{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:32:20Z","timestamp":1790112740488,"version":"4.0.1"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000071","name":"National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["1R21HD084114-0"],"award-info":[{"award-number":["1R21HD084114-0"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000071","name":"National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["R01HD110480"],"award-info":[{"award-number":["R01HD110480"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007623","name":"School of Medicine, Emory University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007623","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1-TR002378"],"award-info":[{"award-number":["UL1-TR002378"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>This paper introduces a novel approach to address the challenges associated with transferring blood pressure (BP) data obtained from oscillometric devices used in self-measured BP monitoring systems to integrate this data into medical health records or a proxy database accessible by clinicians, particularly in low literacy populations. To this end, we developed an automated image transcription technique to effectively transcribe readings from BP devices, ultimately enhancing the accessibility and usability of BP data for monitoring and managing BP during pregnancy and the postpartum period, particularly in low-resource settings and low-literate populations. In the designed study, the photos of the BP devices were captured as part of perinatal mobile health (mHealth) monitoring programs, conducted in four studies across two countries. The Guatemala Set 1 and Guatemala Set 2 datasets include the data captured by a cohort of 49 lay midwives from 1697 and 584 pregnant women carrying singletons in the second and third trimesters in rural Guatemala during routine screening. Additionally, we designed an mHealth system in Georgia for postpartum women to monitor and report their BP at home with 23 and 49 African American participants contributing to the Georgia I3 and Georgia IMPROVE projects, respectively. We developed a deep learning-based model which operates in two steps: LCD localization using the You Only Look Once (YOLO) object detection model and digit recognition using a convolutional neural network-based model capable of recognizing multiple digits. We applied color correction and thresholding techniques to minimize the impact of reflection and artifacts. Three experiments were conducted based on the devices used for training the digit recognition model. Overall, our results demonstrate that the device-specific model with transfer learning and the device independent model outperformed the device-specific model without transfer learning. The mean absolute error (MAE) of image transcription on held-out test datasets using the device-independent digit recognition were 1.2 and 0.8 mmHg for systolic and diastolic BP in the Georgia IMPROVE and 0.9 and 0.5 mmHg in Guatemala Set 2 datasets. The MAE, far below the FDA recommendation of 5 mmHg, makes the proposed automatic image transcription model suitable for general use when used with appropriate low-error BP devices.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000588","type":"journal-article","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T13:32:44Z","timestamp":1727875964000},"page":"e0000588","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automated image transcription for perinatal blood pressure monitoring using mobile health technology"],"prefix":"10.1371","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7750-0554","authenticated-orcid":true,"given":"Nasim","family":"Katebi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Whitney","family":"Bremer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tony","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Phan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamila","family":"Jeff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirkland","family":"Armstrong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paula","family":"Phabian-Millbrook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marissa","family":"Platner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimberly","family":"Carroll","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Banafsheh","family":"Shoai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Rohloff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheree L.","family":"Boulet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheryl G.","family":"Franklin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gari D.","family":"Clifford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"issue":"1","key":"pdig.0000588.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12884-021-03809-2","article-title":"Epidemiological trends of maternal hypertensive disorders of pregnancy at the global, regional, and national levels: a population-based study","volume":"21","author":"W Wang","year":"2021","journal-title":"BMC Pregnancy and Childbirth"},{"issue":"9","key":"pdig.0000588.ref002","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1016\/j.placenta.2014.06.375","article-title":"Placental pathology in early intrauterine growth restriction associated with maternal hypertension","volume":"35","author":"JHW Veerbeek","year":"2014","journal-title":"Placenta"},{"issue":"9516","key":"pdig.0000588.ref003","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1016\/S0140-6736(06)68397-9","article-title":"WHO analysis of cause of maternal death: a systematic review","volume":"367","author":"KS Khan","year":"2006","journal-title":"Lancet"},{"key":"pdig.0000588.ref004","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.3389\/fphys.2018.01771","article-title":"Genetic variants in preeclampsia: Lessons from studies in Latin-American populations","volume":"9","author":"RT Michita","year":"2018","journal-title":"Frontiers in Physiology"},{"issue":"17","key":"pdig.0000588.ref005","doi-asserted-by":"crossref","first-page":"585","DOI":"10.15585\/mmwr.mm7117a1","article-title":"Hypertensive disorders in pregnancy and mortality at delivery hospitalization\u2014United States, 2017-2019","volume":"71","author":"ND Ford","year":"2022","journal-title":"Morbidity and Mortality Weekly Report"},{"key":"pdig.0000588.ref006","article-title":"Severe Maternal Morbidity in Georgia, 2009-2020","author":"MR Kramer","year":"2023","journal-title":"Medical Care"},{"issue":"1","key":"pdig.0000588.ref007","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1038\/s41746-021-00486-5","article-title":"Mobile health strategies for blood pressure self-management in urban populations with digital barriers: systematic review and meta-analyses","volume":"4","author":"EC Khoong","year":"2021","journal-title":"NPJ Digital Medicine"},{"issue":"3","key":"pdig.0000588.ref008","doi-asserted-by":"crossref","first-page":"e23","DOI":"10.1161\/HYPERTENSIONAHA.120.15153","article-title":"Trends in hypertension-related cardiovascular mortality in the United States, 2000 to 2018","volume":"76","author":"L Rethy","year":"2020","journal-title":"Hypertension"},{"issue":"12","key":"pdig.0000588.ref009","doi-asserted-by":"crossref","first-page":"1190","DOI":"10.1001\/jama.2020.14545","article-title":"Trends in blood pressure control among US adults with hypertension, 1999-2000 to 2017-2018","volume":"324","author":"P Muntner","year":"2020","journal-title":"JAMA"},{"issue":"18","key":"pdig.0000588.ref010","doi-asserted-by":"crossref","first-page":"533","DOI":"10.15585\/mmwr.mm6918a1","article-title":"Prevalence of self-reported hypertension and antihypertensive medication use by county and rural-urban classification\u2014United States, 2017","volume":"69","author":"CM Samanic","year":"2020","journal-title":"Morbidity and Mortality Weekly Report"},{"issue":"1","key":"pdig.0000588.ref011","doi-asserted-by":"crossref","first-page":"1819052","DOI":"10.1080\/16549716.2020.1819052","article-title":"Utility of the three-delays model and its potential for supporting a solution-based approach to accessing intrapartum care in low-and middle-income countries: A qualitative evidence synthesis","volume":"13","author":"V Actis Danna","year":"2020","journal-title":"Global Health Action"},{"issue":"1","key":"pdig.0000588.ref012","doi-asserted-by":"crossref","first-page":"15","DOI":"10.4103\/0970-0218.106622","article-title":"Equipment errors: A prevalent cause for fallacy in blood pressure recording\u2014A point prevalence estimate from an Indian health university","volume":"38","author":"B Mishra","year":"2013","journal-title":"Indian Journal of Community Medicine: Official Publication of Indian Association of Preventive & Social Medicine"},{"issue":"2","key":"pdig.0000588.ref013","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1161\/HYPERTENSIONAHA.117.10295","article-title":"Accuracy of blood pressure measurement devices in pregnancy: A systematic review of validation studies","volume":"71","author":"NA Bello","year":"2018","journal-title":"Hypertension"},{"key":"pdig.0000588.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12978-018-0554-z","article-title":"mHealth intervention to improve the continuum of maternal and perinatal care in rural Guatemala: A pragmatic, randomized controlled feasibility trial","volume":"15","author":"B Martinez","year":"2018","journal-title":"Reproductive Health"},{"key":"pdig.0000588.ref015","doi-asserted-by":"crossref","unstructured":"Valderrama CE, Marzbanrad F, Stroux L, Martinez B, Hall-Clifford R, Liu C, Katebi N, Rohloff P, Clifford GD. Improving the quality of point of care diagnostics with real-time machine learning in low literacy LMIC settings. In: Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies; 2018. p. 1\u201311.","DOI":"10.1145\/3209811.3209815"},{"issue":"7-8","key":"pdig.0000588.ref016","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1080\/03091902.2016.1223196","article-title":"An mHealth monitoring system for traditional birth attendant-led antenatal risk assessment in rural Guatemala","volume":"40","author":"L Stroux","year":"2016","journal-title":"Journal of Medical Engineering & Technology"},{"key":"pdig.0000588.ref017","doi-asserted-by":"crossref","first-page":"543176","DOI":"10.3389\/frai.2021.543176","article-title":"CNN-based LCD transcription of blood pressure from a mobile phone camera","volume":"4","author":"SS Kulkarni","year":"2021","journal-title":"Frontiers in Artificial Intelligence"},{"key":"pdig.0000588.ref018","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 779\u201388.","DOI":"10.1109\/CVPR.2016.91"},{"issue":"3","key":"pdig.0000588.ref019","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/ajh\/hpz182","article-title":"Self-monitoring of blood pressure in patients with hypertension-related multi-morbidity: Systematic review and individual patient data meta-analysis","volume":"33","author":"JP Sheppard","journal-title":"American Journal of Hypertension"},{"issue":"22","key":"pdig.0000588.ref020","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1001\/jama.2013.281078","article-title":"Can mobile health technologies transform health care?","volume":"310","author":"SR Steinhubl","journal-title":"JAMA"},{"key":"pdig.0000588.ref021","first-page":"2","article-title":"Challenges in blood pressure self-measurement","author":"S Wagner","year":"2012","journal-title":"International Journal of Telemedicine and Applications"},{"key":"pdig.0000588.ref022","volume-title":"Journal of Health Informatics in Developing Countries","author":"R Hall-Clifford","year":"2017"},{"issue":"7","key":"pdig.0000588.ref023","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1109\/29.1643","article-title":"Experiments on neural net recognition of spoken and written text","volume":"36","author":"DJ Burr","year":"1988","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"pdig.0000588.ref024","article-title":"Multi-digit recognition using a space displacement neural network","volume":"4","author":"O Matan","year":"1991","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"pdig.0000588.ref025","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1109\/34.588017","article-title":"A lexicon driven approach to handwritten word recognition for real-time applications","volume":"19","author":"G Kim","year":"1997","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pdig.0000588.ref026","unstructured":"Bahlmann C, Haasdonk B, Burkhardt H. Online handwriting recognition with support vector machines\u2014a kernel approach. In: Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition; 2002. p. 49\u201354."},{"key":"pdig.0000588.ref027","doi-asserted-by":"crossref","unstructured":"Babu UR, Venkateswarlu Y, Chintha AK. Handwritten digit recognition using K-nearest neighbour classifier. In: 2014 World Congress on Computing and Communication Technologies; 2014. p. 60\u201365.","DOI":"10.1109\/WCCCT.2014.7"},{"key":"pdig.0000588.ref028","first-page":"1","article-title":"An efficient and improved scheme for handwritten digit recognition based on convolutional neural network","volume":"1","author":"S Ali","journal-title":"SN Applied Sciences"},{"key":"pdig.0000588.ref029","doi-asserted-by":"crossref","unstructured":"Leelasantiham A. A system for checking code numbers on a credit card and a paper of personal information. In: International Conference on Computer Technology and Development; 2009. Vol. 1, p. 455\u2013458.","DOI":"10.1109\/ICCTD.2009.152"},{"key":"pdig.0000588.ref030","unstructured":"Goodfellow IJ, Bulatov Y, Ibarz J, Arnoud S, Shet V. Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv Preprint arXiv:1312.6082; 2013."},{"key":"pdig.0000588.ref031","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10032-004-0138-z","article-title":"Camera-based analysis of text and documents: A survey","volume":"7","author":"J Liang","year":"2005","journal-title":"International Journal of Document Analysis and Recognition (IJDAR)"},{"key":"pdig.0000588.ref032","doi-asserted-by":"crossref","unstructured":"Smith R. An overview of the Tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007); 2007. Vol. 2, p. 629\u2013633.","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"pdig.0000588.ref033","unstructured":"Tesseract. Tesseract GitHub repository. GitHub repository; 2005. Available at: https:\/\/github.com\/tesseract-ocr\/tesseract."},{"key":"pdig.0000588.ref034","doi-asserted-by":"crossref","unstructured":"Mammeri A, Khiari E, Boukerche A. Road-sign text recognition architecture for intelligent transportation systems. In: 2014 IEEE 80th Vehicular Technology Conference (VTC2014-Fall); 2014. p. 1\u20135.","DOI":"10.1109\/VTCFall.2014.6966161"},{"key":"pdig.0000588.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2018\/7075814","article-title":"A deep learning approach of vehicle multitarget detection from traffic video","volume":"2018","author":"X Li","year":"2018","journal-title":"Journal of Advanced Transportation"},{"key":"pdig.0000588.ref036","doi-asserted-by":"crossref","unstructured":"Kannadaguli P. YOLO v4 based human detection system using aerial thermal imaging for UAV based surveillance applications. In: 2020 International Conference on Decision Aid Sciences and Application (DASA); 2020. p. 1213\u20131219.","DOI":"10.1109\/DASA51403.2020.9317198"},{"key":"pdig.0000588.ref037","doi-asserted-by":"crossref","first-page":"75385","DOI":"10.1109\/ACCESS.2022.3192034","article-title":"STBI-YOLO: A real-time object detection method for lung nodule recognition","volume":"10","author":"K Liu","year":"2022","journal-title":"IEEE Access"},{"key":"pdig.0000588.ref038","doi-asserted-by":"crossref","first-page":"105742","DOI":"10.1016\/j.compag.2020.105742","article-title":"Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments","volume":"178","author":"D Wu","year":"2020","journal-title":"Computers and Electronics in Agriculture"},{"key":"pdig.0000588.ref039","doi-asserted-by":"crossref","unstructured":"Huang Y, Yan Q, Li Y, Chen Y, Wang X, Gao L, Tang Z. A YOLO-based table detection method. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). 2019. p. 813\u2013818.","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"pdig.0000588.ref040","unstructured":"Lin T. LabelImg annotation tool. Available at: https:\/\/github.com\/heartexlabs\/labelImg."},{"key":"pdig.0000588.ref041","unstructured":"Kulkarni S, Katebi N, Clifford GD. BPimageTranscribe. GitHub repository. Available at: https:\/\/doi.org\/10.5281\/zenodo.4383306."},{"issue":"6","key":"pdig.0000588.ref042","doi-asserted-by":"crossref","first-page":"e0155677","DOI":"10.1371\/journal.pone.0155677","article-title":"How accurate are home blood pressure devices in use? A cross-sectional study","volume":"11","author":"M Ruzicka","year":"2016","journal-title":"PLoS One"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T13:32:58Z","timestamp":1727875978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000588"}},"subtitle":[],"editor":[{"given":"Esli","family":"Osmanlliu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000588","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.06.16.23291435","asserted-by":"object"}]},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]}}}