Development of a Natural Language Processing Engine to Generate Bladder Cancer Pathology Data for Health Services Research
- PMID: 28916254
- PMCID: PMC5696035
- DOI: 10.1016/j.urology.2017.07.056
Development of a Natural Language Processing Engine to Generate Bladder Cancer Pathology Data for Health Services Research
Abstract
Objective: To take the first step toward assembling population-based cohorts of patients with bladder cancer with longitudinal pathology data, we developed and validated a natural language processing (NLP) engine that abstracts pathology data from full-text pathology reports.
Methods: Using 600 bladder pathology reports randomly selected from the Department of Veterans Affairs, we developed and validated an NLP engine to abstract data on histology, invasion (presence vs absence and depth), grade, the presence of muscularis propria, and the presence of carcinoma in situ. Our gold standard was based on an independent review of reports by 2 urologists, followed by adjudication. We assessed the NLP performance by calculating the accuracy, the positive predictive value, and the sensitivity. We subsequently applied the NLP engine to pathology reports from 10,725 patients with bladder cancer.
Results: When comparing the NLP output to the gold standard, NLP achieved the highest accuracy (0.98) for the presence vs the absence of carcinoma in situ. Accuracy for histology, invasion (presence vs absence), grade, and the presence of muscularis propria ranged from 0.83 to 0.96. The most challenging variable was depth of invasion (accuracy 0.68), with an acceptable positive predictive value for lamina propria (0.82) and for muscularis propria (0.87) invasion. The validated engine was capable of abstracting pathologic characteristics for 99% of the patients with bladder cancer.
Conclusion: NLP had high accuracy for 5 of 6 variables and abstracted data for the vast majority of the patients. This now allows for the assembly of population-based cohorts with longitudinal pathology data.
Published by Elsevier Inc.
Conflict of interest statement
Figures
![Figure 1](https://webcf.waybackmachine.org/web/20220408220705im_/https://www.ncbi.nlm.nih.gov/pmc/articles/instance/5696035/bin/nihms905699f1.gif)
Comment in
-
Editorial Comment.Urology. 2017 Dec;110:90-91. doi: 10.1016/j.urology.2017.07.057. Epub 2017 Oct 16. Urology. 2017. PMID: 29050642 No abstract available.
Similar articles
-
Automated Extraction of Grade, Stage, and Quality Information From Transurethral Resection of Bladder Tumor Pathology Reports Using Natural Language Processing.JCO Clin Cancer Inform. 2018 Dec;2:1-8. doi: 10.1200/CCI.17.00128. JCO Clin Cancer Inform. 2018. PMID: 30652586 Free PMC article.
-
A natural language processing program effectively extracts key pathologic findings from radical prostatectomy reports.J Endourol. 2014 Dec;28(12):1474-8. doi: 10.1089/end.2014.0221. J Endourol. 2014. PMID: 25211697
-
Automating the Capture of Structured Pathology Data for Prostate Cancer Clinical Care and Research.JCO Clin Cancer Inform. 2019 Jul;3:1-8. doi: 10.1200/CCI.18.00084. JCO Clin Cancer Inform. 2019. PMID: 31314550 Free PMC article.
-
Discerning tumor status from unstructured MRI reports--completeness of information in existing reports and utility of automated natural language processing.J Digit Imaging. 2010 Apr;23(2):119-32. doi: 10.1007/s10278-009-9215-7. Epub 2009 May 30. J Digit Imaging. 2010. PMID: 19484309 Free PMC article. Review.
-
Clinical Natural Language Processing in 2014: Foundational Methods Supporting Efficient Healthcare.Yearb Med Inform. 2015 Aug 13;10(1):194-8. doi: 10.15265/IY-2015-035. Yearb Med Inform. 2015. PMID: 26293868 Free PMC article. Review.
Cited by 11 articles
-
Automatic Classification of Cancer Pathology Reports: A Systematic Review.J Pathol Inform. 2022 Jan 20;13:100003. doi: 10.1016/j.jpi.2022.100003. eCollection 2022. J Pathol Inform. 2022. PMID: 35242443 Free PMC article.
-
Improving natural language information extraction from cancer pathology reports using transfer learning and zero-shot string similarity.JAMIA Open. 2021 Sep 30;4(3):ooab085. doi: 10.1093/jamiaopen/ooab085. eCollection 2021 Jul. JAMIA Open. 2021. PMID: 34604711 Free PMC article.
-
Partial Versus Complete Bacillus Calmette-Guérin Intravesical Therapy and Bladder Cancer Outcomes in High-risk Non-muscle-invasive Bladder Cancer: Is NIMBUS the Full Story?Eur Urol Open Sci. 2021 Feb 16;26:35-43. doi: 10.1016/j.euros.2021.01.009. eCollection 2021 Apr. Eur Urol Open Sci. 2021. PMID: 34337506 Free PMC article.
-
Natural language processing systems for pathology parsing in limited data environments with uncertainty estimation.JAMIA Open. 2020 Oct 14;3(3):431-438. doi: 10.1093/jamiaopen/ooaa029. eCollection 2020 Oct. JAMIA Open. 2020. PMID: 33381748 Free PMC article.
-
Natural Language Processing for Surveillance of Cervical and Anal Cancer and Precancer: Algorithm Development and Split-Validation Study.JMIR Med Inform. 2020 Nov 3;8(11):e20826. doi: 10.2196/20826. JMIR Med Inform. 2020. PMID: 32469840 Free PMC article.
Publication types
MeSH terms
Grant support
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical