{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T23:20:35Z","timestamp":1789514435509,"version":"build-2803163510"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T00:00:00Z","timestamp":1715212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB029699"],"award-info":[{"award-number":["R01EB029699"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R21EB027344"],"award-info":[{"award-number":["R21EB027344"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01NS120924"],"award-info":[{"award-number":["R01NS120924"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:p>Acuity assessments are vital for timely interventions and fair resource allocation in critical care settings. Conventional acuity scoring systems heavily depend on subjective patient assessments, leaving room for implicit bias and errors. These assessments are often manual, time-consuming, intermittent, and challenging to interpret accurately, especially for healthcare providers. This risk of bias and error is likely most pronounced in time-constrained and high-stakes environments, such as critical care settings. Furthermore, such scores do not incorporate other information, such as patients\u2019 mobility level, which can indicate recovery or deterioration in the intensive care unit (ICU), especially at a granular level. We hypothesized that wearable sensor data could assist in assessing patient acuity granularly, especially in conjunction with clinical data from electronic health records (EHR). In this prospective study, we evaluated the impact of integrating mobility data collected from wrist-worn accelerometers with clinical data obtained from EHR for estimating acuity. Accelerometry data were collected from 87 patients wearing accelerometers on their wrists in an academic hospital setting. The data was evaluated using five deep neural network models: VGG, ResNet, MobileNet, SqueezeNet, and a custom Transformer network. These models outperformed a rule-based clinical score (Sequential Organ Failure Assessment, SOFA) used as a baseline when predicting acuity state (for ground truth we labeled as unstable patients if they needed life-supporting therapies, and as stable otherwise), particularly regarding the precision, sensitivity, and F1 score. The results demonstrate that integrating accelerometer data with demographics and clinical variables improves predictive performance compared to traditional scoring systems in healthcare. Deep learning models consistently outperformed the SOFA score baseline across various scenarios, showing notable enhancements in metrics such as the area under the receiver operating characteristic (ROC) Curve (AUC), precision, sensitivity, specificity, and F1 score. The most comprehensive scenario, leveraging accelerometer, demographics, and clinical data, achieved the highest AUC of 0.73, compared to 0.53 when using SOFA score as the baseline, with significant improvements in precision (0.80 vs. 0.23), specificity (0.79 vs. 0.73), and F1 score (0.77 vs. 0.66). This study demonstrates a novel approach beyond the simplistic differentiation between stable and unstable conditions. By incorporating mobility and comprehensive patient information, we distinguish between these states in critically ill patients and capture essential nuances in physiology and functional status. Unlike rudimentary definitions, such as equating low blood pressure with instability, our methodology delves deeper, offering a more holistic understanding and potentially valuable insights for acuity assessment.<\/jats:p>","DOI":"10.3389\/fneur.2024.1386728","type":"journal-article","created":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T11:41:00Z","timestamp":1715254860000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Wearable sensors in patient acuity assessment in critical care"],"prefix":"10.3389","volume":"15","author":[{"given":"Jessica","family":"Sena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Tahsin","family":"Mostafiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea E.","family":"Davidson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabyasachi","family":"Bandyopadhyay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhash","family":"Nerella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tezcan","family":"Ozrazgat-Baslanti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Shickel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tyler","family":"Loftus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William Robson","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azra","family":"Bihorac","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parisa","family":"Rashidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"640685","DOI":"10.3389\/fdgth.2021.640685","article-title":"Deep multi-modal transfer learning for augmented patient acuity assessment in the intelligent ICU","volume":"3","author":"Shickel","year":"2021","journal-title":"Front Digit Health"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1879","DOI":"10.1038\/s41598-019-38491-0","article-title":"DeepSOFA: a continuous acuity score for critically ill patients using clinically interpretable deep learning","volume":"9","author":"Shickel","year":"2019","journal-title":"Sci Rep"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1097\/MLR.0b013e3181468ca3","article-title":"The association of registered nurse staffing levels and patient outcomes: systematic review and meta-analysis","volume":"45","author":"Kane","year":"2007","journal-title":"Med Care"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"6252","DOI":"10.48550\/arXiv.2303.06252","article-title":"AI-enhanced intensive care unit: revolutionizing patient care with pervasive sensing","volume":"10","author":"Nerella","year":"2023","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.apnr.2009.12.004","article-title":"Nursing staffing, nursing workload, the work environment and patient outcomes","volume":"24","author":"Duffield","year":"2011","journal-title":"Appl Nurs Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1097\/00003246-198108000-00008","article-title":"APACHE\u2014acute physiology and chronic health evaluation: a physiologically based classification system","volume":"9","author":"Knaus","year":"1981","journal-title":"Crit Care Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1097\/00003246-198411000-00012","article-title":"A simplified acute physiology score for ICU patients","volume":"12","author":"Gall","year":"1984","journal-title":"Crit Care Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (Sepsis-related organ failure assessment) score to describe organ dysfunction\/failure: On behalf of the working group on Sepsis-related problems of the European Society of Intensive Care Medicine","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1308\/003588406X130615","article-title":"The value of modified early warning score (MEWS) in surgical in-patients: a prospective observational study","volume":"88","author":"Gardner-Thorpe","year":"2006","journal-title":"Ann R Coll Surg Engl"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"38","DOI":"10.15265\/IY-2015-014","article-title":"Health informatics via machine learning for the clinical Management of Patients","volume":"10","author":"Clifton","year":"2015","journal-title":"Yearb Med Inform"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"103364","DOI":"10.1016\/j.jbi.2019.103364","article-title":"Unsupervised machine learning for the discovery of latent disease clusters and patient subgroups using electronic health records","volume":"102","author":"Wang","year":"2020","journal-title":"J Biomed Inform"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"7924","DOI":"10.1038\/s41598-022-11997-w","article-title":"Automated machine learning for differentiation of hepatocellular carcinoma from intrahepatic cholangiocarcinoma on multiphasic MRI","volume":"12","author":"Hu","year":"2022","journal-title":"Sci Rep"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"26094","DOI":"10.1038\/srep26094","article-title":"Deep patient: an unsupervised representation to predict the future of patients from the electronic health records","volume":"6","author":"Miotto","year":"2016","journal-title":"Sci Rep"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.48550\/arXiv.2202.01427","article-title":"SparGE: Sparse coding-based patient similarity learning via low-rank constraints and graph embedding","volume":"3","author":"Wei","year":"2022","journal-title":"arXiv"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"8020","DOI":"10.1038\/s41598-019-44004-w","article-title":"Intelligent ICU for autonomous patient monitoring using pervasive sensing and deep learning","volume":"9","author":"Davoudi","year":"2019","journal-title":"Sci Rep"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1109\/BIBM58861.2023.10385764","article-title":"Diurnal pain classification in critically ill patients using machine learning on Accelerometry and analgesic data","author":"Sena","year":"2023","journal-title":"IEEE Int Conf Bioinform Biomed Workshops"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5163","DOI":"10.48550\/arXiv.2005.05163","article-title":"Development of computable phenotype to identify and characterize transitions in acuity status in intensive care unit","author":"Ren","year":"2020","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"ArXiv"},{"key":"ref19","author":"He","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"4861","DOI":"10.48550\/arXiv.1704.04861","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"7360","DOI":"10.48550\/arXiv.1602.07360","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size","author":"Iandola","year":"2016","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"6000","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.3390\/s22051911","article-title":"Wearable sensor-based human activity recognition with transformer model","volume":"22","author":"Dirgov\u00e1 Lupt\u00e1kov\u00e1","year":"2022","journal-title":"Sensors"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"100078","DOI":"10.1016\/j.neuri.2022.100078","article-title":"Deep CNN hyperparameter optimization algorithms for sensor-based human activity recognition","volume":"2","author":"Raziani","year":"2022","journal-title":"Neurosci Inform"},{"key":"ref25","author":"Jordao","year":""},{"key":"ref26","doi-asserted-by":"publisher","first-page":"13029","DOI":"10.1109\/JSEN.2021.3069927","article-title":"Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review","volume":"21","author":"Ramanujam","year":"2021","journal-title":"IEEE Sensors J"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"67","DOI":"10.48550\/arXiv.2307.00067","article-title":"Transformers in healthcare: a survey","volume":"30","author":"Nerella","year":"2023","journal-title":"arXiv"},{"key":"ref28","year":""},{"key":"ref29","year":""},{"key":"ref30","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1097\/00006199-198707000-00002","article-title":"The Braden scale for predicting pressure sore risk","volume":"36","author":"Bergstrom","year":"1987","journal-title":"Nurs Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.05504","article-title":"Computable phenotypes to characterize changing patient brain dysfunction in the intensive care unit","author":"Yuanfang","year":"2023","journal-title":"ArXiv"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"10902","DOI":"10.48550\/arXiv.1907.10902","article-title":"Optuna: A next-generation Hyperparameter optimization framework","volume":"25","author":"Akiba","year":"2019","journal-title":"arXiv"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"d2304","DOI":"10.1136\/bmj.d2304","article-title":"How to obtain the P value from a confidence interval","volume":"343","author":"Altman","year":"2011","journal-title":"BMJ"},{"key":"ref35","article-title":"A unified approach to interpreting model predictions","volume":"24","author":"Lundberg","year":"2017","journal-title":"arXiv"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1386728\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T11:41:10Z","timestamp":1715254870000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1386728\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,9]]},"references-count":35,"alternative-id":["10.3389\/fneur.2024.1386728"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2024.1386728","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,9]]},"article-number":"1386728"}}