{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:03:58Z","timestamp":1784397838298,"version":"3.55.0"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Oxford Biomedical Research Centre"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Study objectives<\/jats:title>\n                    <jats:p>To develop and evaluate artificial intelligence methods for detecting upper-body joint positions from video recordings of individuals during sleep, providing a foundation for future automated, video-based analysis of sleep movements that extends beyond conventional sensor-based methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed HypnoPose and tested five different model configurations. We pretrained each variant on a public body pose dataset and evaluated on a sleep pose dataset comprising 4419 annotated frames from 198 video segments depicting movement across 74 participants (10 RBD, 4 PD, 9 healthy controls, 51 referred for vPSG screening) recorded in clinical and home settings. We manually annotated each frame with 13 body joints, visibility flags, and head orientation. We evaluated model performance against state-of-the-art pose estimators using precision (mAP) and recall (mAR) metrics based on Object Keypoint Similarity (OKS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>HypnoPose achieved the highest performance (mAP: 0.088, AP@0.5: 0.326) in the sleep domain, doubling baseline HigherHRNet results (mAP: 0.041, AP@0.5: 0.165) and outperforming gold-standard architectures. It showed 40%\u2013120% relative mAP improvement for occluded joints, enhancing detection of the head, shoulders, and elbows. Home recordings showed higher precision than clinic data (mAP 0.14 vs 0.07). Within clinic recordings, NREM stages outperform Wake (mAP 0.11\u20130.13 vs 0.06).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We present a proof-of-concept for detecting upper-body joint positions from sleep images, even when blankets occlude the person. Our method improves relative precision by 115% compared to standard models. While absolute performance remains modest, this work establishes a first step toward clinically applicable, video-based pose estimation during sleep. Future work should integrate contextual priors and expand annotated sleep datasets.<\/jats:p>\n                    <jats:p>Statement of Significance Video polysomnography (vPSG) is the gold standard for assessing sleep-related disorders. It is resource-intensive, requires specialist expertise for setup and interpretation, and may not capture typical sleep due to the presence of multiple sensors and the laboratory environment. In some populations, such as individuals with REM sleep behavior disorder (RBD), vPSG can be challenging, and clinically relevant behaviors may not occur during a single recording night. At-home recordings provide greater environmental validity but are often constrained by nonstandard camera positioning and suboptimal lighting. This study introduces a benchmark for automated, frame-wise upper-body pose estimation, to identify anatomical joint positions during sleep. While tools for detecting periodic limb movements and REM sleep without atonia already exist, there remains a critical need for objective, scalable methods to quantify complex movements seen in disorders such as RBD, NREM parasomnias, and sleep-related epilepsies. This work lays the foundation for future automated, noncontact movement analysis that complements existing vPSG workflows, reduces manual review time, and supports accessible monitoring of sleep behavior in both clinical and home environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/sleep\/zsag108","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T12:51:34Z","timestamp":1776430294000},"source":"Crossref","is-referenced-by-count":0,"title":["Towards automated joint detection in sleep studies: bridging clinical insight and artificial intelligence"],"prefix":"10.1093","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4865-6661","authenticated-orcid":false,"given":"Alexis","family":"Dorier","sequence":"first","affiliation":[{"name":"Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford , Oxford,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9941-6721","authenticated-orcid":false,"given":"Pietro-Luca","family":"Ratti","sequence":"additional","affiliation":[{"name":"Oxford Sleep Centre, Department of Clinical Neurophysiology, Oxford University Hospitals NHS Foundation Trust , Oxford ,","place":["United Kingdom"]},{"name":"Oxford Parkinson\u2019s Disease Centre, Nuffield Department of Clinical Neurosciences, University of Oxford , Oxford,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9903-5083","authenticated-orcid":false,"given":"Mkael","family":"Symmonds","sequence":"additional","affiliation":[{"name":"Oxford Sleep Centre, Department of Clinical Neurophysiology, Oxford University Hospitals NHS Foundation Trust , Oxford ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2397-3652","authenticated-orcid":false,"given":"Timothy","family":"Quinnell","sequence":"additional","affiliation":[{"name":"Respiratory Support and Sleep Centre , Royal Papworth Hospital, Cambridge ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary","family":"Dennis","sequence":"additional","affiliation":[{"name":"Department of Neurology, Sheffield Teaching Hospitals , Sheffield ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-3881","authenticated-orcid":false,"given":"Christine","family":"Lo","sequence":"additional","affiliation":[{"name":"Oxford Sleep Centre, Department of Clinical Neurophysiology, Oxford University Hospitals NHS Foundation Trust , Oxford ,","place":["United Kingdom"]},{"name":"Department of Neurology, Sheffield Teaching Hospitals , Sheffield ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6382-5841","authenticated-orcid":false,"given":"Michele T","family":"Hu","sequence":"additional","affiliation":[{"name":"Oxford Parkinson\u2019s Disease Centre, Nuffield Department of Clinical Neurosciences, University of Oxford , Oxford,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4787-6053","authenticated-orcid":false,"given":"Mauricio","family":"Villarroel","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford , Oxford,","place":["United Kingdom"]},{"name":"The Podium Institute for Sports Medicine and Technology, University of Oxford , Oxford,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"issue":"3","key":"2026071813291686000_ref1","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsab257","article-title":"Video-polysomnography procedures for diagnosis of rapid eye movement sleep behavior disorder (RBD) and the identification of its prodromal stages: guidelines from the International RBD Study Group","volume":"45","author":"Cesari","year":"2022","journal-title":"Sleep"},{"issue":"1","key":"2026071813291686000_ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-018-0016-5","article-title":"REM sleep behaviour disorder","volume":"4","author":"Dauvilliers","year":"2018","journal-title":"Nat Rev Dis Primers"},{"issue":"6","key":"2026071813291686000_ref3","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1002\/mds.24957","article-title":"REM sleep behavior disorder: motor manifestations and pathophysiology","volume":"27","author":"Arnulf","year":"2012","journal-title":"Mov Disord"},{"issue":"5","key":"2026071813291686000_ref4","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1093\/sleep\/31.5.724","article-title":"Quantification of electromyographic activity during REM sleep in multiple muscles in REM sleep behavior disorder","volume":"31","author":"Frauscher","year":"2008","journal-title":"Sleep"},{"issue":"2","key":"2026071813291686000_ref5","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1002\/ana.26517","article-title":"Actigraphy enables home screening of rapid eye movement behavior disorder in Parkinson\u2019s disease","volume":"93","author":"Raschell\u00e0","year":"2023","journal-title":"Ann Neurol"},{"key":"2026071813291686000_ref6","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/B978-0-444-64032-1.00025-4","volume-title":"Handbook of Clinical Neurology","author":"Rundo","year":"2019"},{"key":"2026071813291686000_ref7","doi-asserted-by":"publisher","first-page":"101608","DOI":"10.1016\/j.smrv.2022.101608","article-title":"Economic evaluation of diagnostic sleep studies for obstructive sleep apnoea in the adult population: a systematic review","volume":"62","author":"Natsky","year":"2022","journal-title":"Sleep Med Rev"},{"key":"2026071813291686000_ref8","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.sleep.2023.07.012","article-title":"Partial endorsement of: \u201cvideo-polysomnography procedures for diagnosis of rapid eye movement sleep behavior disorder (RBD) and the identification of its prodromal stages: guidelines from the international RBD study group\u201d by the World Sleep Society","volume":"110","author":"Schenck","year":"2023","journal-title":"Sleep Med"},{"issue":"2","key":"2026071813291686000_ref9","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1007\/s40675-024-00301-z","article-title":"A systematic review on the technical feasibility of home-polysomnography for diagnosis of sleep disorders in adults","volume":"10","author":"Braun","year":"2024","journal-title":"Curr Sleep Med Rep"},{"issue":"7","key":"2026071813291686000_ref10","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.3390\/electronics14071307","article-title":"An in-depth analysis of 2D and 3D pose estimation techniques in deep learning: methodologies and advances","volume":"14","author":"Sun","year":"2025","journal-title":"Electronics (Basel)"},{"key":"2026071813291686000_ref11","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1109\/AINIT61980.2024.10581583","volume-title":"2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024","author":"Zhang","year":"2024"},{"issue":"6","key":"2026071813291686000_ref12","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13061046","article-title":"YOLOv8-PoseBoost: advancements in multimodal robot pose Keypoint detection","volume":"13","author":"Wang","year":"2024","journal-title":"Electronics (Switzerland)"},{"issue":"9","key":"2026071813291686000_ref13","doi-asserted-by":"publisher","DOI":"10.3390\/machines11090891","article-title":"Enhancing 6-DoF object pose estimation through multiple modality fusion: a hybrid CNN architecture with cross-layer and cross-modal integration","volume":"11","author":"Wang","year":"2023","journal-title":"Machines"},{"key":"2026071813291686000_ref14","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1109\/ICIBA62489.2024.10868084","volume-title":"Proceedings of 2024 IEEE 4th International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2024","author":"Lin","year":"2024"},{"key":"2026071813291686000_ref15","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.neunet.2023.01.036","article-title":"BalanceHRNet: an effective network for bottom-up human pose estimation","volume":"161","author":"Li","year":"2023","journal-title":"Neural Netw"},{"key":"2026071813291686000_ref16","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1109\/SPIC62469.2024.10691419","volume-title":"Proceedings of 2024 2nd International Conference on Signal Processing and Intelligent Computing, SPIC 2024","author":"Qi","year":"2024"},{"issue":"6","key":"2026071813291686000_ref17","doi-asserted-by":"publisher","first-page":"7157","DOI":"10.1109\/TPAMI.2022.3222784","article-title":"AlphaPose: whole-body regional multi-person pose estimation and tracking in real-time","volume":"45","author":"Fang","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026071813291686000_ref18","author":""},{"key":"2026071813291686000_ref19"},{"issue":"3","key":"2026071813291686000_ref20","doi-asserted-by":"publisher","DOI":"10.3390\/life15030358","article-title":"Automatic detect incorrect lifting posture with the pose estimation model","volume":"15","author":"Hsu","year":"2025","journal-title":"Life (Basel)"},{"key":"2026071813291686000_ref21","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1109\/BioRob60516.2024.10719777","volume-title":"2024 10th IEEE RAS\/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob)","author":"Santos","year":"2024"},{"key":"2026071813291686000_ref22","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1177\/11779322241231108","article-title":"Human pose estimation for clinical analysis of gait pathologies","volume":"18","author":"Ali","year":"2024","journal-title":"Bioinform Biol Insights"},{"issue":"15","key":"2026071813291686000_ref23","doi-asserted-by":"publisher","first-page":"6839","DOI":"10.3390\/s23156839","article-title":"Enhancing cricket performance analysis with human pose estimation and machine learning","volume":"23","author":"Siddiqui","year":"2023","journal-title":"Sensors"},{"key":"2026071813291686000_ref24","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.aej.2024.10.079","article-title":"IoT-based 3D pose estimation and motion optimization for athletes: application of C3D and OpenPose","volume":"115","author":"Ren","year":"2025","journal-title":"Alex Eng J"},{"issue":"21","key":"2026071813291686000_ref25","doi-asserted-by":"publisher","first-page":"e39977","DOI":"10.1016\/j.heliyon.2024.e39977","article-title":"A comprehensive analysis of the machine learning pose estimation models used in human movement and posture analyses: a narrative review","volume":"10","author":"Roggio","year":"2024","journal-title":"Heliyon"},{"key":"2026071813291686000_ref26","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.cag.2023.09.008","article-title":"Human pose estimation and action recognition for fitness movements","volume":"116","author":"Fu","year":"2023","journal-title":"Comput Graph"},{"key":"2026071813291686000_ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/2301395","article-title":"Pose estimation-assisted dance tracking system based on convolutional neural network","volume":"2022","author":"Mu","year":"2022","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"2026071813291686000_ref28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3603618","article-title":"Deep learning-based human pose estimation: a survey","volume":"56","author":"Zheng","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2026071813291686000_ref29"},{"key":"2026071813291686000_ref30"},{"key":"2026071813291686000_ref31"},{"issue":"5","key":"2026071813291686000_ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s22052014","article-title":"A vision-based system for in-sleep upper-body and head pose classification","volume":"22","author":"Li","year":"2022","journal-title":"Sensors"},{"key":"2026071813291686000_ref33","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC40787.2023.10340050","volume-title":"Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS","author":"Zhu","year":"2023"},{"key":"2026071813291686000_ref34","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/TNSRE.2020.3048121","article-title":"Transfer learning for clinical sleep pose detection using a single 2D IR camera","volume":"29","author":"Mohammadi","year":"2021","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"2","key":"2026071813291686000_ref35","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1109\/JBHI.2024.3432195","article-title":"SaccpaNet: a Separable Atrous Convolution-based Cascade Pyramid Attention Network to estimate body landmarks using cross-modal knowledge transfer for under-blanket sleep posture classification","volume":"30","author":"Tam","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026071813291686000_ref36","doi-asserted-by":"publisher","first-page":"170579","DOI":"10.1109\/ACCESS.2020.3024122","article-title":"Joint apnea and body position analysis for home sleep studies using a wireless audio and motion sensor","volume":"8","author":"M\u0142y\u0144czak","year":"2020","journal-title":"IEEE Access"},{"key":"2026071813291686000_ref37","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.sleep.2021.02.020","article-title":"Total durations of respiratory events are modulated within REM and NREM sleep by sleeping position and obesity in OSA patients","volume":"81","author":"Rissanen","year":"2021","journal-title":"Sleep Med"},{"issue":"3","key":"2026071813291686000_ref38","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/S1087-0792(98)90018-1","article-title":"The effect of body posture on sleep-related breathing disorders: facts and therapeutic implications","volume":"2","author":"Oksenberg","year":"1998","journal-title":"Sleep Med Rev"},{"issue":"5","key":"2026071813291686000_ref39","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1093\/brain\/awh481","article-title":"Adult chronic sleepwalking and its treatment based on polysomnography","volume":"128","author":"Guilleminault","year":"2005","journal-title":"Brain"},{"issue":"5","key":"2026071813291686000_ref40","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1002\/ana.27170","article-title":"Automated detection of isolated REM sleep behavior disorder using computer vision","volume":"97","author":"Abdelfattah","year":"2025","journal-title":"Ann Neurol"},{"key":"2026071813291686000_ref41"},{"issue":"1-3","key":"2026071813291686000_ref42","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: a database and web-based tool for image annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int J Comput Vis"},{"key":"2026071813291686000_ref43"},{"key":"2026071813291686000_ref44"},{"issue":"1","key":"2026071813291686000_ref45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3643512","article-title":"TagSleep3D","volume":"8","author":"Liu","year":"2024","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"}],"container-title":["SLEEP"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/sleep\/advance-article-pdf\/doi\/10.1093\/sleep\/zsag108\/68115158\/zsag108.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/sleep\/article-pdf\/49\/7\/zsag108\/68115158\/zsag108.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/sleep\/article-pdf\/49\/7\/zsag108\/68115158\/zsag108.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:29:27Z","timestamp":1784395767000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/sleep\/article\/doi\/10.1093\/sleep\/zsag108\/8659223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":45,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4,20]]},"published-print":{"date-parts":[[2026,7,13]]}},"URL":"https:\/\/doi.org\/10.1093\/sleep\/zsag108","relation":{},"ISSN":["0161-8105","1550-9109"],"issn-type":[{"value":"0161-8105","type":"print"},{"value":"1550-9109","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,4,20]]},"article-number":"zsag108"}}