PDF herunterladen
Appl Clin Inform 2021; 12(01): 170-178
DOI: 10.1055/s-0041-1723024
Research Article

Extracting Medical Information from Paper COVID-19 Assessment Forms

Colin G. White-Dzuro   *
1   Vanderbilt University School of Medicine, Nashville, Tennessee, United States
,
Jacob D. Schultz‡   *
1   Vanderbilt University School of Medicine, Nashville, Tennessee, United States
,
Cheng Ye
2   Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States
,
Joseph R. Coco
2   Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States
,
Janet M. Myers
3   Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, United States
,
Claude Shackelford
3   Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, United States
,
S. Trent Rosenbloom
1   Vanderbilt University School of Medicine, Nashville, Tennessee, United States
2   Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States
,
Daniel Fabbri
2   Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States
› Institutsangaben Funding None.
› Weitere Informationen
   Lizenzen und Reprints

Abstract

Objective This study examines the validity of optical mark recognition, a novel user interface, and crowdsourced data validation to rapidly digitize and extract data from paper COVID-19 assessment forms at a large medical center.

Methods An optical mark recognition/optical character recognition (OMR/OCR) system was developed to identify fields that were selected on 2,814 paper assessment forms, each with 141 fields which were used to assess potential COVID-19 infections. A novel user interface (UI) displayed mirrored forms showing the scanned assessment forms with OMR results superimposed on the left and an editable web form on the right to improve ease of data validation. Crowdsourced participants validated the results of the OMR system. Overall error rate and time taken to validate were calculated. A subset of forms was validated by multiple participants to calculate agreement between participants.

Results The OMR/OCR tools correctly extracted data from scanned forms fields with an average accuracy of 70% and median accuracy of 78% when the OMR/OCR results were compared with the results from crowd validation. Scanned forms were crowd-validated at a mean rate of 157 seconds per document and a volume of approximately 108 documents per day. A randomly selected subset of documents was reviewed by multiple participants, producing an interobserver agreement of 97% for documents when narrative-text fields were included and 98% when only Boolean and multiple-choice fields were considered.

Conclusion Due to the COVID-19 pandemic, it may be challenging for health care workers wearing personal protective equipment to interact with electronic health records. The combination of OMR/OCR technology, a novel UI, and crowdsourcing data-validation processes allowed for the efficient extraction of a large volume of paper medical documents produced during the COVID-19 pandemic.

Keywords

COVID-19 - data processing - optical mark recognition - optical character recognition - data creation and storage - crowdsourcing - medical form extraction

Protection of Human and Animal Subjects

None.


* Authors contributed equally to this study.


Supplementary Material



Publikationsverlauf

Eingereicht: 10. September 2020

Angenommen: 25. Dezember 2020

Artikel online veröffentlicht:
10. März 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Patel PD, Cobb J, Wright D. et al. Rapid development of telehealth capabilities within pediatric patient portal infrastructure for COVID-19 care: barriers, solutions, results. J Am Med Inform Assoc 2020; 27 (07) 1116-1120
    CrossrefPubMedGoogle Scholar
  • 2 Kim SI, Lee JY. Walk-through screening center for COVID-19: an accessible and efficient screening system in a pandemic situation. J Korean Med Sci 2020; 35 (15) e154
    CrossrefPubMedGoogle Scholar
  • 3 Islam MS, Rahman KM, Sun Y. et al. Current knowledge of COVID-19 and infection prevention and control strategies in healthcare settings: a global analysis. Infect Control Hosp Epidemiol 2020; 41 (10) 1196-1206
    CrossrefPubMedGoogle Scholar
  • 4 Ferioli M, Cisternino C, Leo V, Pisani L, Palange P, Nava S. Protecting healthcare workers from SARS-CoV-2 infection: practical indications. Eur Respir Rev 2020; 29 (155) 200068
    CrossrefPubMedGoogle Scholar
  • 5 Downs SM, Carroll AE, Anand V, Biondich PG. Human and system errors, using adaptive turnaround documents to capture data in a busy practice. AMIA Annu Symp Proc 2005; 2005: 211-215
    PubMedGoogle Scholar
  • 6 Collen MF. Clinical research databases--a historical review. J Med Syst 1990; 14 (06) 323-344
    CrossrefPubMedGoogle Scholar
  • 7 Shah NH, Tenenbaum JD. The coming age of data-driven medicine: translational bioinformatics' next frontier. J Am Med Inform Assoc 2012; 19 (e1): e2-e4
    CrossrefPubMedGoogle Scholar
  • 8 Bhargava BK, McDonald CJ, Rivera HP, McCarthy LJ, Blevins L. Development and Implementation of a Computerized Clinical Laboratory System. Lab Med 1976; 7 (12) 28-37
    CrossrefPubMedGoogle Scholar
  • 9 Tafti AP, Baghaie A, Assefi M, Arabnia HR, Yu Z, Peissig P. OCR as a Service: An Experimental Evaluation of Google Docs OCR, Tesseract, ABBYY FineReader, and Transym. In: Bebis G, Boyle R, Parvin B. et al., eds. Advances in Visual Computing. Lecture Notes in Computer Science. Springer International Publishing; 2016: 735-746
    Google Scholar
  • 10 Biondich PG, Overhage JM, Dexter PR, Downs SM, Lemmon L, McDonald CJ. A modern optical character recognition system in a real world clinical setting: some accuracy and feasibility observations. Proc AMIA Symp 2002; 56-60
    PubMedGoogle Scholar
  • 11 Biondich PG, Anand V, Downs SM, McDonald CJ. Using adaptive turnaround documents to electronically acquire structured data in clinical settings. AMIA Annu Symp Proc 2003; 2003: 86-90
    PubMedGoogle Scholar
  • 12 Shiffman RN, Brandt CA, Freeman BG. Transition to a computer-based record using scannable, structured encounter forms. Arch Pediatr Adolesc Med 1997; 151 (12) 1247-1253
    CrossrefPubMedGoogle Scholar
  • 13 Titlestad G. Use of document image processing in cancer registration: how and why?. Medinfo 1995; 8 (Pt 1): 462
    PubMedGoogle Scholar
  • 14 Bussmann H, Wester CW, Ndwapi N. et al. Hybrid data capture approach for monitoring patients on highly active antiretroviral therapy (HAART) in urban Botswana. Bull World Health Organ Int J Public Health 2006; 842: 127-131
    CrossrefPubMedGoogle Scholar
  • 15 Bergeron BP. Optical mark recognition. Tallying information from filled-in ‘bubbles’. Postgrad Med 1998; 104 (02) 23-25
    CrossrefPubMedGoogle Scholar
  • 16 Shiffman R, Brandt C, Hoffman M, Wiig W, Fernandes L. SEURAT: scanned entry of structured data for a pediatric health maintenance record system. Accessed April 18, 2020 at: https://www.researchgate.net/publication/25901454_SEURAT_Scanned_Entry_of_Structured_Data_for_a_Pediatric_Health_Maintenance_Record_System
    PubMedGoogle Scholar
  • 17 Loke SC, Kasmiran KA, Haron SA. A new method of mark detection for software-based optical mark recognition. PLoS One 2018; 13 (11) e0206420
    CrossrefPubMedGoogle Scholar
  • 18 Chouvatut V, Prathan S. The flexible and adaptive X-mark detection for the simple answer sheets. 2014 International Computer Science and Engineering Conference. Accessed 2014 at: https://ieeexplore.ieee.org/document/6978236
    PubMedGoogle Scholar
  • 19 Sattayakawee N. Test scoring for non-optical grid answer sheet based on projection profile method. Int J Inf Educ Technol 2013; 273-277
    PubMedGoogle Scholar
  • 20 Rakesh S, Atal K, Arora A. Cost effective optical mark reader. Int J Comput Sci Artif Intell. Accessed April 18, 2020 at: https://scholar.google.com/scholar_lookup?journal=International+Journal+of+Computer+Science+and+Artificial+Intelligence&title=Cost+effective+optical+mark+reader&author=S+Rakesh&author=K+Atal&author=A+Arora&volume=3&publication_year=2013&pages=44&
    PubMedGoogle Scholar
  • 21 Bradski G. The Open CV Library. Dr Dobbs J Softw Tools. Accessed 2000 at: https://www.drdobbs.com/open-source/the-opencv-library/184404319
    PubMedGoogle Scholar
  • 22 Ye C, Coco J, Epishova A. et al. A crowdsourcing framework for medical data sets. AMIA Jt Summits Transl Sci Proc 2018; 2017: 273-280
    PubMedGoogle Scholar
  • 23 Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG. Research electronic data capture (REDCap)--a metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inform 2009; 42 (02) 377-381
    CrossrefPubMedGoogle Scholar
  • 24 Harris PA, Taylor R, Minor BL. et al; REDCap Consortium. The REDCap consortium: building an international community of software platform partners. J Biomed Inform 2019; 95: 103208
    CrossrefPubMedGoogle Scholar
  • 25 van Doremalen N, Bushmaker T, Morris DH. et al. Aerosol and surface stability of SARS-CoV-2 as compared with SARS-CoV-1. N Engl J Med 2020; 382 (16) 1564-1567
    CrossrefPubMedGoogle Scholar
  • 26 Popescu S. Roadblocks to infection prevention efforts in health care: SARS-CoV-2/COVID-19 response. Disaster Med Public Health Prep 2020; 14 (04) 538-540
    CrossrefPubMedGoogle Scholar
  • 27 Anand V, Carroll AE, Downs SM. Automated primary care screening in pediatric waiting rooms. Pediatrics 2012; 129 (05) e1275-e1281
    CrossrefPubMedGoogle Scholar
  • 28 Fifolt M, Blackburn J, Rhodes DJ. et al. Man versus machine: comparing double data entry and optical mark recognition for processing CAHPS survey data. Qual Manag Health Care 2017; 26 (03) 131-135
    CrossrefPubMedGoogle Scholar
  • 29 Leung GM, Leung K. Crowdsourcing data to mitigate epidemics. Lancet Digit Health 2020; 2 (04) e156-e157
    CrossrefPubMedGoogle Scholar
  • 30 Spasic I, Nenadic G. Clinical text data in machine learning: systematic review. JMIR Med Inform 2020; 8 (03) e17984
    CrossrefPubMedGoogle Scholar
  • 31 Kawado M, Hinotsu S, Matsuyama Y, Yamaguchi T, Hashimoto S, Ohashi Y. A comparison of error detection rates between the reading aloud method and the double data entry method. Control Clin Trials 2003; 24 (05) 560-569
    CrossrefPubMedGoogle Scholar
  • 32 Paulsen A, Overgaard S, Lauritsen JM. Quality of data entry using single entry, double entry and automated forms processing--an example based on a study of patient-reported outcomes. PLoS One 2012; 7 (04) e35087
    CrossrefPubMedGoogle Scholar