Decision support systems for personalized and participative radiation oncology

Abstract

A paradigm shift from current population based medicine to personalized and participative medicine is underway. This transition is being supported by the development of clinical decision support systems based on prediction models of treatment outcome. In radiation oncology, these models 'learn' using advanced and innovative information technologies (ideally in a distributed fashion - please watch the animation: http://youtu.be/ZDJFOxpwqEA) from all available/appropriate medical data (clinical, treatment, imaging, biological/genetic, etc.) to achieve the highest possible accuracy with respect to prediction of tumor response and normal tissue toxicity. In this position paper, we deliver an overview of the factors that are associated with outcome in radiation oncology and discuss the methodology behind the development of accurate prediction models, which is a multi-faceted process. Subsequent to initial development/validation and clinical introduction, decision support systems should be constantly re-evaluated (through quality assurance procedures) in different patient datasets in order to refine and re-optimize the models, ensuring the continuous utility of the models. In the reasonably near future, decision support systems will be fully integrated within the clinic, with data and knowledge being shared in a standardized, dynamic, and potentially global manner enabling truly personalized and participative medicine.

An architecture of Multiagent System (MAS) for healthcare Intelligent Decision Support System (IDSS)

“…An example; (1) in [19] was developing the DSS only in tertiary care use, (2) in [20] was developing the DSS also only in tertiary care use, (3) in [21] was developing the DSS only in secondary care use and many more as such as shown in Table 2. These means current decision making in healthcare is diagnosed based on a particular stage (primary care, secondary care, tertiary care or etc.).…”

Big data and precision medicine: challenges and strategies with healthcare data

“…In particular, clinical outcome and follow-up data are often not accessible due to heterogeneity stemming from the many institutions involved. On the other side, it is advertised that integrating all data and analyzing these data using methods from data science, one might be able to improve health care in terms of precision medicine, predictive modeling, clinical decision support and also comparative effectiveness research [26,43,50,61]. This advancement is not impeded by data science, but rather by compliance issues.…”

Defining the biological and clinical basis of radiomics

“…In particular, we discovered novel radiomic signature that improved clinical prognostic models, results some of which were also validated in independent data. We thereby demonstrated that radiomics has to be regarded 196 as a data science, following stringent statistical study designs, in order to fulfill its role as a clinical decision support system [66,67].…”

“…To integrate radiomic applications in future clinical cancer management, robust and secure infrastructure has to be developed, allowing storage of massive amounts of sensitive patient data, model development and validation, as well as transparent data and method sharing to foster collaborative research [98]. To facilitate collaborative research, novel concepts such as distributed and continuous learning could be valuable tools [66,99,100]. In particular, innovative and open source software, such as PyRadiomics for radiomic feature extraction (https://pyradiomics.readthedocs.io), the 3D Slicer suite for managing image data [101], and BraTumIA for automatic segmentation [102], can contribute in reproducing independent results in the growing radiomic research community.…”

“…2) Segmentation: Delineation or segmentation of the three dimensional tumor volume is the basis of extracting radiomic tumor imaging features, although historically features were also extracted from two dimensional slides [66][67][68]. Segmentation of tumors is usually performed on axial slices following the image acquisition of radiographic modalities.…”