On Applying Probabilistic Logic Programming to Breast Cancer Data
Medical data is particularly interesting as a subject for relational data mining due to the complex interactions which exist between different entities. Furthermore, the ambiguity of medical imaging causes interpretation to be complex and error-prone, and thus particularly amenable to improvement through automated decision support. Probabilistic Inductive Logic Programming (PILP) is a particularly well-suited tool for this task, since it makes it possible to combine the relational nature of this field with the ambiguity inherent in human interpretation of medical imaging. This work presents a PILP setting for breast cancer data, where several clinical and demographic variables were collected retrospectively, and new probabilistic variables and rules reflecting domain knowledge were introduced. A PILP predictive model was built automatically from this data and experiments show that it can not only match the predictions of a team of experts in the area, but also consistently reduce the error rate of malignancy prediction, when compared to other non-relational techniques.
This work was partially funded by the North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement, and through the European Regional Development Fund (ERDF) as part of project NanoSTIMA (NORTE-01-0145-FEDER-000016). Joana Côrte-Real was funded by the FCT grant SFRH/BD/52235/2013. The authors would like to thank Dr. Elizabeth Burnside for making the dataset used in this paper available to us.
- 3.Brancato, B., Crocetti, E., Bianchi, S., Catarzi, S., Risso, G.G., Bulgaresi, P., Piscioli, F., Scialpi, M., Ciatto, S., Houssami, N.: Accuracy of needle biopsy of breast lesions visible on ultrasound: audit of fine needle versus core needle biopsy in 3233 consecutive samplings with ascertained outcomes. Breast 21(4), 449–454 (2012)CrossRefGoogle Scholar
- 4.Burbank, F.: Stereotactic breast biopsy: comparison of 14- and 11-gauge mammotome probe performance and complication rates. Am. Surg. 63(11), 988–995 (1997)Google Scholar
- 6.Côrte-Real, J., Mantadelis, T., Dutra, I., Rocha, R., Burnside, E.: SkILL - a stochastic inductive logic learner. In: International Conference on Machine Learning and Applications, Miami, Florida, USA, December 2015Google Scholar
- 8.Davis, J., Burnside, E.S., Dutra, I.C., Page, D., Santos Costa, V.: Knowledge discovery from structured mammography reports using inductive logic programming. In: American Medical Informatics Association 2005 Annual Symposium, pp. 86–100 (2005)Google Scholar
- 9.Davis, J., Burnside, E.S., Dutra, I.C., Page, D., Ramakrishnan, R., Santos Costa, V., Shavlik, J.W.: View learning for statistical relational learning: with an application to mammography. In: Kaelbling, L.P., Saffiotti, A. (eds.) IJCAI 2005, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, 30 July–5 August 2005, pp. 677–683. Professional Book Center (2005)Google Scholar
- 10.De Raedt, L., Dries, A., Thon, I., Van den Broeck, G., Verbeke, M.: Inducing probabilistic relational rules from probabilistic examples. In: International Joint Conference on Artificial Intelligence, pp. 1835–1843. AAAI Press (2015)Google Scholar
- 12.D’Orsi, C.J., Bassett, L.W., Berg, W.A., et al.: BI-RADS®: Mammography, 4th edn. American College of Radiology Inc., Reston (2003)Google Scholar
- 13.Dutra, I., Nassif, H., Page, D., et al.: Integrating machine learning and physician knowledge to improve the accuracy of breast biopsy. In: AMIA Annual Symposium Proceedings, Washington, DC, pp. 349–355 (2011)Google Scholar
- 14.Gonçalves, A.V., Thuler, L.C., Kestelman, F.P., Carmo, P.A., Lima, C.F., Cipolotti, R.: Underestimation of malignancy of core needle biopsy for nonpalpable breast lesions. Rev. Bras. Ginecol. Obstet. 33(7), 123–131 (2011)Google Scholar
- 21.Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
- 22.Woods, R., Oliphant, L., Shinki, K., Page, D., Shavlik, J., Burnside, E.: Validation of results from knowledge discovery: mass density as a predictor of breast cancer. J. Digit. Imaging, 418–419 (2009)Google Scholar