CxCaDSS: A Web-Based Clinical Decision Support System for Cervical Cancer

Abstract

Abstract-Data from countries with well-organized screening programs and cancer registries indicate that the vast majority of participants who developed cervical cancer could be explained as underestimation of cases that had at least one abnormal Pap test. Nowadays, there are ancillary molecular biology techniques available that provide important information related to cervical cancer and the HPV natural history, including DNA micro-arrays identifying HPV subtypes, mRNA techniques such as nucleic acid based amplification or flow cytometry identifying E6/E7 oncogenes, and immunocytochemistry techniques such as overexpression of p16. However, each one of these techniques has its own performance, advantages and limitations, thus a combinatorial approach via artificial intelligence methods could exploit the benefits of each method and produce more accurate results. In this paper we present a novel web-based clinical decision support system and its integration with underlying artificial neural networks, for the combination of the results of classic and ancillary techniques in order to increase the accuracy of diagnosis and thus identify women at true risk of developing cervical cancer. The presented system follows the MVC approach enabling it to easily adapt to any underlying data and structure to support clinical decisions for other domains as well.

An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions

“…Recent achievements have shown that it is also of great use to combine different neural networks into recommender systems. There are many works which employed neural networks to improve the recommendation in the domain of recommender systems [3][4][5][6][7] and in the context of web-based decisions [8][9][10][11][12]. The success of these recommendation approaches based on neural networks demonstrates its capability.…”

Bayesian Networks to Support the Management of Patients with ASCUS/LSIL Pap Tests

“…Additionally, future studies should investigate the integration in the BN model of other demographic and medical history data such as age, births or vaccination against HPV among others. This risk assessment model was built as a web app (developed in the Java language using WEKA [16]) and was integrated into the previous constructed and presented webbased information system [8], serving as a decision support system to physicians and medical researchers for the management of new cases or the follow up of existing cases with abnormal Pap tests.…”

“…Since 2010, our team has developed an intelligent clinical decision support system (CDSS), based on Artificial Neural Networks (ANNs), for personalised CxCa diagnosis and prognosis [7]. Moreover, we developed an information technology (IT) system integrating the developed ANNs available as a web-based CDSS for CxCa [8]. This IT system is capable to support many individual users, therefore it can be simultaneously used by researchers, physicians and medical laboratories worldwide.…”

Markov Logic Based Inference Engine for CDSS

“…An inventive method for evaluation of the material's choice can be utilized as a possible part of an inference engine for an expert system in selection of material [17][18][19][20]. Since, experience plays an immense role in the material choice.…”

“…Since, experience plays an immense role in the material choice. The person who is experienced in the materials engineering field, it is observed that he will always prefer choosing the materials which he knows better and reject all other possibilities of choice, excluding and neglecting the new materials and loosing, in this manner, although the other choices might be more sound, both technically and economically [18]. In any expert system, the inference engine is the most important portion that performs the mechanism of "the thinking" by depending upon the contents of the knowledge base.…”