{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:32:13Z","timestamp":1758123133770},"reference-count":41,"publisher":"Georg Thieme Verlag KG","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Appl Clin Inform"],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>\n          Background\u2003In critically ill infants, the position of a peripherally inserted central catheter (PICC) must be confirmed frequently, as the tip may move from its original position and run the risk of hyperosmolar vascular damage or extravasation into surrounding spaces. Automated detection of PICC tip position holds great promise for alerting bedside clinicians to noncentral PICCs.<\/jats:p><jats:p>\n          Objectives\u2003This research seeks to use natural language processing (NLP) and supervised machine learning (ML) techniques to predict PICC tip position based primarily on text analysis of radiograph reports from infants with an upper extremity PICC.<\/jats:p><jats:p>\n          Methods\u2003Radiographs, containing a PICC line in infants under 6 months of age, were manually classified into 12 anatomical locations based on the radiologist's textual report of the PICC line's tip. After categorization, we performed a 70\/30 train\/test split and benchmarked the performance of seven different (neural network, support vector machine, the na\u00efve Bayes, decision tree, random forest, AdaBoost, and K-nearest neighbors) supervised ML algorithms. After optimization, we calculated accuracy, precision, and recall of each algorithm's ability to correctly categorize the stated location of the PICC tip.<\/jats:p><jats:p>\n          Results\u2003A total of 17,337 radiographs met criteria for inclusion and were labeled manually. Interrater agreement was 99.1%. Support vector machines and neural networks yielded accuracies as high as 98% in identifying PICC tips in central versus noncentral position (binary outcome) and accuracies as high as 95% when attempting to categorize the individual anatomical location (12-category outcome).<\/jats:p><jats:p>\n          Conclusion\u2003Our study shows that ML classifiers can automatically extract the anatomical location of PICC tips from radiology reports. Two ML classifiers, support vector machine (SVM) and a neural network, obtained top accuracies in both binary and multiple category predictions. Implementing these algorithms in a neonatal intensive care unit as a clinical decision support system may help clinicians address PICC line position.<\/jats:p>","DOI":"10.1055\/s-0041-1735178","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T23:10:06Z","timestamp":1631142606000},"page":"856-863","source":"Crossref","is-referenced-by-count":8,"title":["Machine Learning for Detection of Correct Peripherally Inserted Central Catheter Tip Position from Radiology Reports in Infants"],"prefix":"10.1055","volume":"12","author":[{"given":"Manan","family":"Shah","sequence":"additional","affiliation":[{"name":"Division of Neonatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"}]},{"given":"Derek","family":"Shu","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, Ohio, United States"}]},{"given":"V. B. Surya","family":"Prasath","sequence":"additional","affiliation":[{"name":"Division of Bioinformatics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"}]},{"given":"Yizhao","family":"Ni","sequence":"additional","affiliation":[{"name":"Division of Bioinformatics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"},{"name":"Department of Biomedical Informatics, University of Cincinnati College of Medicine, Cincinnati, Ohio, United States"}]},{"given":"Andrew H.","family":"Schapiro","sequence":"additional","affiliation":[{"name":"Department of Radiology and Medical Imaging, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"},{"name":"Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, Ohio, United States"}]},{"given":"Kevin R.","family":"Dufendach","sequence":"additional","affiliation":[{"name":"Division of Neonatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"},{"name":"Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, Ohio, United States"},{"name":"Division of Bioinformatics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, United States"}]}],"member":"194","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"issue":"01","key":"ref1","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1097\/ANC.0b013e318278b907","article-title":"A national survey of neonatal peripherally inserted central catheter (PICC) practices","volume":"13","author":"E Sharpe","year":"2013","journal-title":"Adv Neonatal Care"},{"issue":"11","key":"ref2","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1007\/s00247-016-3648-1","article-title":"Variables decreasing tip movement of peripherally inserted central catheters in pediatric patients","volume":"46","author":"R Gnannt","year":"2016","journal-title":"Pediatr Radiol"},{"key":"ref3","first-page":"102","volume-title":"Peripherally inserted central catheters","author":"A Loskutav","year":"2018","edition":"2nd ed."},{"issue":"02","key":"ref4","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s00246-019-02274-1","article-title":"Arrhythmias in children with peripherally inserted central catheters (PICCs)","volume":"41","author":"S S Dhillon","year":"2020","journal-title":"Pediatr Cardiol"},{"issue":"12","key":"ref5","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.1007\/s00247-017-3939-1","article-title":"Non-central peripherally inserted central catheters in neonatal intensive care: complication rates and longevity of catheters relative to tip position","volume":"47","author":"B Goldwasser","year":"2017","journal-title":"Pediatr Radiol"},{"issue":"04","key":"ref6","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1038\/jp.2012.112","article-title":"Peripherally inserted central catheter tip position and risk of associated complications in neonates","volume":"33","author":"A Jain","year":"2013","journal-title":"J Perinatol"},{"issue":"04","key":"ref7","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1055\/s-0039-1695791","article-title":"Interactive NLP in clinical care: identifying incidental findings in radiology reports","volume":"10","author":"G Trivedi","year":"2019","journal-title":"Appl Clin Inform"},{"issue":"01","key":"ref8","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1055\/s-0038-1626725","article-title":"Development and validation of a natural language processing tool to identify patients treated for pneumonia across VA emergency departments","volume":"9","author":"B E Jones","year":"2018","journal-title":"Appl Clin Inform"},{"issue":"02","key":"ref9","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1148\/radiol.16142770","article-title":"Natural language processing in radiology: a systematic review","volume":"279","author":"E Pons","year":"2016","journal-title":"Radiology"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","article-title":"Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review","volume":"73","author":"K Kreimeyer","year":"2017","journal-title":"J Biomed Inform"},{"issue":"01","key":"ref11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00762ED1V01Y201703HLT037","article-title":"Neural network methods in natural language processing","volume":"10","author":"Y Goldberg","year":"2017","journal-title":"Synthesis Lectures on Human Language Technologies"},{"issue":"01","key":"ref12","doi-asserted-by":"crossref","first-page":"e16023","DOI":"10.2196\/16023","article-title":"Sentiment analysis in health and well-being: systematic review","volume":"8","author":"A Zunic","year":"2020","journal-title":"JMIR Med Inform"},{"issue":"02","key":"ref13","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1055\/s-0040-1708049","article-title":"Natural language processing to extract meaningful information from patient experience feedback","volume":"11","author":"K Nawab","year":"2020","journal-title":"Appl Clin Inform"},{"key":"ref14","first-page":"1923","article-title":"Identifying falls risk screenings not documented with administrative codes using natural language processing","volume":"2017","author":"V J Zhu","year":"2018","journal-title":"AMIA Annu Symp Proc"},{"key":"ref15","first-page":"807","article-title":"Computer-assisted diagnostic coding: effectiveness of an NLP-based approach using SNOMED CT to ICD-10 mappings","volume":"2018","author":"A N Nguyen","year":"2018","journal-title":"AMIA Annu Symp Proc"},{"issue":"04","key":"ref16","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.4338\/ACI-2016-08-RA-0129","article-title":"Identification of long bone fractures in radiology reports using natural language processing to support healthcare quality improvement","volume":"7","author":"R W Grundmeier","year":"2016","journal-title":"Appl Clin Inform"},{"issue":"03","key":"ref17","doi-asserted-by":"crossref","first-page":"600","DOI":"10.4338\/ACI-2014-11-RA-0110","article-title":"Natural language processing techniques for extracting and categorizing finding measurements in narrative radiology reports","volume":"6","author":"M Sevenster","year":"2015","journal-title":"Appl Clin Inform"},{"issue":"02","key":"ref18","doi-asserted-by":"crossref","first-page":"447","DOI":"10.4338\/ACI-2017-01-IE-0018","article-title":"Canary: an NLP platform for clinicians and researchers","volume":"8","author":"S Malmasi","year":"2017","journal-title":"Appl Clin Inform"},{"issue":"20","key":"ref19","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"R C Deo","year":"2015","journal-title":"Circulation"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.jbi.2018.07.004","article-title":"An unsupervised machine learning method for discovering patient clusters based on genetic signatures","volume":"85","author":"C Lopez","year":"2018","journal-title":"J Biomed Inform"},{"issue":"02","key":"ref21","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1148\/radiol.2018171820","article-title":"Current applications and future impact of machine learning in radiology","volume":"288","author":"G Choy","year":"2018","journal-title":"Radiology"},{"issue":"11","key":"ref22","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","article-title":"Deep learning in radiology","volume":"25","author":"M P McBee","year":"2018","journal-title":"Acad Radiol"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"issue":"18","key":"ref24","doi-asserted-by":"crossref","first-page":"1806","DOI":"10.1001\/jama.2019.16489","article-title":"How to read articles that use machine learning: users' guides to the medical literature","volume":"322","author":"Y Liu","year":"2019","journal-title":"JAMA"},{"issue":"06","key":"ref25","first-page":"366","article-title":"Principles of automation for patient safety in intensive care: learning from aviation","volume":"44","author":"J Dominiczak","year":"2018","journal-title":"Jt Comm J Qual Patient Saf"},{"issue":"04","key":"ref26","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s10278-017-0025-z","article-title":"A deep-learning system for fully-automated peripherally inserted central catheter (PICC) tip detection","volume":"31","author":"H Lee","year":"2018","journal-title":"J Digit Imaging"},{"issue":"02","key":"ref27","doi-asserted-by":"crossref","first-page":"e0212778","DOI":"10.1371\/journal.pone.0212778","article-title":"Natural language processing and machine learning algorithm to identify brain MRI reports with acute ischemic stroke","volume":"14","author":"C Kim","year":"2019","journal-title":"PLoS One"},{"key":"ref28","volume-title":"Python 3 Reference Manual","author":"G V Rossum","year":"2009"},{"key":"ref29","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"R18","DOI":"10.1016\/j.jacr.2015.12.008","article-title":"Follow-up of incidental pulmonary nodules and the radiology report","volume":"13","author":"D P Blagev","year":"2016","journal-title":"J Am Coll Radiol"},{"issue":"06","key":"ref31","doi-asserted-by":"crossref","first-page":"e205867","DOI":"10.1001\/jamanetworkopen.2020.5867","article-title":"Frequency and types of patient-reported errors in electronic health record ambulatory care notes","volume":"3","author":"S K Bell","year":"2020","journal-title":"JAMA Netw Open"},{"issue":"04","key":"ref32","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1093\/jamia\/ocaa293","article-title":"Speaking up about patient-perceived serious visit note errors: patient and family experiences and recommendations","volume":"28","author":"B D Lam","year":"2021","journal-title":"J Am Med Inform Assoc"},{"issue":"01","key":"ref33","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1093\/jamia\/ocw067","article-title":"Comparison of accuracy of physical examination findings in initial progress notes between paper charts and a newly implemented electronic health record","volume":"24","author":"S Yadav","year":"2017","journal-title":"J Am Med Inform Assoc"},{"issue":"12","key":"ref34","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1001\/jama.2018.1171","article-title":"Electronic health record usability issues and potential contribution to patient harm","volume":"319","author":"J L Howe","year":"2018","journal-title":"JAMA"},{"issue":"04","key":"ref35","doi-asserted-by":"crossref","first-page":"479","DOI":"10.4300\/JGME-D-16-00123.1","article-title":"Electronic health record effects on work-life balance and burnout within the I3 population collaborative","volume":"9","author":"S L Robertson","year":"2017","journal-title":"J Grad Med Educ"},{"issue":"08","key":"ref36","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.ijmedinf.2015.04.002","article-title":"Impact of electronic health record technology on the work and workflow of physicians in the intensive care unit","volume":"84","author":"P Carayon","year":"2015","journal-title":"Int J Med Inform"},{"issue":"05","key":"ref37","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1177\/0018720815576827","article-title":"Usability and safety in electronic medical records interface design: a review of recent literature and guideline formulation","volume":"57","author":"M Zahabi","year":"2015","journal-title":"Hum Factors"},{"key":"ref38","volume-title":"Pattern Recognition and Machine Learning","author":"C M Bishop","year":"2016"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-94463-0","volume-title":"Neural Networks and Deep Learning: A Textbook","author":"C C Aggarwal","year":"2018"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809682","volume-title":"Kernel Methods for Pattern Analysis","author":"J CN Shawe-Taylor","year":"2004"},{"issue":"01","key":"ref41","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"}],"container-title":["Applied Clinical Informatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/s-0041-1735178.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T23:11:21Z","timestamp":1631142681000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/s-0041-1735178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":41,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2021,8,4]]},"published-print":{"date-parts":[[2021,8]]}},"URL":"https:\/\/doi.org\/10.1055\/s-0041-1735178","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["1869-0327"],"issn-type":[{"value":"1869-0327","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}