{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T22:50:12Z","timestamp":1771455012563,"version":"3.50.1"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2020,7,26]],"date-time":"2020-07-26T00:00:00Z","timestamp":1595721600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Hand hygiene is essential for preventing hospital-acquired infections but is difficult to accurately track. The gold-standard (human auditors) is insufficient for assessing true overall compliance. Computer vision technology has the ability to perform more accurate appraisals. Our primary objective was to evaluate if a computer vision algorithm could accurately observe hand hygiene dispenser use in images captured by depth sensors.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>Sixteen depth sensors were installed on one hospital unit. Images were collected continuously from March to August 2017. Utilizing a convolutional neural network, a machine learning algorithm was trained to detect hand hygiene dispenser use in the images. The algorithm\u2019s accuracy was then compared with simultaneous in-person observations of hand hygiene dispenser usage. Concordance rate between human observation and algorithm\u2019s assessment was calculated. Ground truth was established by blinded annotation of the entire image set. Sensitivity and specificity were calculated for both human and machine-level observation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>A concordance rate of 96.8% was observed between human and algorithm (kappa = 0.85). Concordance among the 3 independent auditors to establish ground truth was 95.4% (Fleiss\u2019s kappa = 0.87). Sensitivity and specificity of the machine learning algorithm were 92.1% and 98.3%, respectively. Human observations showed sensitivity and specificity of 85.2% and 99.4%, respectively.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>A computer vision algorithm was equivalent to human observation in detecting hand hygiene dispenser use. Computer vision monitoring has the potential to provide a more complete appraisal of hand hygiene activity in hospitals than the current gold-standard given its ability for continuous coverage of a unit in space and time.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaa115","type":"journal-article","created":{"date-parts":[[2020,5,21]],"date-time":"2020-05-21T11:08:13Z","timestamp":1590059293000},"page":"1316-1320","source":"Crossref","is-referenced-by-count":55,"title":["Automatic detection of hand hygiene using computer vision technology"],"prefix":"10.1093","volume":"27","author":[{"given":"Amit","family":"Singh","sequence":"first","affiliation":[{"name":"Department of Pediatrics, Stanford University School of Medicine, Stanford, California, USA"}]},{"given":"Albert","family":"Haque","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, California, USA"}]},{"given":"Alexandre","family":"Alahi","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}]},{"given":"Serena","family":"Yeung","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University, Stanford, California, USA"}]},{"given":"Michelle","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, California, USA"}]},{"given":"Jill R","family":"Glassman","sequence":"additional","affiliation":[{"name":"Clinical Excellence Research Center, Stanford University School of Medicine, Stanford, California, USA"}]},{"given":"William","family":"Beninati","sequence":"additional","affiliation":[{"name":"Intermountain TeleHealth Services, Murray, Utah, USA"}]},{"given":"Terry","family":"Platchek","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Stanford University School of Medicine, Stanford, California, USA"},{"name":"Clinical Excellence Research Center, Stanford University School of Medicine, Stanford, California, USA"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, California, USA"}]},{"given":"Arnold","family":"Milstein","sequence":"additional","affiliation":[{"name":"Clinical Excellence Research Center, Stanford University School of Medicine, Stanford, California, USA"}]}],"member":"286","published-online":{"date-parts":[[2020,7,26]]},"reference":[{"key":"2020110613095992600_ocaa115-B1","year":"2020"},{"key":"2020110613095992600_ocaa115-B2","volume-title":"WHO Guidelines on Hand Hygiene in Health Care: First Global Patient Safety Challenge: Clean Care is Safer Care","year":"2009"},{"issue":"2","key":"2020110613095992600_ocaa115-B3","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.ajic.2013.07.014","article-title":"Accuracy of a radiofrequency identification (RFID) badge system to monitor hand hygiene behavior during routine clinical activities","volume":"42","author":"Pineles","year":"2014","journal-title":"Am J Infect Control"},{"issue":"10","key":"2020110613095992600_ocaa115-B4","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1016\/j.ajic.2012.01.026","article-title":"Automated hand hygiene count devices may better measure compliance than human observation","volume":"40","author":"Morgan","year":"2012","journal-title":"Am J Infect Control"},{"issue":"5","key":"2020110613095992600_ocaa115-B5","doi-asserted-by":"crossref","first-page":"224","DOI":"10.5005\/jp-journals-10071-23165","article-title":"Video surveillance of hand hygiene: a better tool for monitoring and ensuring hand hygiene adherence","volume":"23","author":"Sharma","year":"2019","journal-title":"Indian J Crit Care Med"},{"issue":"7","key":"2020110613095992600_ocaa115-B6","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.ajic.2015.03.008","article-title":"Measuring hand hygiene compliance rates at hospital entrances","volume":"43","author":"Vaidotas","year":"2015","journal-title":"Am J Infect Control"},{"issue":"1","key":"2020110613095992600_ocaa115-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/cid\/cir773","article-title":"Using high-technology to enforce low-technology safety measures: the use of third-party remote video auditing and real-time feedback in healthcare","volume":"54","author":"Armellino","year":"2012","journal-title":"Clin Infect Dis"},{"issue":"22","key":"2020110613095992600_ocaa115-B8","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"1","key":"2020110613095992600_ocaa115-B9","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat Med"},{"issue":"7660","key":"2020110613095992600_ocaa115-B10","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/nature22985","article-title":"Corrigendum: dermatologist-level classification of skin cancer with deep neural networks","volume":"546","author":"Esteva","year":"2017","journal-title":"Nature"},{"issue":"22","key":"2020110613095992600_ocaa115-B11","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Ehteshami Bejnordi","year":"2017","journal-title":"JAMA"},{"key":"2020110613095992600_ocaa115-B12","first-page":"792","article-title":"Learning spatio-temporal structure from RGB-D videos for human activity detection and anticipation","author":"Koppula","year":"2013","journal-title":"In: International Conference on Machine Learning"},{"key":"2020110613095992600_ocaa115-B13","first-page":"842","author":"Sung","year":"2012"},{"key":"2020110613095992600_ocaa115-B14","first-page":"357","author":"Xia","year":"2015"},{"key":"2020110613095992600_ocaa115-B15","first-page":"5903","author":"Rehder","year":"2018"},{"issue":"1","key":"2020110613095992600_ocaa115-B16","doi-asserted-by":"crossref","first-page":"ofv200","DOI":"10.1093\/ofid\/ofv200","article-title":"Using computer vision and depth sensing to measure healthcare worker-patient contacts and personal protective equipment adherence within hospital rooms","volume":"3","author":"Chen","year":"2016","journal-title":"Open Forum Infect Dis"},{"issue":"1","key":"2020110613095992600_ocaa115-B17","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1093\/intqhc\/mzy099","article-title":"The use of privacy-protected computer vision to measure the quality of healthcare worker hand hygiene","volume":"31","author":"Awwad","year":"2019","journal-title":"Int J Qual Health Care"},{"key":"2020110613095992600_ocaa115-B18","author":"Huang","year":"2017"},{"issue":"7553","key":"2020110613095992600_ocaa115-B19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2020110613095992600_ocaa115-B20","first-page":"1137","author":"Kohavi","year":"1995"},{"key":"2020110613095992600_ocaa115-B21","first-page":"75","article-title":"Towards vision-based smart hospitals: a system for tracking and monitoring hand hygiene compliance","volume":"68","author":"Haque","year":"2017","journal-title":"Mach Learn Healthcare"},{"issue":"1","key":"2020110613095992600_ocaa115-B22","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s41746-019-0087-z","article-title":"A computer vision system for deep learning-based detection of patient mobilization activities in the ICU","volume":"2","author":"Yeung","year":"2019","journal-title":"NPJ Digit Med"},{"key":"2020110613095992600_ocaa115-B23","volume-title":"Statistical Methods for Rates and Proportions","author":"Fleiss","year":"2013"},{"key":"2020110613095992600_ocaa115-B24"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/8\/1316\/34152697\/ocaa115.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/8\/1316\/34152697\/ocaa115.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:30:53Z","timestamp":1604691053000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/27\/8\/1316\/5876566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,26]]},"references-count":24,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2020,7,26]]},"published-print":{"date-parts":[[2020,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaa115","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,8]]},"published":{"date-parts":[[2020,7,26]]}}}