Bayesian networks to support the management of patients with ASCUS/LSIL pap tests

In the majority of cases, cervical cancer (CxCa) develops as a result of underestimated abnormalities in the Pap test. Nowadays, there are ancillary molecular biology techniques providing important information related to CxCa and the Human Papillomavirus (HPV) natural history, including HPV DNA test, HPV mRNA tests and immunocytochemistry tests. However, these techniques have their own performance, advantages and limitations, thus a combinatorial approach via computational intelligence methods could exploit the benefits of each method and produce more accurate results. In this paper we present a risk assessment model based on a Bayesian Network which, by combining the results of Pap test and ancillary tests, may identify women at true risk of developing cervical cancer and support the management of patients with ASCUS or LSIL cytology. The model, following the paradigm of other implemented systems, can be integrated into existing platforms and be available on mobile terminals for anytime/anyplace medical consultation.

[1]  Tassos Tagaris,et al.  CxCaDSS: A Web-Based Clinical Decision Support System for Cervical Cancer , 2015 .

[2]  Nir Friedman,et al.  Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning , 2009 .

[3]  A. Spathis,et al.  Identification of Women for Referral to Colposcopy by Neural Networks: A Preliminary Study Based on LBC and Molecular Biomarkers , 2012, Journal of biomedicine & biotechnology.

[4]  Richard Scheines,et al.  Causation, Prediction, and Search, Second Edition , 2000, Adaptive computation and machine learning.

[5]  A. Spathis,et al.  Clinical performance of human papillomavirus E6, E7 mRNA flow cytometric assay compared to human papillomavirus DNA typing. , 2011, Analytical and quantitative cytology and histology.

[6]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[7]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[8]  Petros Karakitsos,et al.  A preliminary study of the potential of tree classifiers in triage of high-grade squamous intraepithelial lesions. , 2011, Analytical and quantitative cytology and histology.

[9]  Joakim Dillner,et al.  Overview of human papillomavirus-based and other novel options for cervical cancer screening in developed and developing countries. , 2008, Vaccine.

[10]  A. Prentza,et al.  A Communication Platform for Tele-monitoring and Tele-management of Type 1 Diabetes , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[11]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .

[12]  P. Spirtes,et al.  An Algorithm for Fast Recovery of Sparse Causal Graphs , 1991 .

[13]  A. Lie,et al.  Performance of Human Papillomavirus DNA and mRNA Testing Strategies for Women with and without Cervical Neoplasia , 2009, Journal of Clinical Microbiology.

[14]  Panagiotis Bountris,et al.  An Intelligent Clinical Decision Support System for Patient-Specific Predictions to Improve Cervical Intraepithelial Neoplasia Detection , 2014, BioMed research international.

[15]  J. Dungan.  Efficacy of HPV DNA Testing With Cytology Triage and/or Repeat HPV DNA Testing in Primary Cervical Cancer Screening , 2009 .