Abstract
Breast cancer patients often discontinue their long-term treatments, such as hormone therapy, increasing the risk of cancer recurrence. These discontinuations may be caused by adverse patient-centered outcomes (PCOs) due to hormonal drug side effects or other factors. PCOs are not detectable through laboratory tests, and are sparsely documented in electronic health records. Thus, there is a need to explore complementary sources of information for PCOs associated with breast cancer treatments. Social media is a promising resource, but extracting true PCOs from it first requires the accurate detection of real breast cancer patients. We describe a natural language processing (NLP) pipeline for automatically detecting breast cancer patients from Twitter based on their self-reports. The pipeline uses breast cancer-related keywords to collect streaming data from Twitter, applies NLP patterns to filter out noisy posts, and then employs a machine learning classifier trained using manually-annotated data (n = 5,019) for distinguishing firsthand self-reports of breast cancer from other tweets. A classifier based on bidirectional encoder representations from transformers (BERT) showed human-like performance and achieved F\(_1\)-score of 0.857 (inter-annotator agreement: 0.845; Cohen’s kappa) for the positive class, considerably outperforming the next best classifier—a recurrent neural network with bidirectional long short-term memory (F\(_1\)-score: 0.670). Qualitative analyses of posts from automatically-detected users revealed discussions about side effects, non-adherence and mental health conditions, illustrating the feasibility of our social media-based approach for studying breast cancer related PCOs from a large population.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
A major different between PCOs and PROs is that the former may depend on the interpretation of the caregiver, while the latter is not.
- 2.
We intend to use information from tweets labeled as F in our future studies.
References
Attai, D.J., Cowher, M.S., Al-Hamadani, M., Schoger, J.M., Staley, A.C., Landercasper, J.: Twitter social media is an effective tool for breast cancer patient education and support: patient-reported outcomes by survey. J. Med. Internet Res. 17(7), e188 (2015)
Banerjee, I., Bozkurt, S., Caswell-Jin, J.L., Kurian, A.W., Rubin, D.L.: Natural language processing approaches to detect the timeline of metastatic recurrence of breast cancer. JCO Clin. Cancer Inform. 3, 1–12 (2019)
Bottorff, J.L., Struik, L.L., Bissell, L.J., Graham, R., Stevens, J., Richardson, C.G.: A social media approach to inform youth about breast cancer and smoking: an exploratory descriptive study. Collegian 21(2), 159–168 (2014)
Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37–46 (1960)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
van Herk-Sukel, M.P.P., van de Poll-Franse, L.V., Voogd, A.C., Nieuwenhuijzen, G.A.P., Coebergh, J.W.W., Herings, R.M.C.: Half of breast cancer patients discontinue tamoxifen and any endocrine treatment before the end of the recommended treatment period of 5 years: a population-based analysis. Breast Cancer Res. Treat. 122(3), 843–851 (2010). https://doi.org/10.1007/s10549-009-0724-3
McCowan, C., et al.: Cohort study examining tamoxifen adherence and its relationship to mortality in women with breast cancer. British J. Cancer 99(11), 1763–1768 (2008). https://doi.org/10.1038/sj.bjc.6604758
Milata, J.L., Otte, J.L., Carpenter, J.S.: Oral endocrine therapy nonadherence, adverse effects, decisional support, and decisional needs in women with breast cancer. Cancer Nurs. 41(1), E9–E18 (2018). https://doi.org/10.1097/NCC.0000000000000430
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Sarker, A., Chandrashekar, P., Magge, A., Cai, H., Klein, A., Gonzalez, G.: Discovering cohorts of pregnant women from social media for safety surveillance and analysis. J. Med. Internet Res. 19(10), e361 (2017)
Sarker, A., DeRoos, A., Perrone, J.: Mining social media for prescription medication abuse monitoring: a review and proposal for a data-centric framework. J. Am. Med. Inform. Assoc. 27(2), 315–329 (2019). https://doi.org/10.1093/jamia/ocz162
Sarker, A., Gonzalez, G.: A corpus for mining drug-related knowledge from Twitter chatter: language models and their utilities. Data Brief 10, 122–131 (2017)
Viera, A.J., Garrett, J.M., et al.: Understanding interobserver agreement: the kappa statistic. Fam. Med. 37(5), 360–363 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Al-Garadi, M.A. et al. (2020). Automatic Breast Cancer Cohort Detection from Social Media for Studying Factors Affecting Patient-Centered Outcomes. In: Michalowski, M., Moskovitch, R. (eds) Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science(), vol 12299. Springer, Cham. https://doi.org/10.1007/978-3-030-59137-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-59137-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59136-6
Online ISBN: 978-3-030-59137-3
eBook Packages: Computer ScienceComputer Science (R0)