Heath Goodrum1, Kirk Roberts1, Elmer V Bernstam2. 1. School of Biomedical Informatics, The University of Texas Health Science Center at Houston, TX, United States. 2. School of Biomedical Informatics, The University of Texas Health Science Center at Houston, TX, United States; Division of General Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at Houston, TX, United States. Electronic address: Elmer.V.Bernstam@uth.tmc.edu.
Abstract
OBJECTIVES: Electronic Health Records (EHRs) contain scanned documents from a variety of sources such as identification cards, radiology reports, clinical correspondence, and many other document types. We describe the distribution of scanned documents at one health institution and describe the design and evaluation of a system to categorize documents into clinically relevant and non-clinically relevant categories as well as further sub-classifications. Our objective is to demonstrate that text classification systems can accurately classify scanned documents. METHODS: We extracted text using Optical Character Recognition (OCR). We then created and evaluated multiple text classification machine learning models, including both "bag of words" and deep learning approaches. We evaluated the system on three different levels of classification using both the entire document as input, as well as the individual pages of the document. Finally, we compared the effects of different text processing methods. RESULTS: A deep learning model using ClinicalBERT performed best. This model distinguished between clinically-relevant documents and not clinically-relevant documents with an accuracy of 0.973; between intermediate sub-classifications with an accuracy of 0.949; and between individual classes with an accuracy of 0.913. DISCUSSION: Within the EHR, some document categories such as "external medical records" may contain hundreds of scanned pages without clear document boundaries. Without further sub-classification, clinicians must view every page or risk missing clinically-relevant information. Machine learning can automatically classify these scanned documents to reduce clinician burden. CONCLUSION: Using machine learning applied to OCR-extracted text has the potential to accurately identify clinically-relevant scanned content within EHRs.
OBJECTIVES: Electronic Health Records (EHRs) contain scanned documents from a variety of sources such as identification cards, radiology reports, clinical correspondence, and many other document types. We describe the distribution of scanned documents at one health institution and describe the design and evaluation of a system to categorize documents into clinically relevant and non-clinically relevant categories as well as further sub-classifications. Our objective is to demonstrate that text classification systems can accurately classify scanned documents. METHODS: We extracted text using Optical Character Recognition (OCR). We then created and evaluated multiple text classification machine learning models, including both "bag of words" and deep learning approaches. We evaluated the system on three different levels of classification using both the entire document as input, as well as the individual pages of the document. Finally, we compared the effects of different text processing methods. RESULTS: A deep learning model using ClinicalBERT performed best. This model distinguished between clinically-relevant documents and not clinically-relevant documents with an accuracy of 0.973; between intermediate sub-classifications with an accuracy of 0.949; and between individual classes with an accuracy of 0.913. DISCUSSION: Within the EHR, some document categories such as "external medical records" may contain hundreds of scanned pages without clear document boundaries. Without further sub-classification, clinicians must view every page or risk missing clinically-relevant information. Machine learning can automatically classify these scanned documents to reduce clinician burden. CONCLUSION: Using machine learning applied to OCR-extracted text has the potential to accurately identify clinically-relevant scanned content within EHRs.
Authors: Asia Friedman; Jesse C Crosson; Jenna Howard; Elizabeth C Clark; Maria Pellerano; Ben-Tzion Karsh; Benjamin Crabtree; Carlos Roberto Jaén; Deborah J Cohen Journal: J Am Med Inform Assoc Date: 2013-07-31 Impact factor: 4.497
Authors: Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun Journal: Nature Date: 2017-01-25 Impact factor: 49.962
Authors: Alistair E W Johnson; Tom J Pollard; Lu Shen; Li-Wei H Lehman; Mengling Feng; Mohammad Ghassemi; Benjamin Moody; Peter Szolovits; Leo Anthony Celi; Roger G Mark Journal: Sci Data Date: 2016-05-24 Impact factor: 6.444
Authors: Amy G Feldman; Susan Moore; Sheana Bull; Megan A Morris; Kumanan Wilson; Cameron Bell; Margaret M Collins; Kathryn M Denize; Allison Kempe Journal: JMIR Form Res Date: 2022-01-13