{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:26:15Z","timestamp":1793917575057,"version":"4.8.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cancer Causes Control"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Real-world oncology data are essential for clinical research and precision cancer care. However, genomic biomarkers are often embedded in scanned, unstructured clinical documents requiring manual abstraction before becoming available in cancer registries, delaying real-world evidence generation. This study evaluated and compared three open-source optical character recognition (OCR) approaches, Tesseract, EasyOCR, and a hybrid implementation, to determine which best enables automated extraction of Oncotype DX recurrence scores and improves the timeliness and quality of real-world oncology data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We evaluated the feasibility of automated genomic data extraction using 675 Oncotype DX reports from a Midwestern U.S. health system. EasyOCR, Tesseract, and a hybrid OCR approach were used to extract recurrence scores from scanned reports. OCR-derived values were compared with manually abstracted scores and local cancer registry data. Performance was assessed using agreement, precision, recall, F1 score, and processing time. Multivariable logistic regression was performed to identify factors associated with discordance between registry-reported and manually abstracted scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The hybrid OCR approach demonstrated the highest performance, achieving 97% agreement with manual abstraction, precision of 0.997, recall of 0.972, and an F1 score of 0.984. Registry abstraction demonstrated comparable performance but required greater manual effort. Automated extraction substantially reduced processing time while maintaining high accuracy. Logistic regression showed registry discordance was largely independent of patient and tumor characteristics, with unknown progesterone receptor (PR) status as the only significant predictor.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Automated extraction of genomic biomarkers represents a scalable approach to reducing delays in cancer data availability. Earlier capture of genomic information may support cancer registry modernization and improve real-world evidence generation in precision oncology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s10552-026-02252-y","type":"journal-article","created":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T12:30:09Z","timestamp":1789907409000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the data latency gap: automated extraction of genomic biomarkers from unstructured clinical documents to support real-world oncology data"],"prefix":"10.1007","volume":"37","author":[{"given":"Qianyun","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikitha","family":"Vobugari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jane Y. C.","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Schelomo","family":"Marmor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,20]]},"reference":[{"key":"2252_CR1","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1038\/s41571-019-0167-7","volume":"16","author":"CM Booth","year":"2019","unstructured":"Booth CM, Karim S, Mackillop WJ (2019) Real-world data: towards achieving the achievable in cancer care. Nat Rev Clin Oncol 16:312\u2013325. https:\/\/doi.org\/10.1038\/s41571-019-0167-7","journal-title":"Nat Rev Clin Oncol"},{"key":"2252_CR2","unstructured":"(2020) Real-World Evidence. U.S. Food and Drug Administration"},{"key":"2252_CR3","unstructured":"U.S. Food and Drug Administration (2017) Use of Real-World Evidence to Support Regulatory Decision-Making for Medical Devices. U.S. Food and Drug Administration"},{"key":"2252_CR4","doi-asserted-by":"publisher","DOI":"10.2196\/51003","volume":"25","author":"J Chishtie","year":"2023","unstructured":"Chishtie J, Sapiro N, Wiebe N et al (2023) Use of Epic electronic health record system for health care research: scoping review. J Med Internet Res 25:e51003. https:\/\/doi.org\/10.2196\/51003","journal-title":"J Med Internet Res"},{"key":"2252_CR5","doi-asserted-by":"publisher","first-page":"287","DOI":"10.3322\/caac.21714","volume":"72","author":"LT Penberthy","year":"2022","unstructured":"Penberthy LT, Rivera DR, Lund JL et al (2022) An overview of real-world data sources for oncology and considerations for research. CA A Cancer J Clin 72:287\u2013300. https:\/\/doi.org\/10.3322\/caac.21714","journal-title":"CA A Cancer J Clin"},{"key":"2252_CR6","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1186\/s12874-022-01768-6","volume":"22","author":"F Liu","year":"2022","unstructured":"Liu F, Panagiotakos D (2022) Real-world data: a brief review of the methods, applications, challenges and opportunities. BMC Med Res Methodol 22:287. https:\/\/doi.org\/10.1186\/s12874-022-01768-6","journal-title":"BMC Med Res Methodol"},{"key":"2252_CR7","first-page":"135","volume":"41","author":"FP Boscoe","year":"2014","unstructured":"Boscoe FP (2014) Trends in reporting delay in United States central cancer registries. J Registry Manag 41:135\u2013138","journal-title":"J Registry Manag"},{"key":"2252_CR8","doi-asserted-by":"publisher","first-page":"5546","DOI":"10.1245\/s10434-024-15393-8","volume":"31","author":"BE Palis","year":"2024","unstructured":"Palis BE, Janczewski LM, Browner AE et al (2024) The National Cancer Database conforms to the standardized framework for registry and data quality. Ann Surg Oncol 31:5546\u20135559. https:\/\/doi.org\/10.1245\/s10434-024-15393-8","journal-title":"Ann Surg Oncol"},{"key":"2252_CR9","unstructured":"North American Association of Central Cancer Registries. https:\/\/www.naaccr.org\/resources-international-registries\/"},{"key":"2252_CR10","doi-asserted-by":"publisher","DOI":"10.1093\/jncimonographs\/lgu018","author":"HK Weir","year":"2014","unstructured":"Weir HK, Johnson CJ, Mariotto AB et al (2014) Evaluation of North American Association of Central Cancer Registries\u2019 (NAACCR) data for use in population-based cancer survival studies. JNCI Monogr. https:\/\/doi.org\/10.1093\/jncimonographs\/lgu018","journal-title":"JNCI Monogr"},{"key":"2252_CR11","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1158\/1055-9965.EPI-06-0167","volume":"15","author":"H Brenner","year":"2006","unstructured":"Brenner H, Hakulinen T (2006) Up-to-date estimates of cancer patient survival even with common latency in cancer registration. Cancer Epidemiol Biomarkers Prev 15:1727\u20131732. https:\/\/doi.org\/10.1158\/1055-9965.EPI-06-0167","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"2252_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/1478-7954-4-10","volume":"4","author":"G Tagliabue","year":"2006","unstructured":"Tagliabue G, Maghini A, Fabiano S et al (2006) Consistency and accuracy of diagnostic cancer codes generated by automated registration: comparison with manual registration. Popul Health Metr 4:10. https:\/\/doi.org\/10.1186\/1478-7954-4-10","journal-title":"Popul Health Metr"},{"key":"2252_CR13","first-page":"833","volume":"2015","author":"X Li","year":"2015","unstructured":"Li X, Hu G, Teng X, Xie G (2015) Building structured personal health records from photographs of printed medical records. AMIA Annu Symp Proc 2015:833\u2013842","journal-title":"AMIA Annu Symp Proc"},{"key":"2252_CR14","doi-asserted-by":"publisher","first-page":"16","DOI":"10.15265\/IY-2017-004","volume":"26","author":"CP Friedman","year":"2017","unstructured":"Friedman CP, Rubin JC, Sullivan KJ (2017) Toward an information infrastructure for global health improvement. Yearb Med Inform 26:16\u201323. https:\/\/doi.org\/10.15265\/IY-2017-004","journal-title":"Yearb Med Inform"},{"key":"2252_CR15","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djx187","author":"S Khozin","year":"2017","unstructured":"Khozin S, Blumenthal GM, Pazdur R (2017) Real-world data for clinical evidence generation in oncology. J Natl Cancer Inst. https:\/\/doi.org\/10.1093\/jnci\/djx187","journal-title":"J Natl Cancer Inst"},{"key":"2252_CR16","doi-asserted-by":"publisher","first-page":"e90","DOI":"10.1136\/amiajnl-2011-000182","volume":"19","author":"LV Rasmussen","year":"2012","unstructured":"Rasmussen LV, Peissig PL, McCarty CA, Starren J (2012) Development of an optical character recognition pipeline for handwritten form fields from an electronic health record. J Am Med Inform Assoc 19:e90\u2013e95. https:\/\/doi.org\/10.1136\/amiajnl-2011-000182","journal-title":"J Am Med Inform Assoc"},{"key":"2252_CR17","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1177\/17407745221093621","volume":"19","author":"J Hom","year":"2022","unstructured":"Hom J, Nikowitz J, Ottesen R, Niland JC (2022) Facilitating clinical research through automation: combining optical character recognition with natural language processing. Clin Trials 19:504\u2013511. https:\/\/doi.org\/10.1177\/17407745221093621","journal-title":"Clin Trials"},{"key":"2252_CR18","first-page":"58","volume":"79","author":"E Liette","year":"2008","unstructured":"Liette E, Meyers C, Olenik K (2008) Is document imaging the right choice for your organization? J AHIMA 79:58\u201360","journal-title":"J AHIMA"},{"key":"2252_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104302","volume":"144","author":"H Goodrum","year":"2020","unstructured":"Goodrum H, Roberts K, Bernstam EV (2020) Automatic classification of scanned electronic health record documents. Int J Med Inform 144:104302. https:\/\/doi.org\/10.1016\/j.ijmedinf.2020.104302","journal-title":"Int J Med Inform"},{"key":"2252_CR20","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.gie.2020.08.038","volume":"93","author":"SN Laique","year":"2021","unstructured":"Laique SN, Hayat U, Sarvepalli S et al (2021) Application of optical character recognition with natural language processing for large-scale quality metric data extraction in colonoscopy reports. Gastrointest Endosc 93:750\u2013757. https:\/\/doi.org\/10.1016\/j.gie.2020.08.038","journal-title":"Gastrointest Endosc"},{"key":"2252_CR21","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.22.00034","volume":"6","author":"SW Gray","year":"2022","unstructured":"Gray SW, Ottesen RA, Currey M et al (2022) Leveraging an informatics approach to identify an unmet clinical need for BRCA1\/2 testing among patients with ovarian cancer. JCO Clin Cancer Inform 6:e2200034. https:\/\/doi.org\/10.1200\/CCI.22.00034","journal-title":"JCO Clin Cancer Inform"},{"key":"2252_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.100933","volume":"5","author":"J Kefeli","year":"2024","unstructured":"Kefeli J, Tatonetti N (2024) TCGA-Reports: a machine-readable pathology report resource for benchmarking text-based AI models. Patterns (N Y) 5:100933. https:\/\/doi.org\/10.1016\/j.patter.2024.100933","journal-title":"Patterns (N Y)"},{"key":"2252_CR23","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.21.00137","volume":"6","author":"MJ Hassett","year":"2022","unstructured":"Hassett MJ, Cronin C, Tsou TC et al (2022) eSyM: an electronic health record-integrated patient-reported outcomes-based cancer symptom management program used by six diverse health systems. JCO Clin Cancer Inform 6:e2100137. https:\/\/doi.org\/10.1200\/CCI.21.00137","journal-title":"JCO Clin Cancer Inform"},{"key":"2252_CR24","volume-title":"Epic, Cerner growing EHR market share with increased hospital consolidation: KLAS","author":"H Landi","year":"2019","unstructured":"Landi H (2019) Epic, Cerner growing EHR market share with increased hospital consolidation: KLAS. FierceHealthcare"},{"key":"2252_CR25","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1056\/NEJMoa1804710","volume":"379","author":"JA Sparano","year":"2018","unstructured":"Sparano JA, Gray RJ, Makower DF et al (2018) Adjuvant chemotherapy guided by a 21-gene expression assay in breast cancer. N Engl J Med 379:111\u2013121. https:\/\/doi.org\/10.1056\/NEJMoa1804710","journal-title":"N Engl J Med"},{"key":"2252_CR26","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/ICDAR.2007.4376991","volume-title":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","author":"R Smith","year":"2007","unstructured":"Smith R (2007) An overview of the tesseract OCR engine. Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol 2. IEEE, Curitiba, pp 629\u2013633"},{"key":"2252_CR27","doi-asserted-by":"publisher","unstructured":"Baek Y, Lee B, Han D, et al (2019) Character region awareness for text detection. In: IEEE\/CVF computer society conference on computer vision and pattern recognition, Long Beach, pp 9357\u20139366. https:\/\/doi.org\/10.1109\/CVPR.2019.00959","DOI":"10.1109\/CVPR.2019.00959"},{"key":"2252_CR28","unstructured":"JaidedAI EasyOCR. GitHub repository. https:\/\/github.com\/JaidedAI\/EasyOCR\\"},{"key":"2252_CR29","unstructured":"El Yousfi M (2023) Introduction to EasyOCR. In: Medium. https:\/\/medium.com\/@mohamed5elyousfi\/-277e9c685578"},{"key":"2252_CR30","volume-title":"The Fourth Annual Test of OCR Accuracy","author":"S Rice","year":"1995","unstructured":"Rice S, Jenkins F, Nartker T (1995) The Fourth Annual Test of OCR Accuracy. Information Science Research Institute, University of Nevada, Las Vegas"},{"key":"2252_CR31","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-031-41734-4_7","volume-title":"Document analysis and recognition\u2014ICDAR 2023","author":"M Cuper","year":"2023","unstructured":"Cuper M, Van Dongen C, Koster T (2023) Unraveling confidence: examining confidence scores as proxy for OCR quality. In: Fink GA, Jain R, Kise K, Zanibbi R (eds) Document analysis and recognition\u2014ICDAR 2023. Springer Nature Switzerland, Cham, pp 104\u2013120"},{"key":"2252_CR32","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/3476887.3476888","volume-title":"The 6th international workshop on historical document imaging and processing","author":"C Neudecker","year":"2021","unstructured":"Neudecker C, Baierer K, Gerber M et al (2021) A survey of OCR evaluation tools and metrics. The 6th international workshop on historical document imaging and processing. ACM, Lausanne, pp 13\u201318"},{"key":"2252_CR33","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837\u2013845","journal-title":"Biometrics"},{"issue":"4","key":"2252_CR34","first-page":"153","volume":"49","author":"DE Rollison","year":"2022","unstructured":"Rollison DE, Levin GM, Warner JL et al (2022) Current and emerging informatics initiatives impactful to cancer registries. J Registry Manag. 49(4):153\u2013160","journal-title":"J Registry Manag."},{"key":"2252_CR35","doi-asserted-by":"publisher","DOI":"10.1093\/jncimonographs\/lgae024","author":"H-S Chen","year":"2024","unstructured":"Chen H-S, Negoita S, Schwartz S et al (2024) Toward real-time reporting of cancer incidence: methodology, pilot study, and SEER Program implementation. J Natl Cancer Inst Monogr. https:\/\/doi.org\/10.1093\/jncimonographs\/lgae024","journal-title":"J Natl Cancer Inst Monogr"},{"key":"2252_CR36","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1377\/hlthaff.2017.1579","volume":"37","author":"V Agarwala","year":"2018","unstructured":"Agarwala V, Khozin S, Singal G et al (2018) Real-world evidence in support of precision medicine: clinico-genomic cancer data as a case study. Health Aff (Millwood) 37:765\u2013772. https:\/\/doi.org\/10.1377\/hlthaff.2017.1579","journal-title":"Health Aff (Millwood)"}],"container-title":["Cancer Causes &amp; Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10552-026-02252-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10552-026-02252-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10552-026-02252-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:05:38Z","timestamp":1793916338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10552-026-02252-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,20]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["2252"],"URL":"https:\/\/doi.org\/10.1007\/s10552-026-02252-y","relation":{},"ISSN":["0957-5243","1573-7225"],"issn-type":[{"value":"0957-5243","type":"print"},{"value":"1573-7225","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,20]]},"assertion":[{"value":"26 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"165"}}