[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290570-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290570-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","automated-lung-ultrasound-pulmonary-disease-quantification-using-an-unsupervised-machine-learning-technique-for-covid-19","Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19","","COVID-19 is an ongoing global health pandemic. Although PCR and other tests exist, they do not directly establish pulmonary disease burden. Point-of-care lung ultrasound (POCUS) can assess characteristic pulmonary findings, and ultrasound is inexpensive, portable, and widely available. An unsupervised calculated lung ultrasound (CLU) index quantifies A/B lines, consolidations, and pleural effusions as a score of pulmonary disease burden without large-scale training. CLU was tested on 52 examinations and showed strong agreement with radiologist findings across disease states. Because COVID-19 is global, CLU may support more accurate assessment in resource-constrained settings with limited ultrasound expertise.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/automated-lung-ultrasound-pulmonary-disease-quantification-using-an-unsupervised-machine-learning-technique-for-covid-19/290570/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/automated-lung-ultrasound-pulmonary-disease-quantification-using-an-unsupervised-machine-learning-technique-for-covid-19/290570.png","ImageObject",300,407,{"name":42,"@type":43},"Liam","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-23","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the CLU index address in COVID-19 assessment?","Question",{"text":63,"@type":64},"It quantifies pulmonary disease burden rather than relying on tests that do not directly establish burden. The CLU index uses ultrasound findings to produce a quantitative severity-related score.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which lung ultrasound findings can the CLU index quantify?",{"text":68,"@type":64},"It can quantify A lines and B lines, consolidations, and pleural effusions, and then use them to compute a CLU index score.",{"name":70,"@type":61,"acceptedAnswer":71},"How was the CLU index evaluated and what were the results?",{"text":72,"@type":64},"It was tested on 52 lung ultrasound examinations from multiple institutions and demonstrated excellent concordance with radiologist findings across different pulmonary disease states.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290570,1789642106,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","diagnostics  \nArticle  \nAutomated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19  \nHersh Sagreiya 1, *, Michael A. Jacobs 2,3 and Alireza Akhbardeh 3,4  \nCitation: Sagreiya, H.; Jacobs, M.A.; Akhbardeh, A. Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19 . Diagnostics 2023, 13, 2692. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/diagnostics13162692](10.3390/diagnostics13162692)  \nAcademic Editor: Chiara Martini  \n1 Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA  \n2 The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA  \n3 Department of Diagnostic and Interventional Imaging, The University of Texas Health Science Center, Houston, TX 77030, USA  \n4 Ambient Digital LLC, Daly City, CA 94014, USA  \n* [Correspondence: hersh.sagreiya@pennmedicine.upenn.edu](Correspondence: hersh.sagreiya@pennmedicine.upenn.edu); Tel.: +1-215-614-0351  \nAbstract: COVID-19 is an ongoing global health pandemic. Although COVID-19 can be diagnosed with various tests such as PCR, these tests do not establish pulmonary disease burden. Whereas point-of-care lung ultrasound (POCUS) can directly assess the severity of characteristic pulmonary findings of COVID-19, the advantage of using US is that it is inexpensive, portable, and widely available for use in many clinical settings. For automated assessment of pulmonary findings, we have developed an unsupervised learning technique termed the calculated lung ultrasound (CLU) index. The CLU can quantify various types of lung findings, such as A or B lines, consolidations, and pleural effusions, and it uses these findings to calculate a CLU index score, which is a quantitative measure of pulmonary disease burden. This is accomplished using an unsupervised, patient-specific approach that does not require training on a large dataset. The CLU was tested on 52 lung ultrasound examinations from several institutions. CLU demonstrated excellent concordance with radiologist findings in different pulmonary disease states. Given the global nature of COVID-19, the CLU would be useful for sonographers and physicians in resource-strapped areas with limited ultrasound training and diagnostic capacities for more accurate assessment of pulmonary status.  \nKeywords: ultrasound; machine learning; COVID-19; unsupervised learning; POCUS; computer vision; treatment effectiveness  \n1. Introduction  \nReceived: 21 April 2023  \nRevised: 30 July 2023  \nAccepted: 11 August 2023  \nPublished: 16 August 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \nSARS-CoV-2, also known as COVID-19, is a global pandemic that has led to over six hundred million documented cases and 6 .8 million deaths, and it has resulted in devastating economic damage as of early 2023 [1] . Radiological imaging is useful for assessing pulmonary disease burden, assessing disease severity, and tracking the disease course [2] . Although X-rays are both portable and inexpensive, they lack sensitivity compared to CT, with a reported sensitivity of 69%[3] . While CT provides excellent anatomic imaging, its use in the United States is typically limited to acute cases, it is not portable, and it may bedifficult to access for longitudinal monitoring due to logistical concerns, cost, and cumulative radiation dose [4,5] . However, ultrasound (US) is relatively inexpensive, portable, and widely available, and it has successfully been used to monitor lung diseases [6] . Infact,","cbCaiaDFm8opuseq","https://ap.wps.com/l/cbCaiaDFm8opuseq","pdf",1765362,"English","# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What problem does the CLU index address in COVID-19 assessment?\",\"answer\":\"It quantifies pulmonary disease burden rather than relying on tests that do not directly establish burden. The CLU index uses ultrasound findings to produce a quantitative severity-related score.\"},{\"question\":\"Which lung ultrasound findings can the CLU index quantify?\",\"answer\":\"It can quantify A lines and B lines, consolidations, and pleural effusions, and then use them to compute a CLU index score.\"},{\"question\":\"How was the CLU index evaluated and what were the results?\",\"answer\":\"It was tested on 52 lung ultrasound examinations from multiple institutions and demonstrated excellent concordance with radiologist findings across different pulmonary disease states.\"}]","Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19 | PDF",28]