A text-mining approach to obtain detailed treatment information from free-text fields in population-based cancer registries: A study of non-small cell lung cancer in California

• Published in: PloS one Vol. 14; no. 2; p. e0212454
• Main Authors: Maguire, Frances B., Morris, Cyllene R., Parikh-Patel, Arti, Cress, Rosemary D., Keegan, Theresa H. M., Li, Chin-Shang, Lin, Patrick S., Kizer, Kenneth W.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 22.02.2019; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Antineoplastic Agents - therapeutic use; Artificial intelligence; Bevacizumab; California; Cancer; Cancer research; Cancer therapies; Cancer treatment; Carcinoma, Non-Small-Cell Lung - drug therapy; Care and treatment; Chemotherapy; Chronic illnesses; Computer and Information Sciences; Data Collection - statistics & numerical data; Data mining; Data Mining - methods; Data Mining - statistics & numerical data; Data processing; Dosage and administration; Electronic health records; Electronic Health Records - statistics & numerical data; Epidemiology; Female; Health sciences; Hematology; Humans; Identification; Informatics; Lung cancer; Lung diseases; Lung Neoplasms - drug therapy; Male; Medical diagnosis; Medical records; Medicine; Medicine and Health Sciences; Mining industry; Natural language processing; Non-small cell lung cancer; Non-small cell lung carcinoma; Nursing schools; Oncology; Patients; Pemetrexed; Perl; Physical Sciences; Population; Population-based studies; Public health; Registries - statistics & numerical data; Research and Analysis Methods; Respiratory system agents; Small cell lung cancer; Software; Studies; California; Sacramento California; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0212454

Population-based cancer registries have treatment information for all patients making them an excellent resource for population-level monitoring. However, specific treatment details, such as drug names, are contained in a free-text format that is difficult to process and summarize. We assessed the accuracy and efficiency of a text-mining algorithm to identify systemic treatments for lung cancer from free-text fields in the California Cancer Registry. The algorithm used Perl regular expressions in SAS 9.4 to search for treatments in 24,845 free-text records associated with 17,310 patients in California diagnosed with stage IV non-small cell lung cancer between 2012 and 2014. Our algorithm categorized treatments into six groups that align with National Comprehensive Cancer Network guidelines. We compared results to a manual review (gold standard) of the same records. Percent agreement ranged from 91.1% to 99.4%. Ranges for other measures were 0.71-0.92 (Kappa), 74.3%-97.3% (sensitivity), 92.4%-99.8% (specificity), 60.4%-96.4% (positive predictive value), and 92.9%-99.9% (negative predictive value). The text-mining algorithm used one-sixth of the time required for manual review. SAS-based text mining of free-text data can accurately detect systemic treatments administered to patients and save considerable time compared to manual review, maximizing the utility of the extant information in population-based cancer registries for comparative effectiveness research.