Probabilistic Logic Models and Their Application to Breast Cancer

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 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 to 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. Experiments show that the probabilistic model produced can not only match the predictions of a team of experts in the area, but also produce meaningful rules which output better calibrated probability values.

Bibtex

@InProceedings{corte-real-ilp17-lbp,
  author =    {J. Côrte-Real and I. Dutra and R. Rocha},
  title =     {{Probabilistic Logic Models and Their Application to Breast Cancer}},
  booktitle = {Proceedings of the 27th International Conference on Inductive 
               Logic Programming (ILP 2017) - Late-Breaking Papers},
  month =     {September},
  year =      {2017},
  address =   {Orléans, France},
}

Download Paper

PDF file