DESIREE - A web-based software ecosystem for the personalized, collaborative and multidisciplinary management of primary breast cancer

Authors: Nekane Larburu Rubio Naiara Muro Amuchastegui Mónica Arrúe Gabaráin Roberto Álvarez Sánchez Jon Kerexeta Sarriegi

Date: 09.11.2018


Abstract

Breast cancer is the most common cancer in women worldwide, with around 1.7 million new cases every year, and it is a complex disease. Each case is usually discussed in multidisciplinary teams or committees, called breast units. They are composed by oncologists, surgeons, psychologists and other specialist, and they use to have very limited time, around 3 to 10 minutes per patient, to make a treatment decision. Some cases may be quite «easy», but 10-20% of the cases are not so clear - what we called «grey areas», and they may not be supported by clinical guidelines, which are the standards used by clinicians to make treatment decisions. Therefore, we need tools to support clinicians in their decision making process. For that DESIREE, the system presented in this demo, is composed by three main components: (i) an image based breast and tumour characterization tool, (ii) a predictive model after breast conservative therapy and radio-biological model, and (iii) a clinical decision support system with three main components: a guideline based CDSS, which implements various international and local guidelines; a similarity based CDSS, where its possible to explore given treatments to closest patients, and the most significant variables they share with the patient to treat; and the experience based CDSS, which processes all information from previous cases and generates new knowledge, augmenting the guidelines. All these are supported by DESIMS (i.e. DESiree Information Management System), a Security and Access Control module and an image system for image and models visualization.

BIB_text

@Article {
title = {DESIREE - A web-based software ecosystem for the personalized, collaborative and multidisciplinary management of primary breast cancer},
pages = {8531099},
keywds = {
Breast Cancer, Decision Support Systems, Clinical, Guidlenes CPGs
}
abstract = {

Breast cancer is the most common cancer in women worldwide, with around 1.7 million new cases every year, and it is a complex disease. Each case is usually discussed in multidisciplinary teams or committees, called breast units. They are composed by oncologists, surgeons, psychologists and other specialist, and they use to have very limited time, around 3 to 10 minutes per patient, to make a treatment decision. Some cases may be quite «easy», but 10-20% of the cases are not so clear - what we called «grey areas», and they may not be supported by clinical guidelines, which are the standards used by clinicians to make treatment decisions. Therefore, we need tools to support clinicians in their decision making process. For that DESIREE, the system presented in this demo, is composed by three main components: (i) an image based breast and tumour characterization tool, (ii) a predictive model after breast conservative therapy and radio-biological model, and (iii) a clinical decision support system with three main components: a guideline based CDSS, which implements various international and local guidelines; a similarity based CDSS, where its possible to explore given treatments to closest patients, and the most significant variables they share with the patient to treat; and the experience based CDSS, which processes all information from previous cases and generates new knowledge, augmenting the guidelines. All these are supported by DESIMS (i.e. DESiree Information Management System), a Security and Access Control module and an image system for image and models visualization.


}
isbn = {978-153864294-8},
doi = {10.1109/HealthCom.2018.8531099},
date = {2018-11-09},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

Zorrotzaurreko Erribera 2, Deusto,
48014 Bilbao (Spain)

close overlay

Behavioral advertising cookies are necessary to load this content

Accept behavioral advertising cookies