating state-of-the-art algorithms for sleep-wake classification using wrist-worn wearable devices\"
\n3. \"Deep Learning-based Sleep Detection using Torso Patch Vital Signs Improves Sleep-Wake Detection over Wrist Actigraphy\"
\n4. \"Validation of an automated sleep detection algorithm using data from multiple accelerometer brands\"
\n5. \"Sleep Measurement Using Wrist-Worn Accelerometer Data Compared with Polysomnography\"
\nWrist-worn accelerometers can detect sleep onset and wake. Various algorithms classify sleep-wake using wrist acceleration data. Deep learning techniques show promise in accurately classifying sleep stages using accelerometer data. Algorithms utilize features to improve sleep detection and staging. Performance has been compared to polysomnography. Deep learning algorithms outperform other algorithms in sleep-wake classification. Overall, wrist-worn accelerometers with deep learning provide a promising approach for accurately detecting sleep onset and wake.
\n1. \"Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality\"
\n2. \"Evaluating state-of-the-art algorithms for sleep-wake classification using wrist-worn wearable devices\"
\n3. \"Deep Learning-based Sleep Detection using Torso Patch Vital Signs Improves Sleep-Wake Detection over Wrist Actigraphy\"
\n4. \"Validation of an automated sleep detection algorithm using data from multiple accelerometer brands\"
\n5. \"Sleep Measurement Using Wrist-Worn Accelerometer Data Compared with Polysomnography\"
\nNice, thanks!
", "rawMarkdown": "Nice, thanks!", "votes": null } ], "comments": [ { "id": 2571717, "author_name": "arifhossain00", "author_url": "", "post_date": "12/23/2023 13:54:21", "content": "Nice, thanks!
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2426514": "# ***Literature Review*** on detecting sleep from **wrist-worn accelerometer** data\n\nWrist-worn accelerometers can detect sleep onset and wake. Various algorithms classify sleep-wake using wrist acceleration data. Deep learning techniques show promise in accurately classifying sleep stages using accelerometer data. Algorithms utilize features to improve sleep detection and staging. Performance has been compared to polysomnography. Deep learning algorithms outperform other algorithms in sleep-wake classification. Overall, wrist-worn accelerometers with deep learning provide a promising approach for accurately detecting sleep onset and wake.\n\n---\n\n**1. \"Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality\"**\n\n- **Title:** Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality\n- **Contributions:** \n - Developed and validated a self-supervised deep neural network for sleep stage classification using accelerometer data\n - Studied the association between sleep duration and efficiency with mortality outcomes\n- **Insights:** The study developed a self-supervised deep neural network for sleep stage classification using wrist-worn accelerometers.\n- **Authors:** Han Yuan, Tatiana Plekhanova, Rosemary Walmsley, Amy C. Reynolds, Kathleen J. Maddison, Mariette Jela Bućan, Philip R. Gehrman, Alex V. Rowlands, David W. Ray, Derrick Bennett, Joanne A. McVeigh, Leon Straker, Peter R. Eastwood, Simon D. Kyle, Aiden R. Doherty\n- **PDF Link:** [Download PDF](https://www.medrxiv.org/content/medrxiv/early/2023/07/08/2023.07.07.23292251.full.pdf)\n- **Journal Name:** medRxiv\n\n---\n\n**2. \"Evaluating state-of-the-art algorithms for sleep-wake classification using wrist-worn wearable devices\"**\n\n- **Title:** Evaluating state-of-the-art algorithms for sleep-wake classification using wrist-worn wearable devices\n- **Contributions:** \n - Evaluation and comparison of sleep-wake prediction algorithms\n - Identification of the best performing algorithm (DACNN)\n- **Insights:** The study evaluated different algorithms for sleep-wake classification using wrist-worn accelerometer data, with the DACNN algorithm performing the best.\n- **Authors:** Matthew R. Patterson, Adonay A. S. Nunes, Dawid Gerstel, Rakesh Pilkar, Ali Neishabouri, Christine C. Guo\n- **PDF Link:** [Download PDF](https://academic.oup.com/sleep/article-pdf/46/Supplement_1/A421/50467947/zsad077.0955.pdf)\n- **Journal Name:** Sleep\n\n---\n\n**3. \"Deep Learning-based Sleep Detection using Torso Patch Vital Signs Improves Sleep-Wake Detection over Wrist Actigraphy\"**\n\n- **Title:** Deep Learning-based Sleep Detection using Torso Patch Vital Signs Improves Sleep-Wake Detection over Wrist Actigraphy\n- **Contributions:** \n - Deep learning algorithm improves sleep detection and staging.\n - Vital signs enhance determination of wake-sleep state.\n- **Insights:** The study found that using a deep learning algorithm with vital signs and movement data from a torso-wearable patch sensor improved sleep detection compared to wrist-worn accelerometer data.\n- **Authors:** Matt Pipke, J. Sekaric, Dylan Richards, Maged Gendy, Sabra M. Abbott, Kathryn J. Reid, Phyllis C. Zee\n- **PDF Link:** [Download PDF](https://academic.oup.com/sleep/article-pdf/46/Supplement_1/A122/50466557/zsad077.0275.pdf)\n- **Journal Name:** Sleep\n\n---\n\n**4. \"Validation of an automated sleep detection algorithm using data from multiple accelerometer brands\"**\n\n- **Title:** Validation of an automated sleep detection algorithm using data from multiple accelerometer brands\n- **Contributions:** \n - Validating an automated sleep detection algorithm\n - Comparing accelerometer data with polysomnography (PSG) data\n- **Insights:** The automated sleep detection algorithm applied to wrist-worn accelerometers provides comparable measures of sleep onset and waking time, but a poor measure of wake during the sleep period.\n- **Authors:** Tatiana Plekhanova, Alex V. Rowlands, Melanie J. Davies, Andrew P. Hall, Tom Yates, Charlotte L. Edwardson\n- **PDF Link:** [Download PDF](https://figshare.com/articles/journal_contribution/Validation_of_an_automated_sleep_detection_algorithm_using_data_from_multiple_accelerometer_brands/21930570/1/files/39528148.pdf)\n- **Journal Name:** Journal of Sleep Research\n\n---\n\n**5. \"Sleep Measurement Using Wrist-Worn Accelerometer Data Compared with Polysomnography\"**\n\n- **Title:** Sleep Measurement Using Wrist-Worn Accelerometer Data Compared with Polysomnography\n- **Contributions:** \n - Comparison of sleep measurement using wrist-worn accelerometer data with polysomnography\n - Evaluation of alternative sleep onset definitions and their impact on sleep estimates\n- **Insights:** Sleep onset and wake can be detected from wrist-worn accelerometer data with high sensitivity but low specificity.\n- **Authors:** John D. Chase, Michael A. Busa, John Staudenmayer, John R. Sirard\n- **PDF Link:** [Download PDF](https://www.mdpi.com/1424-8220/22/13/5041/pdf?version=1656935847)\n- **Journal Name:** Sensors", "2571717": "Nice, thanks!" }, "source": "meta" }