ABSTRACT
Radiotherapy outcomes are determined by complex interactions among treatment, anatomical, and patient-related variables. A key component of radiation oncology research is to predict, at the time of treatment planning, or during the course of fractionated radiation treatment, the probability of tumor eradication and normal tissue risks for the type of treatment being considered for that particular patient (Torres-Roca & Stevens 2008). Outcomes in radiotherapy are usually characterized by tumor control probability (TCP) and the surrounding normal tissue complication probability (NTCP) (Webb 2001; Steel 2002). Traditionally, these outcomes are modeled using information about the dose distribution and the fractionation (Moissenko et al. 2005). However, it is recognized that radiation response may also be affected by multiple clinical prognostic factors (Marks 2002); more recently, inherited genetic variations have been suggested as playing an important role in radiosensitivity (West et al. 2007; Alsner et al. 2008). Therefore, recent approaches have utilized data-driven models incorporating advanced informatics tools in which dose-volume metrics are mixed with other patient or disease-based prognostic factors to improve outcomes prediction (El Naqa 2012). Accurate prediction of treatment outcomes would provide clinicians with better tools for informed decisionmaking about expected benefits versus anticipated risks.
