Big Data in radiation therapy: challenges and opportunities

Abstract

Data collected and generated by radiation oncology can be classified by the Volume, Variety, Velocity and Veracity (4Vs) of Big Data because they are spread across different care providers and not easily shared owing to patient privacy protection. The magnitude of the 4Vs is substantial in oncology, especially owing to imaging modalities and unclear data definitions. To create useful models ideally all data of all care providers are understood and learned from; however, this presents challenges in the guise of poor data quality, patient privacy concerns, geographical spread, interoperability and large volume. In radiation oncology, there are many efforts to collect data for research and innovation purposes. Clinical trials are the gold standard when proving any hypothesis that directly affects the patient. Collecting data in registries with strict predefined rules is also a common approach to find answers. A third approach is to develop data stores that can be used by modern machine learning techniques to provide new insights or answer hypotheses. We believe all three approaches have their strengths and weaknesses, but they should all strive to create Findable, Accessible, Interoperable, Reusable (FAIR) data. To learn from these data, we need distributed learning techniques, sending machine learning algorithms to FAIR data stores around the world, learning from trial data, registries and routine clinical data rather than trying to centralize all data. To improve and personalize medicine, rapid learning platforms must be able to process FAIR “Big Data” to evaluate current clinical practice and to guide further innovation.

Better be prepared

“…These changes were observed in well-nourished subjects, and the magnitude is consistent with clinical paradigms [72]. Especially in older patients, bed rest related to hospital stay results in a diminished ability to perform basic activities of daily life, like transfers and walking [73][74][75]. The loss of independent physical functioning is a common side effect of hospitalization and is also called hospitalization-associated disability [35].…”

“…Second, the readiness for change and willingness to share data should be increased. Lustberg et al [73] reported that the barriers for technological innovations and data-sharing are not of technological or ethical nature; however, barriers might be a lack of resources, expertise, and willingness to share data of health care professionals and researchers [73]. The absence of willingness to share data results from an ego-centered belief; the feeling of competition between institutes and not allowing comparison of performances with each other [73].…”

“…Lustberg et al [73] reported that the barriers for technological innovations and data-sharing are not of technological or ethical nature; however, barriers might be a lack of resources, expertise, and willingness to share data of health care professionals and researchers [73]. The absence of willingness to share data results from an ego-centered belief; the feeling of competition between institutes and not allowing comparison of performances with each other [73]. Therefore, it is recommended that professionals working in the field of perioperative care align on the readiness to invest in resources to build FAIR-databases, build-up expertise, and move from an ego-centered system towards an eco-centered system in which they take social responsibility to enhance data-management to improve patient outcomes.…”

Radiation Oncology in the Era of Big Data and Machine Learning for Precision Medicine

“…Big data has characterized by four V's: volume, variety, velocity and veracity [3]. In radiation oncology, data can be categorized as "Big Data" because (a) the use of dataintensive imaging modalities (volume), (b) the imaging archives are growing rapidly (velocity), (c) there is an increasing amount of imaging and diagnostic modalities available (variety), and (d) interpretation and quality differs between care providers (veracity) [4]. The radiation oncologists are overwhelmed with scientific literature, rapidly evolving treatment techniques, and the exponentially increasing amount of clinical data [5].…”

Data at Scale

“…Very often, those systems and / or data formats might not be interoperable between each other's. No matter, what the source of clinical data is, data fragmentation represents one of the biggest issues when dealing with clinical data in general [1]. Data fragmentation occurs when a collection of data in memory is broken up into many pieces that are not close together.…”