{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T06:50:24Z","timestamp":1787986224843,"version":"build-2784847793"},"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T00:00:00Z","timestamp":1616630400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"100th Anniversary Chulalongkorn University for Doctoral Scholarship"},{"name":"90th Anniversary of Chulalongkorn University Research Grant"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background and objectives<\/jats:title>\n<jats:p>Diagnosis of Pulmonary Rifampicin Resistant Tuberculosis (RR-TB) with the Drug-Susceptibility Test (DST) is costly and time-consuming. Furthermore, GeneXpert for rapid diagnosis is not widely available in Indonesia. This study aims to develop and evaluate the CUHAS-ROBUST model performance, an artificial-intelligence-based RR-TB screening tool.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>A cross-sectional study involved suspected all type of RR-TB patients with complete sputum Lowenstein Jensen DST (reference) and 19 clinical, laboratory, and radiology parameter results, retrieved from medical records in hospitals under the Faculty of Medicine, Hasanuddin University Indonesia, from January 2015-December 2019. The Artificial Neural Network (ANN) models were built along with other classifiers. The model was tested on participants recruited from January 2020-October 2020 and deployed into CUHAS-ROBUST (index test) application. Sensitivity, specificity, and accuracy were obtained for assessment.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>A total of 487 participants (32 Multidrug-Resistant\/MDR 57 RR-TB, 398 drug-sensitive) were recruited for model building and 157 participants (23 MDR and 21 RR) in prospective testing. The ANN full model yields the highest values of accuracy (88% (95% CI 85\u201391)), and sensitivity (84% (95% CI 76\u201389)) compare to other models that show sensitivity below 80% (Logistic Regression 32%, Decision Tree 44%, Random Forest 25%, Extreme Gradient Boost 25%). However, this ANN has lower specificity among other models (90% (95% CI 86\u201393)) where Logistic Regression demonstrates the highest (99% (95% CI 97\u201399)). This ANN model was selected for the CUHAS-ROBUST application, although still lower than the sensitivity of global GeneXpert results (87.5%).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The ANN-CUHAS ROBUST outperforms other AI classifiers model in detecting all type of RR-TB, and by deploying into the application, the health staff can utilize the tool for screening purposes particularly at the primary care level where the GeneXpert examination is not available.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Trial registration<\/jats:title>\n<jats:p><jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/clinicaltrials.gov\/ct2\/show\/NCT04208789\" xlink:type=\"simple\">NCT04208789<\/jats:ext-link>.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0249243","type":"journal-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:28:30Z","timestamp":1616704110000},"page":"e0249243","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Development and performance of CUHAS-ROBUST application for pulmonary rifampicin-resistance tuberculosis screening in Indonesia"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8206-6764","authenticated-orcid":true,"given":"Bumi","family":"Herman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wandee","family":"Sirichokchatchawan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sathirakorn","family":"Pongpanich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanin","family":"Nantasenamat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,3,25]]},"reference":[{"key":"pone.0249243.ref001","volume-title":"WHO consolidated guidelines on drug-resistant tuberculosis treatment","author":"WHO","year":"2019"},{"key":"pone.0249243.ref002","volume-title":"Global Tuberculosis Report","author":"WHO","year":"2019"},{"issue":"2","key":"pone.0249243.ref003","doi-asserted-by":"crossref","first-page":"96","DOI":"10.4103\/0974-2727.180789","article-title":"Epidemiology of Rifampicin Resistant Tuberculosis and Common Mutations in rpoB Gene of Mycobacterium tuberculosis: A Retrospective Study from Six Districts of Punjab (India) Using Xpert MTB\/RIF Assay","volume":"8","author":"R Kaur","year":"2016","journal-title":"J Lab Physicians"},{"issue":"7","key":"pone.0249243.ref004","doi-asserted-by":"crossref","first-page":"e0200523","DOI":"10.1371\/journal.pone.0200523","article-title":"Delayed diagnosis and treatment of tuberculosis in HIV+ patients in Mozambique: A cost-effectiveness analysis of screening protocols based on four symptom screening, smear microscopy, urine LAM test and Xpert MTB\/RIF","volume":"13","author":"S Orlando","year":"2018","journal-title":"PLoS One"},{"issue":"8","key":"pone.0249243.ref005","doi-asserted-by":"crossref","first-page":"e0201731","DOI":"10.1371\/journal.pone.0201731","article-title":"The implementation of Xpert MTB\/RIF assay for diagnosis of tuberculosis in Nepal: A mixed-methods analysis","volume":"13","author":"B Joshi","year":"2018","journal-title":"PLOS ONE"},{"issue":"7","key":"pone.0249243.ref006","doi-asserted-by":"crossref","first-page":"e0180572","DOI":"10.1371\/journal.pone.0180572","article-title":"Sputum quality and diagnostic performance of GeneXpert MTB\/RIF among smear-negative adults with presumed tuberculosis in Uganda","volume":"12","author":"AJ Meyer","year":"2017","journal-title":"PloS one"},{"key":"pone.0249243.ref007","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1183\/09031936.05.00111304","article-title":"Drug-susceptibility testing in tuberculosis: Methods and reliability of results","volume":"25","author":"S Kim","year":"2005","journal-title":"The European respiratory journal: official journal of the European Society for Clinical Respiratory Physiology"},{"key":"pone.0249243.ref008","doi-asserted-by":"crossref","first-page":"401896","DOI":"10.1155\/2012\/401896","article-title":"A Systematic Review of Clinical Diagnostic Systems Used in the Diagnosis of Tuberculosis in Children","volume":"2012","author":"EC Pearce","year":"2012","journal-title":"AIDS Research and Treatment"},{"issue":"5","key":"pone.0249243.ref009","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/S1532-0464(03)00034-0","article-title":"Logistic regression and artificial neural network classification models: a methodology review","volume":"35","author":"S Dreiseitl","year":"2002","journal-title":"Journal of Biomedical Informatics"},{"issue":"11","key":"pone.0249243.ref010","doi-asserted-by":"crossref","first-page":"e00938","DOI":"10.1016\/j.heliyon.2018.e00938","article-title":"State-of-the-art in artificial neural network applications: A survey","volume":"4","author":"OI Abiodun","year":"2018","journal-title":"Heliyon"},{"issue":"8","key":"pone.0249243.ref011","doi-asserted-by":"crossref","first-page":"e12082","DOI":"10.1371\/journal.pone.0012082","article-title":"Clinical Prediction Rule for Stratifying Risk of Pulmonary Multidrug-Resistant Tuberculosis","volume":"5","author":"D Mart\u00ednez","year":"2010","journal-title":"PLoS One"},{"key":"pone.0249243.ref012","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.neucom.2016.08.151","article-title":"Kritski AL. Neural network models for supporting drug and multidrug resistant tuberculosis screening diagnosis","volume":"265","author":"Seixas JM \u00c9vora LHRA","year":"2017","journal-title":"Neurocomputing"},{"issue":"1","key":"pone.0249243.ref013","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1186\/s12879-017-2669-1","article-title":"Outcomes from patients with presumed drug resistant tuberculosis in five reference centers in Brazil","volume":"17","author":"DMP Ramalho","year":"2017","journal-title":"BMC Infect Dis"},{"issue":"4","key":"pone.0249243.ref014","doi-asserted-by":"crossref","first-page":"309","DOI":"10.4103\/0970-2113.102794","article-title":"Minimal inhibitory concentrations of first-line drugs of multidrug-resistant tuberculosis isolates","volume":"29","author":"N Sch\u00f6nfeld","year":"2012","journal-title":"Lung India"},{"issue":"6","key":"pone.0249243.ref015","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.jinf.2018.10.004","article-title":"Risk factors of multidrug-resistant tuberculosis: A global systematic review and meta-analysis","volume":"77","author":"IS Pradipta","year":"2018","journal-title":"The Journal of infection"},{"issue":"1","key":"pone.0249243.ref016","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/1617-9625-10-11","article-title":"Relationship between smoking and a new index of arterial stiffness, the cardio-ankle vascular index, in male workers: a cross-sectional study","volume":"10","author":"K Hata","year":"2012","journal-title":"Tob Induc Dis"},{"issue":"1","key":"pone.0249243.ref017","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.mce.2010.04.005","article-title":"The anti-inflammatory and immunosuppressive effects of glucocorticoids, recent developments and mechanistic insights","volume":"335","author":"AE Coutinho","year":"2011","journal-title":"Mol Cell Endocrinol"},{"issue":"Supplement 1","key":"pone.0249243.ref018","first-page":"S14","volume":"43","year":"2020","journal-title":"2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes\u20142020"},{"key":"pone.0249243.ref019","doi-asserted-by":"crossref","first-page":"225","DOI":"10.2147\/COPD.S228958","article-title":"GOLD Classifications, COPD Hospitalization, and All-Cause Mortality in Chronic Obstructive Pulmonary Disease: The HUNT Study","volume":"15","author":"L Bhatta","year":"2020","journal-title":"Int J Chron Obstruct Pulmon Dis"},{"issue":"1","key":"pone.0249243.ref020","doi-asserted-by":"crossref","first-page":"e00064","DOI":"10.1128\/CMR.00064-18","article-title":"Diagnosis of Human Immunodeficiency Virus Infection","volume":"32","author":"BS Parekh","year":"2018","journal-title":"Clin Microbiol Rev"},{"issue":"7","key":"pone.0249243.ref021","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1373\/clinchem.2018.296962","article-title":"The National Glycohemoglobin Standardization Program: Over 20 Years of Improving Hemoglobin A(1c) Measurement","volume":"65","author":"RR Little","year":"2019","journal-title":"Clin Chem"},{"key":"pone.0249243.ref022","first-page":"108","article-title":"Ziehl-Neelsen staining: Theory and practice","volume":"12","author":"A Deun","year":"2008","journal-title":"The international journal of tuberculosis and lung disease: the official journal of the International Union against Tuberculosis and Lung Disease"},{"key":"pone.0249243.ref023","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.jctube.2016.05.005","article-title":"Diagnosis of active tuberculosis disease: From microscopy to molecular techniques","volume":"4","author":"AJ Caulfield","year":"2016","journal-title":"Journal of Clinical Tuberculosis and Other Mycobacterial Diseases"},{"issue":"2","key":"pone.0249243.ref024","doi-asserted-by":"crossref","first-page":"161","DOI":"10.21037\/qims.2018.03.06","article-title":"Radiological signs associated with pulmonary multi-drug resistant tuberculosis: an analysis of published evidences","volume":"8","author":"YXJ W\u00e1ng","year":"2018","journal-title":"Quant Imaging Med Surg"},{"issue":"6","key":"pone.0249243.ref025","first-page":"145","article-title":"Current tools available for the diagnosis of drug-resistant tuberculosis","volume":"3","author":"C Gilpin","year":"2016","journal-title":"Ther Adv Infect Dis"},{"issue":"2","key":"pone.0249243.ref026","doi-asserted-by":"crossref","first-page":"e0149258","DOI":"10.1371\/journal.pone.0149258","article-title":"Genotypic, Phenotypic and Clinical Validation of GeneXpert in Extra-Pulmonary and Pulmonary Tuberculosis in India","volume":"11","author":"UB Singh","year":"2016","journal-title":"PloS one"},{"issue":"1","key":"pone.0249243.ref027","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1186\/s12916-017-0955-9","article-title":"A comparison of liquid and solid culture for determining relapse and durable cure in phase III TB trials for new regimens","volume":"15","author":"PPJ Phillips","year":"2017","journal-title":"BMC Medicine"},{"issue":"1","key":"pone.0249243.ref028","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.ijmyco.2012.11.003","article-title":"Inconsistencies in drug susceptibility testing of Mycobacterium tuberculosis: Current riddles and recommendations","volume":"2","author":"B Varghese","year":"2013","journal-title":"International Journal of Mycobacteriology"},{"issue":"3","key":"pone.0249243.ref029","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1378\/chest.51.3.275","article-title":"N-Acetyl-L-Cysteine Sputum Homogenization and Its Mechanism of Action on Isolation of Tubercle Bacilli","volume":"51","author":"V Lorian","year":"1967","journal-title":"Diseases of the Chest"},{"key":"pone.0249243.ref030","first-page":"147","author":"K Stinson","year":"2014","journal-title":"Global Laboratory Initiative a Working Group of the Stop TB Partnership: Mycobacteriology Laboratory Manual"},{"issue":"52","key":"pone.0249243.ref031","first-page":"3094","article-title":"Antimicrobial susceptibility testing of Mycobacterium tuberculosis complex for first and second line drugs by broth dilution in a microtiter plate format","author":"L Hall","year":"2011","journal-title":"J Vis Exp"},{"key":"pone.0249243.ref032","author":"R Saia","year":"2019","journal-title":"A Discretized Enriched Technique to Enhance Machine Learning Performance in Credit Scoring"},{"key":"pone.0249243.ref033","first-page":"150","article-title":"Artificial Neural Networks in Medical Diagnosis","volume":"8","author":"Q Al-Shayea","year":"2011","journal-title":"Int J Comput Sci Issues"},{"key":"pone.0249243.ref034","volume-title":"R: A language and environment for statistical computing","author":"RDC Team","year":"2020"},{"key":"pone.0249243.ref035","first-page":"2","article-title":"neuralnet: Training of Neural Networks","author":"F G\u00fcnther","year":"2010","journal-title":"R Journal"},{"key":"pone.0249243.ref036","doi-asserted-by":"crossref","first-page":"37","DOI":"10.4310\/CIS.2018.v18.n1.a2","article-title":"investigation for loss functions widely used in machine learning","volume":"18","author":"F Nie","year":"2018","journal-title":"Communications in Information and Systems"},{"key":"pone.0249243.ref037","doi-asserted-by":"crossref","first-page":"237","DOI":"10.2747\/1548-1603.44.3.237","article-title":"Improving Classification Accuracy Assessments with Statistical Bootstrap Resampling Techniques","volume":"44","author":"K Weber","year":"2007","journal-title":"Giscience & Remote Sensing\u2014GISCI REMOTE SENS"},{"key":"pone.0249243.ref038","unstructured":"Blank S. Resampling Stats for Excel. Illinois, USA2019."},{"issue":"2","key":"pone.0249243.ref039","doi-asserted-by":"crossref","first-page":"e0213017","DOI":"10.1371\/journal.pone.0213017","article-title":"Evaluation of Xpert MTB-RIF guided diagnosis and treatment of rifampicin-resistant tuberculosis in Indonesia: A retrospective cohort study","volume":"14","author":"AY Soeroto","year":"2019","journal-title":"PloS one"},{"key":"pone.0249243.ref040","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.jbi.2014.02.013","article-title":"Sample size estimation in diagnostic test studies of biomedical informatics","volume":"48","author":"K Hajian-Tilaki","year":"2014","journal-title":"Journal of Biomedical Informatics"},{"issue":"2","key":"pone.0249243.ref041","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.tele.2015.08.006","article-title":"Disease prediction with different types of neural network classifiers","volume":"33","author":"C-H Weng","year":"2016","journal-title":"Telematics and Informatics"},{"issue":"10","key":"pone.0249243.ref042","first-page":"846","article-title":"Do electronic medical records improve quality of care?","volume":"61","author":"DP Manca","year":"2015","journal-title":"Yes. Can Fam Physician"},{"key":"pone.0249243.ref043","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.jocm.2018.07.002","article-title":"Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis","volume":"28","author":"A Alwosheel","year":"2018","journal-title":"Journal of Choice Modelling"},{"key":"pone.0249243.ref044","doi-asserted-by":"crossref","first-page":"55","DOI":"10.2147\/POR.S172613","article-title":"Attitudes and beliefs related to reporting alcohol consumption in research studies: a case from Jordan","volume":"9","author":"FH Alhashimi","year":"2018","journal-title":"Pragmat Obs Res"},{"key":"pone.0249243.ref045","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/1472-6947-14-51","article-title":"Hidden in plain sight: bias towards sick patients when sampling patients with sufficient electronic health record data for research","volume":"14","author":"A Rusanov","year":"2014","journal-title":"BMC Med Inform Decis Mak"},{"issue":"4","key":"pone.0249243.ref046","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1183\/13993003.00986-2016","article-title":"Dosage of isoniazid and rifampicin poorly predicts drug exposure in tuberculosis patients","volume":"48","author":"MGG Sturkenboom","year":"2016","journal-title":"European Respiratory Journal"},{"issue":"4","key":"pone.0249243.ref047","doi-asserted-by":"crossref","first-page":"423","DOI":"10.3855\/jidc.7324","article-title":"Glycated hemoglobin screening identifies patients admitted for retreatment of tuberculosis at risk for diabetes in Tanzania","volume":"10","author":"ML Sariko","year":"2016","journal-title":"Journal of infection in developing countries"},{"key":"pone.0249243.ref048","author":"I Allaouzi","year":"2018","journal-title":"A 3D-CNN and SVM for Multi-Drug Resistance Detection"},{"key":"pone.0249243.ref049","author":"M Tatusch","year":"2018","journal-title":"Detection of Multidrug-Resistant Tuberculosis Using Convolutional Neural Networks and Decision Trees"},{"issue":"12","key":"pone.0249243.ref050","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1007\/s11548-018-1857-9","article-title":"Detecting drug-resistant tuberculosis in chest radiographs","volume":"13","author":"S Jaeger","year":"2018","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"2","key":"pone.0249243.ref051","doi-asserted-by":"crossref","first-page":"W126","DOI":"10.2214\/AJR.14.13116","article-title":"Radiographic Techniques, Contrast, and Noise","volume":"204","author":"W Huda","year":"2015","journal-title":"X-Ray Imaging. American Journal of Roentgenology"},{"issue":"3","key":"pone.0249243.ref052","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1007\/s12291-015-0535-8","article-title":"Assessment of Hematological Parameters in Pulmonary Tuberculosis Patients","volume":"31","author":"K Rohini","year":"2016","journal-title":"Indian J Clin Biochem"},{"key":"pone.0249243.ref053","doi-asserted-by":"crossref","first-page":"319","DOI":"10.25271\/2017.5.4.381","article-title":"A Normalization Methods for Backpropagation: A Comparative Study","volume":"5","author":"A Eesa","year":"2017","journal-title":"Science Journal of University of Zakho"},{"key":"pone.0249243.ref054","first-page":"8","article-title":"Data Normalization to Accelerate Training for Linear Neural Net to Predict Tropical Cyclone Tracks %","volume":"2015","author":"J Jin","year":"2015","journal-title":"J Mathematical Problems in Engineering"},{"key":"pone.0249243.ref055","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1007\/978-0-387-39940-9_565","volume-title":"Encyclopedia of Database Systems","author":"P Refaeilzadeh","year":"2009"},{"key":"pone.0249243.ref056","first-page":"12","article-title":"Comparison of three back-propagation training algorithms for two case studies","author":"O Kisi","year":"2005","journal-title":"Indian Journal of Engineering and Materials Sciences"},{"issue":"1","key":"pone.0249243.ref057","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"JM Johnson","year":"2019","journal-title":"Journal of Big Data"},{"key":"pone.0249243.ref058","first-page":"321","volume":"16","author":"NV Chawla","year":"2002","journal-title":"SMOTE: Synthetic Minority Over-sampling Technique"},{"issue":"1","key":"pone.0249243.ref059","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/S1473-3099(17)30691-6","article-title":"Xpert MTB\/RIF Ultra for detection of Mycobacterium tuberculosis and rifampicin resistance: a prospective multicentre diagnostic accuracy study","volume":"18","author":"SE Dorman","year":"2018","journal-title":"Lancet Infect Dis"},{"key":"pone.0249243.ref060","doi-asserted-by":"crossref","first-page":"E25","DOI":"10.5888\/pcd16.180385","article-title":"Geographic and Social Factors Associated With Chronic Disease Self-Management Program Participation: Going the \"Extra-Mile\" for Disease Prevention","volume":"16","author":"J Bobitt","year":"2019","journal-title":"Prev Chronic Dis"},{"issue":"1","key":"pone.0249243.ref061","first-page":"e000746","volume":"2","author":"BH Willis","year":"2012","journal-title":"Empirical evidence that disease prevalence may affect the performance of diagnostic tests with an implicit threshold: a cross-sectional study"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0249243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:29:33Z","timestamp":1616704173000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0249243"}},"subtitle":[],"editor":[{"given":"Frederick","family":"Quinn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,3,25]]},"references-count":61,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0249243","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,25]]}}}