On Applying Probabilistic Logic Programming to Breast Cancer Data

Joana Côrte-Real, Inês Dutra and Ricardo Rocha

September 2017


Abstract

Medical data is particularly interesting as a subject for relational data mining due to the complex interactions which exist between different en tities. 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 f or this task, since it makes it possible to combine the relational nature of this field with the ambiguity inherent in human interpretation of me dical imaging. This work presents a PILP setting for breast cancer data, where several clinical and demographic variables were collected retrospe ctively, and new probabilistic variables and rules reflecting domain knowledge were introduced. A PILP predictive model was built automatically f rom 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.

Bibtex

@InProceedings{corte-real-ilp17,
  author =    {J. Côrte-Real and I. Dutra and R. Rocha},
  title =     {{On Applying Probabilistic Logic Programming to Breast Cancer Data}},
  booktitle = {Proceedings of the 27th International Conference on Inductive Logic Programming (ILP 2017)},
  pages =     {},
  number =    {},
  series =    {LNAI},
  publisher = {Springer},
  editor =    {N. Lachiche and C. Vrain},
  month =     {September},
  year =      {2017},
  address =   {Orléans, France},
  note =      {To be published in 2018},
}

Download Paper

PDF file