OBJECTIVE: Structured data on mammographic findings are difficult to obtain without manual review. We developed and evaluated a rule-based natural language processing (NLP) system to extract mammographic findings from free-text mammography reports. MATERIALS AND METHODS: The NLP system extracted four mammographic findings: mass, calcification, asymmetry, and architectural distortion, using a dictionary look-up method on 93,705 mammography reports from Group Health. Status annotations and anatomical location annotation were associated to each NLP detected finding through association rules. After excluding negated, uncertain, and historical findings, affirmative mentions of detected findings were summarized. Confidence flags were developed to denote reports with highly confident NLP results and reports with possible NLP errors. A random sample of 100 reports was manually abstracted to evaluate the accuracy of the system. RESULTS: The NLP system correctly coded 96-99 out of our sample of 100 reports depending on findings. Measures of sensitivity, specificity and negative predictive values exceeded 0.92 for all findings. Positive predictive values were relatively low for some findings due to their low prevalence. DISCUSSION: Our NLP system was implemented entirely in SAS Base, which makes it portable and easy to implement. It performed reasonably well with multiple applications, such as using confidence flags as a filter to improve the efficiency of manual review. Refinements of library and association rules, and testing on more diverse samples may further improve its performance. CONCLUSION: Our NLP system successfully extracts clinically useful information from mammography reports. Moreover, SAS is a feasible platform for implementing NLP algorithms.
OBJECTIVE: Structured data on mammographic findings are difficult to obtain without manual review. We developed and evaluated a rule-based natural language processing (NLP) system to extract mammographic findings from free-text mammography reports. MATERIALS AND METHODS: The NLP system extracted four mammographic findings: mass, calcification, asymmetry, and architectural distortion, using a dictionary look-up method on 93,705 mammography reports from Group Health. Status annotations and anatomical location annotation were associated to each NLP detected finding through association rules. After excluding negated, uncertain, and historical findings, affirmative mentions of detected findings were summarized. Confidence flags were developed to denote reports with highly confident NLP results and reports with possible NLP errors. A random sample of 100 reports was manually abstracted to evaluate the accuracy of the system. RESULTS: The NLP system correctly coded 96-99 out of our sample of 100 reports depending on findings. Measures of sensitivity, specificity and negative predictive values exceeded 0.92 for all findings. Positive predictive values were relatively low for some findings due to their low prevalence. DISCUSSION: Our NLP system was implemented entirely in SAS Base, which makes it portable and easy to implement. It performed reasonably well with multiple applications, such as using confidence flags as a filter to improve the efficiency of manual review. Refinements of library and association rules, and testing on more diverse samples may further improve its performance. CONCLUSION: Our NLP system successfully extracts clinically useful information from mammography reports. Moreover, SAS is a feasible platform for implementing NLP algorithms.
Authors: David S Carrell; Scott Halgrim; Diem-Thy Tran; Diana S M Buist; Jessica Chubak; Wendy W Chapman; Guergana Savova Journal: Am J Epidemiol Date: 2014-01-30 Impact factor: 4.897
Authors: J M H Timmers; A L M Verbeek; J IntHout; R M Pijnappel; M J M Broeders; G J den Heeten Journal: Eur Radiol Date: 2013-04-18 Impact factor: 5.315
Authors: Aruna Venkatesan; Philip Chu; Karla Kerlikowske; Edward A Sickles; Rebecca Smith-Bindman Journal: Radiology Date: 2009-01-21 Impact factor: 11.105
Authors: Justin A Strauss; Chun R Chao; Marilyn L Kwan; Syed A Ahmed; Joanne E Schottinger; Virginia P Quinn Journal: J Am Med Inform Assoc Date: 2012-07-21 Impact factor: 4.497
Authors: Zexian Zeng; Xiaoyu Li; Sasa Espino; Ankita Roy; Kristen Kitsch; Susan Clare; Seema Khan; Yuan Luo Journal: AMIA Annu Symp Proc Date: 2018-04-16
Authors: Steffani R Bailey; John D Heintzman; Miguel Marino; Megan J Hoopes; Brigit A Hatch; Rachel Gold; Stuart C Cowburn; Christine A Nelson; Heather E Angier; Jennifer E DeVoe Journal: Am J Prev Med Date: 2016-08-10 Impact factor: 5.043
Authors: Selen Bozkurt; Francisco Gimenez; Elizabeth S Burnside; Kemal H Gulkesen; Daniel L Rubin Journal: J Biomed Inform Date: 2016-07-04 Impact factor: 6.317