The big data effort in radiation oncology: Data mining or data farming?

Global Workforce and Access: Demand, Education, Quality

There has long existed a substantial disparity in access to radiotherapy globally. This issue has only been exacerbated as the growing disparity of cancer incidence between high-income countries (HIC) and low and middle-income countries (LMICs) widens, with a pronounced increase in cancer cases in LMICs. Even within HICs, iniquities within local communities may lead to a lack of access to care. Due to these trends, it is imperative to find solutions to narrow global disparities. This requires the engagement of a diverse cohort of stakeholders, including working professionals, non-governmental organizations, nonprofits, professional societies, academic and training institutions, and industry. This review brings together a diverse group of experts to highlight critical areas that could help reduce the current global disparities in radiation oncology. Advancements in technology and treatment, such as artificial intelligence, brachytherapy, hypofractionation, and digital networks, in combination with implementation science and novel funding mechanisms, offer means for increasing access to care and education globally. Common themes across sections reveal how utilizing these new innovations and strengthening collaborative efforts among stakeholders can help improve access to care globally while setting the framework for the next generation of innovations.

Modelling radiobiology

Radiotherapy has played an essential role in cancer treatment for over a century, and remains one of the best-studied methods of cancer treatment. Because of its close links with the physical sciences, it has been the subject of extensive quantitative mathematical modelling, but a complete understanding of the mechanisms of radiotherapy has remained elusive. In part this is because of the complexity and range of scales involved in radiotherapy-from physical radiation interactions occurring over nanometres to evolution of patient responses over months and years. This review presents the current status and ongoing research in modelling radiotherapy responses across these scales, including basic physical mechanisms of DNA damage, the immediate biological responses this triggers, and genetic- and patient-level determinants of response. Finally, some of the major challenges in this field and potential avenues for future improvements are also discussed.

A joint physics and radiobiology DREAM team vision - Towards better response prediction models to advance radiotherapy

Radiotherapy developed empirically through experience balancing tumour control and normal tissue toxicities. Early simple mathematical models formalized this practical knowledge and enabled effective cancer treatment to date. Remarkable advances in technology, computing, and experimental biology now create opportunities to incorporate this knowledge into enhanced computational models. The ESTRO DREAM (Dose Response, Experiment, Analysis, Modelling) workshop brought together experts across disciplines to pursue the vision of personalized radiotherapy for optimal outcomes through advanced modelling. The ultimate vision is leveraging quantitative models dynamically during therapy to ultimately achieve truly adaptive and biologically guided radiotherapy at the population as well as individual patient-based levels. This requires the generation of models that inform response-based adaptations, individually optimized delivery and enable biological monitoring to provide decision support to clinicians. The goal is expanding to models that can drive the realization of personalized therapy for optimal outcomes. This position paper provides their propositions that describe how innovations in biology, physics, mathematics, and data science including AI could inform models and improve predictions. It consolidates the DREAM team's consensus on scientific priorities and organizational requirements. Scientifically, it stresses the need for rigorous, multifaceted model development, comprehensive validation and clinical applicability and significance. Organizationally, it reinforces the prerequisites of interdisciplinary research and collaboration between physicians, medical physicists, radiobiologists, and computational scientists throughout model development. Solely by a shared understanding of clinical needs, biological mechanisms, and computational methods, more informed models can be created. Future research environment and support must facilitate this integrative method of operation across multiple disciplines.

Perceptions on and roadblocks to implementation of standardized nomenclature in radiation oncology: A survey from TG-263U1

PURPOSE

AAPM Task Group No. 263U1 (Update to Report No. 263 - Standardizing Nomenclatures in Radiation Oncology) disseminated a survey to receive feedback on utilization, gaps, and means to facilitate further adoption.

METHODS

The survey was created by TG-263U1 members to solicit feedback from physicists, dosimetrists, and physicians working in radiation oncology. Questions on the adoption of the TG-263 standard were coupled with demographic information, such as clinical role, place of primary employment (e.g., private hospital, academic center), and size of institution. The survey was emailed to all AAPM, AAMD, and ASTRO members.

RESULTS

The survey received 463 responses with 310 completed survey responses used for analysis, of whom most had the clinical role of medical physicist (73%) and the majority were from the United States (83%). There were 83% of respondents who indicated that they believe that having a nomenclature standard is important or very important and 61% had adopted all or portions of TG-263 in their clinics. For those yet to adopt TG-263, the staffing and implementation efforts were the main cause for delaying adoption. Fewer respondents had trouble adopting TG-263 for organs at risk (29%) versus target (44%) nomenclature. Common themes in written feedback were lack of physician support and available resources, especially in vendor systems, to facilitate adoption.

CONCLUSIONS

While there is strong support and belief in the benefit of standardized nomenclature, the widespread adoption of TG-263 has been hindered by the effort needed by staff for implementation.  Feedback from the survey is being utilized to drive the focus of the update efforts and create tools to facilitate easier adoption of TG-263.

Operational Ontology for Oncology (O3): A Professional Society-Based, Multistakeholder, Consensus-Driven Informatics Standard Supporting Clinical and Research Use of Real-World Data From Patients Treated for Cancer

PURPOSE

The ongoing lack of data standardization severely undermines the potential for automated learning from the vast amount of information routinely archived in electronic health records (EHRs), radiation oncology information systems, treatment planning systems, and other cancer care and outcomes databases. We sought to create a standardized ontology for clinical data, social determinants of health, and other radiation oncology concepts and interrelationships.

METHODS AND MATERIALS

The American Association of Physicists in Medicine's Big Data Science Committee was initiated in July 2019 to explore common ground from the stakeholders' collective experience of issues that typically compromise the formation of large inter- and intra-institutional databases from EHRs. The Big Data Science Committee adopted an iterative, cyclical approach to engaging stakeholders beyond its membership to optimize the integration of diverse perspectives from the community.

RESULTS

We developed the Operational Ontology for Oncology (O3), which identified 42 key elements, 359 attributes, 144 value sets, and 155 relationships ranked in relative importance of clinical significance, likelihood of availability in EHRs, and the ability to modify routine clinical processes to permit aggregation. Recommendations are provided for best use and development of the O3 to 4 constituencies: device manufacturers, centers of clinical care, researchers, and professional societies.

CONCLUSIONS

O3 is designed to extend and interoperate with existing global infrastructure and data science standards. The implementation of these recommendations will lower the barriers for aggregation of information that could be used to create large, representative, findable, accessible, interoperable, and reusable data sets to support the scientific objectives of grant programs. The construction of comprehensive "real-world" data sets and application of advanced analytical techniques, including artificial intelligence, holds the potential to revolutionize patient management and improve outcomes by leveraging increased access to information derived from larger, more representative data sets.

A Phase II Study of Optimized Individualized Adaptive Radiotherapy for Hepatocellular Carcinoma

PURPOSE

We hypothesized that optimizing the utility of stereotactic body radiotherapy (SBRT) based on the individual patient's probability for tumor control and risk of liver injury would decrease toxicity without sacrificing local control in patients with impaired liver function or tumors not amenable to thermal ablation.

PATIENTS AND METHODS

Patients with Child-Pugh (CP) A to B7 liver function with aggregate tumor size >3.5 cm, or CP ≥ B8 with any size tumor were prospectively enrolled on an Institutional Review Board-approved phase II clinical trial to undergo SBRT with baseline and midtreatment dose optimization using a quantitative, individualized utility-based analysis. Primary endpoints were change in CP score of ≥2 points within 6 months and local control. Protocol-treated patients were compared with patients receiving conventional SBRT at another cancer center using overlap weighting.

RESULTS

A total of 56 patients with 80 treated tumors were analyzed with a median follow-up of 11.2 months. Two-year cumulative incidence of local progression was 6.4% [95% confidence interval (CI, 2.4-13.4)]. Twenty-one percent of patients experienced treatment-related toxicity within 6 months, which is similar to the rate for SBRT in patients with CP A liver function. An analysis using overlap weighting revealed similar local control [HR, 0.69; 95% CI (0.25-1.91); P = 0.48] and decreased toxicity [OR, 0.26; 95% CI (0.07-0.99); P = 0.048] compared with conventional SBRT.

CONCLUSIONS

Treatment of individuals with impaired liver function or tumors not amenable to thermal ablation with a treatment paradigm designed to optimize utility may decrease treatment-related toxicity while maintaining tumor control.

Infrastructure tools to support an effective Radiation Oncology Learning Health System

PURPOSE

Radiation Oncology Learning Health System (RO-LHS) is a promising approach to improve the quality of care by integrating clinical, dosimetry, treatment delivery, research data in real-time. This paper describes a novel set of tools to support the development of a RO-LHS and the current challenges they can address.

METHODS

We present a knowledge graph-based approach to map radiotherapy data from clinical databases to an ontology-based data repository using FAIR concepts. This strategy ensures that the data are easily discoverable, accessible, and can be used by other clinical decision support systems. It allows for visualization, presentation, and data analyses of valuable information to identify trends and patterns in patient outcomes. We designed a search engine that utilizes ontology-based keyword searching, synonym-based term matching that leverages the hierarchical nature of ontologies to retrieve patient records based on parent and children classes, connects to the Bioportal database for relevant clinical attributes retrieval. To identify similar patients, a method involving text corpus creation and vector embedding models (Word2Vec, Doc2Vec, GloVe, and FastText) are employed, using cosine similarity and distance metrics.

RESULTS

The data pipeline and tool were tested with 1660 patient clinical and dosimetry records resulting in 504 180 RDF (Resource Description Framework) tuples and visualized data relationships using graph-based representations. Patient similarity analysis using embedding models showed that the Word2Vec model had the highest mean cosine similarity, while the GloVe model exhibited more compact embeddings with lower Euclidean and Manhattan distances.

CONCLUSIONS

The framework and tools described support the development of a RO-LHS. By integrating diverse data sources and facilitating data discovery and analysis, they contribute to continuous learning and improvement in patient care. The tools enhance the quality of care by enabling the identification of cohorts, clinical decision support, and the development of clinical studies and machine learning programs in radiation oncology.

Patients with progression of spinal metastases who present to the clinic have better outcomes compared to those who present to the emergency department

BACKGROUND

As cancer therapies have improved, spinal metastases are increasingly common. Resulting complications have a significant impact on patient's quality of life. Optimal methods of surveillance and avoidance of neurologic deficits are understudied. This study compares the clinical course of patients who initially presented to the emergency department (ED) versus a multidisciplinary spine oncology clinic and who underwent stereotactic body radiation therapy (SBRT) secondary to progression/presentation of metastatic spine disease.

METHODS

We performed a retrospective analysis of a prospectively maintained database of adult oncologic patients who underwent spinal SBRT at a single hospital from 2010 to 2021. Descriptive statistics and survival analyses were performed.

RESULTS

We identified 498 spinal radiographic treatment sites in 390 patients. Of these patients, 118 (30.3%) presented to the ED. Patients presenting to the ED compared to the clinic had significantly more severe spinal compression (52.5% vs. 11.7%; p < 0.0001), severe pain (28.8% vs. 10.3%; p < 0.0001), weakness (24.5% vs. 4.5%; p < 0.0001), and difficulty walking (24.5% vs. 4.5%; p < 0.0001). Patients who presented to the ED compared to the clinic were significantly more likely to have surgical intervention followed by SBRT (55.4% vs. 15.3%; p < 0.0001) compared to SBRT alone. Patients who presented to the ED compared to the clinic had a significantly quicker interval to distant spine progression (5.1 ± 6.5 vs. 9.1 ± 10.2 months; p = 0.004), systemic progression (5.1 ± 7.2 vs. 9.2 ± 10.7 months; p < 0.0001), and worse overall survival (9.3 ± 10.0 vs. 14.3 ± 13.7 months; p = 0.002).

CONCLUSION

The establishment of multidisciplinary spine oncology clinics is an opportunity to potentially allow for earlier, more data-driven treatment of their spinal metastatic disease.

[Real world data in radiotherapy: A data farming project by Unitrad]

The aim of the data farming project by the Unitrad group is to produce and use large quantities of structured real-life data throughout radiotherapy treatment. Starting in 2016, target real world data were selected at expert consensus conferences and regularly updated, then captured in MOSAIQ© as the patient was treated. For each partner institution, the data was then stored in a relational database, then extracted and used by researchers to create real world knowledge. This production was carried out in a multicentre, coordinated fashion. When necessary, the raw data was shared according to the research projects, in compliance with regulations. Feedack was provided at each stage, enabling the system to evolve flexibly and rapidly, using the "agile" method. This work, which is constantly evolving, has led to the creation of health data warehouses focused on data of interest in radiotherapy, and the publication of numerous academic studies. It forms part of the wider context of the exploitation of real-life data in cancerology. Unitrad data farming is a collaborative project for creating knowledge from real-life radiotherapy data, based on an active network of clinicians and researchers.

(Common) Data Elements in Radiation Oncology: A Systematic Literature Review

PURPOSE

Structured medical data documentation is highly relevant in a data-driven discipline such as radiation oncology. Defined (common) data elements (CDEs) can be used to record data in clinical trials, health records, or computer systems for improved standardization and data exchange. The International Society for Radiation Oncology Informatics initiated a project for a scientific literature analysis of defined data elements for structured documentation in radiation oncology.

METHODS

We performed a systematic literature review on both PubMed and Scopus to analyze publications relevant to the utilization of specified data elements for the documentation of radiation therapy (RT)-related information. Relevant publications were retrieved as full-text and searched for published data elements. Finally, the extracted data elements were quantitatively analyzed and classified.

RESULTS

We found a total of 452 publications, of which 46 were considered relevant for structured data documentation. Twenty-nine publications addressed defined RT-specific data elements, of which 12 publications provided data elements. Only two publications focused on data elements in radiation oncology. The 29 analyzed publications were heterogeneous regarding the subject and usage of the defined data elements, and different concepts/terms for defined data elements were used.

CONCLUSION

The literature about structured data documentation in radiation oncology using defined data elements is scarce. There is a need for a comprehensive list of RT-specific CDEs the radio-oncologic community can rely on. As it has been done in other medical fields, establishing such a list would be of great value for clinical practice and research as it would promote interoperability and standardization.

Developing a Data and Analytics Platform to Enable a Breast Cancer Learning Health System at a Regional Cancer Center

PURPOSE

This study documents the creation of automated, longitudinal, and prospective data and analytics platform for breast cancer at a regional cancer center. This platform combines principles of data warehousing with natural language processing (NLP) to provide the integrated, timely, meaningful, high-quality, and actionable data required to establish a learning health system.

METHODS

Data from six hospital information systems and one external data source were integrated on a nightly basis by automated extract/transform/load jobs. Free-text clinical documentation was processed using a commercial NLP engine.

RESULTS

The platform contains 141 data elements of 7,019 patients with newly diagnosed breast cancer who received care at our regional cancer center from January 1, 2014, to June 3, 2022. Daily updating of the database takes an average of 56 minutes. Evaluation of the tuning of NLP jobs found overall high performance, with an F1 of 1.0 for 19 variables, with a further 16 variables with an F1 of > 0.95.

CONCLUSION

This study describes how data warehousing combined with NLP can be used to create a prospective data and analytics platform to enable a learning health system. Although upfront time investment required to create the platform was considerable, now that it has been developed, daily data processing is completed automatically in less than an hour.

Machine Learning Model of Emergency Department Use for Patients Undergoing Treatment for Head and Neck Cancer Using Comprehensive Multifactor Electronic Health Records

PURPOSE

To use a hybrid method, combining statistical profiling, machine learning (ML), and clinical evaluation to predict emergency department (ED) visits among patients with head and neck cancer undergoing radiotherapy.

MATERIALS AND METHODS

Patients with head and neck cancer treated with radiation therapy from 2015 to 2019 were identified using electronic health record data. Records from 60 days before 90 days after treatment were analyzed. Statistical profiling and ML were used to create a predictive model for ED visits during or after radiation therapy. A comprehensive set of variables were studied. Multiple ML models were developed including extreme gradient-boosted decision tree and generalized logistic regression with comparison of multiple predictive performance metrics.

RESULTS

Of the 1,355 patients studied, 13% had an ED visit during or after treatment. Our hybrid methodology enabled evidence-based winnowing of candidate features from 141 to 11 with clinically applicable, evidence-based thresholds. Extreme gradient boosting had the highest area under the curve (0.81 ± 0.06) with a sensitivity of 0.89 ± 0.10 and exceeded generalized logistic regression (area under the curve 0.64 ± 0.02). Significant predictors of ED visits during treatment included increasingly complex opioid use, number of prior ED visits, tumor volume, rate of change of blood urea nitrogen, total bilirubin, body mass index, and distance from hospital.

CONCLUSION

Our approach combining bootstrapped statistical profiling and ML importance analysis supported integration of clinician input to identify a distilled set of phenotypical characteristics for developing ML models predicting which patients undergoing head and neck cancer radiation therapy were at risk for ED visits.

A Deep-Learning Error Detection System in Radiation Therapy

Delivering radiation therapy based on erroneous or corrupted treatment plan data has previously and unfortunately resulted in severe, sometimes grave patient harm. Aiming to prevent such harm and improve safety in radiation therapy treatment, this work introduces a novel, yet intuitive algorithm for strategically structuring the complex and unstructured data typical of modern treatment plans so their treatment sites may automatically be verified with deep-learning architectures. The proposed algorithm utilizes geometric and dose plan parameters to represent each plan's data as a heat map to feed a deep-learning classifier that will predict the plan's treatment site. Once it is returned by the classifier, a plan's predicted site can be compared to its documented intended site, and a warning raised should the two differ. Using real head-neck, breast, and prostate treatment plan data retrieved at two hospitals in the United States, the algorithm is evaluated by observing the accuracy of convolutional neural networks (ConvNets) in correctly classifying the structured heat map data. Many well-known ConvNet architectures are tested, and ResNet-18 performs the best with a testing accuracy of 97.8% and 0.979 F-1 score. Clearly, the heat maps generated by the proposed algorithm, despite using only a few of the many available plan parameters, retain enough information for correct treatment site classification. The simple construction and ease of interpretation make the heat maps an attractive choice for classification and error detection.

Artificial Intelligence for Radiation Oncology Applications Using Public Datasets

Artificial intelligence (AI) has exceptional potential to positively impact the field of radiation oncology. However, large curated datasets - often involving imaging data and corresponding annotations - are required to develop radiation oncology AI models. Importantly, the recent establishment of Findable, Accessible, Interoperable, Reusable (FAIR) principles for scientific data management have enabled an increasing number of radiation oncology related datasets to be disseminated through data repositories, thereby acting as a rich source of data for AI model building. This manuscript reviews the current and future state of radiation oncology data dissemination, with a particular emphasis on published imaging datasets, AI data challenges, and associated infrastructure. Moreover, we provide historical context of FAIR data dissemination protocols, difficulties in the current distribution of radiation oncology data, and recommendations regarding data dissemination for eventual utilization in AI models. Through FAIR principles and standardized approaches to data dissemination, radiation oncology AI research has nothing to lose and everything to gain.

Trends in Radiation Oncology Treatment Fractionation at a Single Academic Center, 2010-2020

Purpose

Recent clinical trials suggest hypofractionated treatment regimens are appropriate for treatment of many cancers. It is important to understand and document hypofractionation adoption because of its implications for treatment center patient volumes. There is no recent U.S. study of trends in hypofractionation adoption that includes comparisons of multiple disease sites and data since the onset of COVID-19. In this context, this study describes trends in treatment fractionation at a single academic center from 2010 to 2020.

Methods and Materials

From an institutional database, records were extracted for treatment of 4 disease site categories: all cancers, breast cancer, prostate cancer, and bone metastases. For each disease site, the mean number of fractions per treatment course was reported for each year of the study period. To explore whether the COVID-19 pandemic was associated with increased hypofractionation adoption, piecewise linear regression models were used to estimate a changepoint in the time trend of mean monthly number of fractions per treatment course and to evaluate whether this changepoint coincided with pandemic onset.

Results

The data set included 22,865 courses of radiation treatment and 375,446 treatment fractions. The mean number of fractions per treatment course for all cancers declined from 17.5 in 2010 to 13.6 in 2020. There was increased adoption of hypofractionation at this institution for all cancers and specifically for both breast and prostate cancer. For bone metastases, hypofractionation had largely been adopted before the study period. For most disease sites, adoption of hypofractionated treatment courses occurred before pandemic onset. Bone metastases was the only disease site where a pandemic-driven increase in hypofractionation adoption could not be ruled out.

Conclusions

This study reveals increasing use of hypofractionated regimens for a variety of cancers throughout the study period, which largely occurred before the onset of the COVID-19 pandemic at this institution.

Molecular Biology in Treatment Decision Processes-Neuro-Oncology Edition

Computational approaches including machine learning, deep learning, and artificial intelligence are growing in importance in all medical specialties as large data repositories are increasingly being optimised. Radiation oncology as a discipline is at the forefront of large-scale data acquisition and well positioned towards both the production and analysis of large-scale oncologic data with the potential for clinically driven endpoints and advancement of patient outcomes. Neuro-oncology is comprised of malignancies that often carry poor prognosis and significant neurological sequelae. The analysis of radiation therapy mediated treatment and the potential for computationally mediated analyses may lead to more precise therapy by employing large scale data. We analysed the state of the literature pertaining to large scale data, computational analysis, and the advancement of molecular biomarkers in neuro-oncology with emphasis on radiation oncology. We aimed to connect existing and evolving approaches to realistic avenues for clinical implementation focusing on low grade gliomas (LGG), high grade gliomas (HGG), management of the elderly patient with HGG, rare central nervous system tumors, craniospinal irradiation, and re-irradiation to examine how computational analysis and molecular science may synergistically drive advances in personalised radiation therapy (RT) and optimise patient outcomes.

Influential Usage of Big Data and Artificial Intelligence in Healthcare

Artificial intelligence (AI) is making computer systems capable of executing human brain tasks in many fields in all aspects of daily life. The enhancement in information and communications technology (ICT) has indisputably improved the quality of people's lives around the globe. Especially, ICT has led to a very needy and tremendous improvement in the health sector which is commonly known as electronic health (eHealth) and medical health (mHealth). Deep machine learning and AI approaches are commonly presented in many applications using big data, which consists of all relevant data about the medical health and diseases which a model can access at the time of execution or diagnosis of diseases. For example, cardiovascular imaging has now accurate imaging combined with big data from the eHealth record and pathology to better characterize the disease and personalized therapy. In clinical work and imaging, cancer care is getting improved by knowing the tumor biology and helping in the implementation of precision medicine. The Markov model is used to extract new approaches for leveraging cancer. In this paper, we have reviewed existing research relevant to eHealth and mHealth where various models are discussed which uses big data for the diagnosis and healthcare system. This paper summarizes the recent promising applications of AI and big data in medical health and electronic health, which have potentially added value to diagnosis and patient care.

Cancer Informatics for Cancer Centers: Scientific Drivers for Informatics, Data Science, and Care in Pediatric, Adolescent, and Young Adult Cancer

Cancer Informatics for Cancer Centers (CI4CC) is a grassroots, nonprofit 501c3 organization intended to provide a focused national forum for engagement of senior cancer informatics leaders, primarily aimed at academic cancer centers anywhere in the world but with a special emphasis on the 70 National Cancer Institute-funded cancer centers. This consortium has regularly held topic-focused biannual face-to-face symposiums. These meetings are a place to review cancer informatics and data science priorities and initiatives, providing a forum for discussion of the strategic and pragmatic issues that we faced at our respective institutions and cancer centers. Here, we provide meeting highlights from the latest CI4CC Symposium, which was delayed from its original April 2020 schedule because of the COVID-19 pandemic and held virtually over three days (September 24, October 1, and October 8) in the fall of 2020. In addition to the content presented, we found that holding this event virtually once a week for 6 hours was a great way to keep the kind of deep engagement that a face-to-face meeting engenders. This is the second such publication of CI4CC Symposium highlights, the first covering the meeting that took place in Napa, California, from October 14-16, 2019. We conclude with some thoughts about using data science to learn from every child with cancer, focusing on emerging activities of the National Cancer Institute's Childhood Cancer Data Initiative.

Clinical Natural Language Processing for Radiation Oncology: A Review and Practical Primer

Natural language processing (NLP), which aims to convert human language into expressions that can be analyzed by computers, is one of the most rapidly developing and widely used technologies in the field of artificial intelligence. Natural language processing algorithms convert unstructured free text data into structured data that can be extracted and analyzed at scale. In medicine, this unlocking of the rich, expressive data within clinical free text in electronic medical records will help untap the full potential of big data for research and clinical purposes. Recent major NLP algorithmic advances have significantly improved the performance of these algorithms, leading to a surge in academic and industry interest in developing tools to automate information extraction and phenotyping from clinical texts. Thus, these technologies are poised to transform medical research and alter clinical practices in the future. Radiation oncology stands to benefit from NLP algorithms if they are appropriately developed and deployed, as they may enable advances such as automated inclusion of radiation therapy details into cancer registries, discovery of novel insights about cancer care, and improved patient data curation and presentation at the point of care. However, challenges remain before the full value of NLP is realized, such as the plethora of jargon specific to radiation oncology, nonstandard nomenclature, a lack of publicly available labeled data for model development, and interoperability limitations between radiation oncology data silos. Successful development and implementation of high quality and high value NLP models for radiation oncology will require close collaboration between computer scientists and the radiation oncology community. Here, we present a primer on artificial intelligence algorithms in general and NLP algorithms in particular; provide guidance on how to assess the performance of such algorithms; review prior research on NLP algorithms for oncology; and describe future avenues for NLP in radiation oncology research and clinics.

Automated data abstraction for quality surveillance and outcome assessment in radiation oncology

Rigorous radiotherapy quality surveillance and comprehensive outcome assessment require electronic capture and automatic abstraction of clinical, radiation treatment planning, and delivery data. We present the design and implementation framework of an integrated data abstraction, aggregation, and storage, curation, and analytics software: the Health Information Gateway and Exchange (HINGE), which collates data for cancer patients receiving radiotherapy. The HINGE software abstracts structured DICOM‐RT data from the treatment planning system (TPS), treatment data from the treatment management system (TMS), and clinical data from the electronic health records (EHRs). HINGE software has disease site‐specific “Smart” templates that facilitate the entry of relevant clinical information by physicians and clinical staff in a discrete manner as part of the routine clinical documentation. Radiotherapy data abstracted from these disparate sources and the smart templates are processed for quality and outcome assessment. The predictive data analyses are done on using well‐defined clinical and dosimetry quality measures defined by disease site experts in radiation oncology. HINGE application software connects seamlessly to the local IT/medical infrastructure via interfaces and cloud services and performs data extraction and aggregation functions without human intervention. It provides tools to assess variations in radiation oncology practices and outcomes and determines gaps in radiotherapy quality delivered by each provider.

PET Molecular Imaging: A Holistic Review of Current Practice and Emerging Perspectives for Diagnosis, Therapeutic Evaluation and Prognosis in Clinical Oncology

PET/CT molecular imaging has been imposed in clinical oncological practice over the past 20 years, driven by its two well-grounded foundations: quantification and radiolabeled molecular probe vectorization. From basic visual interpretation to more sophisticated full kinetic modeling, PET technology provides a unique opportunity to characterize various biological processes with different levels of analysis. In clinical practice, many efforts have been made during the last two decades to standardize image analyses at the international level, but advanced metrics are still under use in practice. In parallel, the integration of PET imaging with radionuclide therapy, also known as radiolabeled theranostics, has paved the way towards highly sensitive radionuclide-based precision medicine, with major breakthroughs emerging in neuroendocrine tumors and prostate cancer. PET imaging of tumor immunity and beyond is also emerging, emphasizing the unique capabilities of PET molecular imaging to constantly adapt to emerging oncological challenges. However, these new horizons face the growing complexity of multidimensional data. In the era of precision medicine, statistical and computer sciences are currently revolutionizing image-based decision making, paving the way for more holistic cancer molecular imaging analyses at the whole-body level.

Validation of the American Joint Committee on Cancer Eighth Edition Staging of Patients With Metastatic Cutaneous Melanoma Treated With Immune Checkpoint Inhibitors

IMPORTANCE

Immune checkpoint inhibitors (ICIs) have transformed the survival of patients with metastatic melanoma. Patient prognosis is reflected by the American Joint Committee on Cancer (AJCC) staging system; however, it is unknown whether the metastatic (M) stage categories for cutaneous melanoma remain informative of prognosis in patients who have received ICIs.

OBJECTIVES

To evaluate the outcomes of patients with metastatic cutaneous melanoma based on the M stage category from the AJCC eighth edition and to determine whether these designations continue to inform the prognosis of patients who have received ICIs.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study included patients with metastatic cutaneous melanoma who were treated between August 2006 and August 2019 at the University of Michigan. The estimated median follow-up time was 35.5 months. Patient data were collected via the electronic medical record system. Critical findings were externally validated in a multicenter nationwide cohort of patients treated within the Veterans Affairs health care system. Data analysis was conducted from February 2020 to January 2021.

EXPOSURES

All patients were treated with dual-agent concurrent ipilimumab and nivolumab followed by maintenance nivolumab or single-agent ipilimumab, nivolumab, or pembrolizumab therapy. Patients were staged using the AJCC eighth edition.

MAIN OUTCOMES AND MEASURES

Univariable and multivariable analyses were used to assess the prognostic value of predefined clinicopathologic baseline factors on survival.

RESULTS

In a discovery cohort of 357 patients (mean [SD] age, 62.6 [14.2] years; 254 [71.1%] men) with metastatic cutaneous melanoma treated with ICIs, the M category in the AJCC eighth edition showed limited prognostic stratification by both univariable and multivariable analyses. The presence of liver metastases and elevated levels of serum lactate dehydrogenase (LDH) offered superior prognostic separation compared with the M category (liver metastases: hazard ratio, 2.22; 95% CI, 1.48-3.33; P < .001; elevated serum LDH: hazard ratio, 1.73; 95% CI, 1.16-2.58; P = .007). An updated staging system based on these factors was externally validated in a cohort of 652 patients (mean [SD] age, 67.9 [11.6] years; 630 [96.6%] men), with patients without liver metastases or elevated LDH levels having the longest survival (median overall survival, 30.7 months).

CONCLUSIONS AND RELEVANCE

This study found that the AJCC eighth edition M category was poorly reflective of prognosis in patients receiving ICIs. Future staging systems could consider emphasizing the presence of liver metastases and elevated LDH levels. Additional studies are needed to confirm the importance of these and other prognostic biomarkers.

Reduction of inter-observer contouring variability in daily clinical practice through a retrospective, evidence-based intervention

BACKGROUND

Inter-observer variations (IOVs) arising during contouring can potentially impact plan quality and patient outcomes. Regular assessment of contouring IOV is not commonly performed in clinical practice due to the large time commitment required of clinicians from conventional methods. This work uses retrospective information from past treatment plans to facilitate a time-efficient, evidence-based intervention to reduce contouring IOV.

METHODS

The contours of 492 prostate cancer treatment plans created by four radiation oncologists were analyzed in this study. Structure volumes, lengths, and DVHs were extracted from the treatment planning system and stratified based on primary oncologist and inclusion of a pelvic lymph node (PLN) target. Inter-observer variations and their dosimetric consequences were assessed using Student's t-tests. Results of this analysis were presented at an intervention meeting, where new consensus contour definitions were agreed upon. The impact of the intervention was assessed one-year later by repeating the analysis on 152 new plans.

RESULTS

Significant IOV in prostate and PLN target delineation existed pre-intervention between oncologists, impacting dose to nearby OARs. IOV was also present for rectum and penile-bulb structures. Post-intervention, IOV decreased for all previously discordant structures. Dosimetric variations were also reduced. Although target contouring concordance increased significantly, some variations still persisted for PLN structures, highlighting remaining areas for improvement.

CONCLUSION

We detected significant contouring IOV in routine practice using easily accessible retrospective data and successfully decreased IOV in our clinic through a reflective intervention. Continued application of this approach may aid improvements in practice standardization and enhance quality of care.

Liver metastasis restrains immunotherapy efficacy via macrophage-mediated T cell elimination

Metastasis is the primary cause of cancer mortality, and cancer frequently metastasizes to the liver. It is not clear whether liver immune tolerance mechanisms contribute to cancer outcomes. We report that liver metastases diminish immunotherapy efficacy systemically in patients and preclinical models. Patients with liver metastases derive limited benefit from immunotherapy independent of other established biomarkers of response. In multiple mouse models, we show that liver metastases siphon activated CD8⁺ T cells from systemic circulation. Within the liver, activated antigen-specific Fas⁺CD8⁺ T cells undergo apoptosis following their interaction with FasL⁺CD11b⁺F4/80⁺ monocyte-derived macrophages. Consequently, liver metastases create a systemic immune desert in preclinical models. Similarly, patients with liver metastases have reduced peripheral T cell numbers and diminished tumoral T cell diversity and function. In preclinical models, liver-directed radiotherapy eliminates immunosuppressive hepatic macrophages, increases hepatic T cell survival and reduces hepatic siphoning of T cells. Thus, liver metastases co-opt host peripheral tolerance mechanisms to cause acquired immunotherapy resistance through CD8⁺ T cell deletion, and the combination of liver-directed radiotherapy and immunotherapy could promote systemic antitumor immunity.

A Deep Learning Approach Validates Genetic Risk Factors for Late Toxicity After Prostate Cancer Radiotherapy in a REQUITE Multi-National Cohort

Background: REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side effects and improve QUalITy of lifE in cancer survivors) is an international prospective cohort study. The purpose of this project was to analyse a cohort of patients recruited into REQUITE using a deep learning algorithm to identify patient-specific features associated with the development of toxicity, and test the approach by attempting to validate previously published genetic risk factors. Methods: The study involved REQUITE prostate cancer patients treated with external beam radiotherapy who had complete 2-year follow-up. We used five separate late toxicity endpoints: ≥grade 1 late rectal bleeding, ≥grade 2 urinary frequency, ≥grade 1 haematuria, ≥ grade 2 nocturia, ≥ grade 1 decreased urinary stream. Forty-three single nucleotide polymorphisms (SNPs) already reported in the literature to be associated with the toxicity endpoints were included in the analysis. No SNP had been studied before in the REQUITE cohort. Deep Sparse AutoEncoders (DSAE) were trained to recognize features (SNPs) identifying patients with no toxicity and tested on a different independent mixed population including patients without and with toxicity. Results: One thousand, four hundred and one patients were included, and toxicity rates were: rectal bleeding 11.7%, urinary frequency 4%, haematuria 5.5%, nocturia 7.8%, decreased urinary stream 17.1%. Twenty-four of the 43 SNPs that were associated with the toxicity endpoints were validated as identifying patients with toxicity. Twenty of the 24 SNPs were associated with the same toxicity endpoint as reported in the literature: 9 SNPs for urinary symptoms and 11 SNPs for overall toxicity. The other 4 SNPs were associated with a different endpoint. Conclusion: Deep learning algorithms can validate SNPs associated with toxicity after radiotherapy for prostate cancer. The method should be studied further to identify polygenic SNP risk signatures for radiotherapy toxicity. The signatures could then be included in integrated normal tissue complication probability models and tested for their ability to personalize radiotherapy treatment planning.

AI in Medical Imaging Informatics: Current Challenges and Future Directions

This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.

Combination of a Big Data Analytics Resource System With an Artificial Intelligence Algorithm to Identify Clinically Actionable Radiation Dose Thresholds for Dysphagia in Head and Neck Patients

Purpose

We combined clinical practice changes, standardizations, and technology to automate aggregation, integration, and harmonization of comprehensive patient data from the multiple source systems used in clinical practice into a big data analytics resource system (BDARS). We then developed novel artificial intelligence algorithms, coupled with the BDARS, to identify structure dose volume histograms (DVH) metrics associated with dysphagia.

Methods and Materials

From the BDARS harmonized data of ≥22,000 patients, we identified 132 patients recently treated for head and neck cancer who also demonstrated dysphagia scores that worsened from base line to a maximum grade ≥2. We developed a method that used both physical and biologically corrected (α/β = 2.5) DVH curves to test both absolute and percentage volume based DVH metrics. Combining a statistical categorization algorithm with machine learning (SCA-ML) provided more extensive detailing of response threshold evidence than either approach alone. A sensitivity guided, minimum input, machine learning (ML) model was iteratively constructed to identify the key structure DVH metric thresholds.

Results

Seven swallowing structures producing 738 candidate DVH metrics were ranked for association with dysphagia using SCA-ML scoring. Structures included superior pharyngeal constrictor (SPC), inferior pharyngeal constrictor (IPC), larynx, and esophagus. Bilateral parotid and submandibular gland (SG) structures were categorized by relative mean dose (eg, SG_high, SG_low) as a dose versus tumor centric analog to contra and ipsilateral designations. Structure DVH metrics with high SCA-ML scores included the following: SPC: D20% (equivalent dose [EQD2] Gy) ≥47.7; SPC: D25% (Gy) ≥50.4; IPC: D35% (Gy) ≥61.7; parotid_low: D60% (Gy) ≥13.2; and SG_high: D35% (Gy) ≥61.7. Larynx: D25% (Gy) ≥21.2 and SG_low: D45% ≥28.2 had high SCA-ML scores but were segmented on less than 90% of plans. A model based on SPC: D20% (EQD2 Gy) alone had sensitivity and area under the curve of 0.88 ± 0.13 and 0.74 ± 0.17, respectively.

Conclusions

This study provides practical demonstration of combining big data with artificial intelligence to increase volume of evidence in clinical learning paradigms.

Machine learning for radiomics-based multimodality and multiparametric modeling

Due to the recent developments of both hardware and software technologies, multimodality medical imaging techniques have been increasingly applied in clinical practice and research studies. Previously, the application of multimodality imaging in oncology has been mainly related to combining anatomical and functional imaging to improve diagnostic specificity and/or target definition, such as positron emission tomography/computed tomography (PET/CT) and single-photon emission CT (SPECT)/CT. More recently, the fusion of various images, such as multiparametric magnetic resonance imaging (MRI) sequences, different PET tracer images, PET/MRI, has become more prevalent, which has enabled more comprehensive characterization of the tumor phenotype. In order to take advantage of these valuable multimodal data for clinical decision making using radiomics, we present two ways to implement the multimodal image analysis, namely radiomic (handcrafted feature) based and deep learning (machine learned feature) based methods. Applying advanced machine (deep) learning algorithms across multimodality images have shown better results compared with single modality modeling for prognostic and/or prediction of clinical outcomes. This holds great potentials for providing more personalized treatment for patients and achieve better outcomes.

Minimum Data Elements for Radiation Oncology: An American Society for Radiation Oncology Consensus Paper

PURPOSE

In recent years, the American Society for Radiation Oncology (ASTRO) has received requests for a standard list of data elements from other societies, database architects, Electronic Health Record vendors and, most recently, the pharmaceutical industry. These requests point to a growing interest in capturing radiation oncology data within registries and for quality measurement, interoperability initiatives, and research. Identifying a short and consistent list will lead to improved care coordination, a reduction in data entry by practice staff, and a more complete view of the holistic approach required for cancer treatment.

METHODS AND MATERIALS

The task force formulated recommendations based on analysis from radiation specific data elements currently in use in registries, accreditation programs, incident learning systems, and electronic health records. The draft manuscript was peer reviewed by 8 reviewers and ASTRO legal counsel and was revised accordingly and posted on the ASTRO website for public comment in April 2019 for 2 weeks. The final document was approved by the ASTRO Board of Directors in June 2019.

Optimizing efficiency and safety in external beam radiotherapy using automated plan check (APC) tool and six sigma methodology

PURPOSE

To develop and implement an automated plan check (APC) tool using a Six Sigma methodology with the aim of improving safety and efficiency in external beam radiotherapy.

METHODS

The Six Sigma define-measure-analyze-improve-control (DMAIC) framework was used by measuring defects stemming from treatment planning that were reported to the departmental incidence learning system (ILS). The common error pathways observed in the reported data were combined with our departmental physics plan check list, and AAPM TG-275 identified items. Prioritized by risk priority number (RPN) and severity values, the check items were added to the APC tool developed using Varian Eclipse Scripting Application Programming Interface (ESAPI). At 9 months post-APC implementation, the tool encompassed 89 check items, and its effectiveness was evaluated by comparing RPN values and rates of reported errors. To test the efficiency gains, physics plan check time and reported error rate were prospectively compared for 20 treatment plans.

RESULTS

The APC tool was successfully implemented for external beam plan checking. FMEA RPN ranking re-evaluation at 9 months post-APC demonstrated a statistically significant average decrease in RPN values from 129.2 to 83.7 (P < .05). After the introduction of APC, the average frequency of reported treatment-planning errors was reduced from 16.1% to 4.1%. For high-severity errors, the reduction was 82.7% for prescription/plan mismatches and 84.4% for incorrect shift note. The process shifted from 4σ to 5σ quality for isocenter-shift errors. The efficiency study showed a statistically significant decrease in plan check time (10.1 ± 7.3 min, P = .005) and decrease in errors propagating to physics plan check (80%).

CONCLUSIONS

Incorporation of APC tool has significantly reduced the error rate. The DMAIC framework can provide an iterative and robust workflow to improve the efficiency and quality of treatment planning procedure enabling a safer radiotherapy process.

Use of metrics to quantify IMRT and VMAT treatment plan complexity: A systematic review and perspectives

PURPOSE

Fixed-field intensity modulated radiation therapy (FF-IMRT) or volumetric modulated arc therapy (VMAT) beams complexity is due to fluence fluctuation. Pre-treatment Quality Assurance (PTQA) failure could be linked to it. Several plan complexity metrics (PCM) have been published to quantify this complexity but in a heterogeneous formalism. This review proposes to gather different PCM and to discuss their eventual PTQA failure identifier abilities.

METHODS AND MATERIALS

A systematic literature search and outcome extraction from MEDLINE/PubMed (National Center for Biotechnology Information, NCBI) was performed. First, a list and a synthesis of available PCM is made in a homogeneous formalism. Second, main results relying on the link between PCM and PTQA results but also on other uses are listed.

RESULTS

A total of 163 studies were identified and n = 19 were selected after inclusion and exclusion criteria application. Difference is made between fluence and degree of freedom (DOF)-based PCM. Results about the PCM potential as PTQA failure identifier are described and synthesized. Others uses are also found in quality, big data, machine learning and audit procedure.

CONCLUSIONS

A state of the art is made thanks to this homogeneous PCM classification. For now, PCM should be seen as a planning procedure quality indicator although PTQA failure identifier results are mitigated. However limited clinical use seems possible for some cases. Yet, addressing the general PTQA failure prediction case could be possible with the big data or machine learning help.

Retrospective analysis of breast radiotherapy treatment plans: Curating the 'non-curated'

INTRODUCTION

This paper provides a demonstration of how non-curated data can be retrospectively cleaned, so that existing repositories of radiotherapy treatment planning data can be used to complete bulk retrospective analyses of dosimetric trends and other plan characteristics.

METHODS

A non curated archive of 1137 radiotherapy treatment plans accumulated over a 12-month period, from five radiotherapy centres operated by one institution, was used to investigate and demonstrate a process of clinical data cleansing, by: identifying and translating inconsistent structure names; correcting inconsistent lung contouring; excluding plans for treatments other than breast tangents and plans without identifiable PTV, lung and heart structures; and identifying but not excluding plans that deviated from the local planning protocol. PTV, heart and lung dose-volume metrics were evaluated, in addition to a sample of personnel and linac load indicators.

RESULTS

Data cleansing reduced the number of treatment plans in the sample by 35.7%. Inconsistent structure names were successfully identified and translated (e.g. 35 different names for lung). Automatically separating whole lung structures into left and right lung structures allowed the effect of contralateral and ipsilateral lung dose to be evaluated, while introducing some small uncertainties, compared to manual contouring. PTV doses were indicative of prescription doses. Breast treatment work was unevenly distributed between oncologists and between metropolitan and regional centres.

CONCLUSION

This paper exemplifies the data cleansing and data analysis steps that may be completed using existing treatment planning data, to provide individual radiation oncology departments with access to information on their own patient populations. Clearly, the well-planned and systematic recording of new, high quality data is the preferred solution, but the retrospective curation of non-curated data may be a useful interim solution, for radiation oncology departments where the systems for recording of new data have yet to be designed and agreed.

Big Data Readiness in Radiation Oncology: An Efficient Approach for Relabeling Radiation Therapy Structures With Their TG-263 Standard Name in Real-World Data Sets

Purpose

To prepare for big data analyses on radiation therapy data, we developed Stature, a tool-supported approach for standardization of structure names in existing radiation therapy plans. We applied the widely endorsed nomenclature standard TG-263 as the mapping target and quantified the structure name inconsistency in 2 real-world data sets.

Methods and Materials

The clinically relevant structures in the radiation therapy plans were identified by reference to randomized controlled trials. The Stature approach was used by clinicians to identify the synonyms for each relevant structure, which was then mapped to the corresponding TG-263 name. We applied Stature to standardize the structure names for 654 patients with prostate cancer (PCa) and 224 patients with head and neck squamous cell carcinoma (HNSCC) who received curative radiation therapy at our institution between 2007 and 2017. The accuracy of the Stature process was manually validated in a random sample from each cohort. For the HNSCC cohort we measured the resource requirements for Stature, and for the PCa cohort we demonstrated its impact on an example clinical analytics scenario.

Results

All but 1 synonym group (“Hydrogel”) was mapped to the corresponding TG-263 name, resulting in a TG-263 relabel rate of 99% (8837 of 8925 structures). For the PCa cohort, Stature matched a total of 5969 structures. Of these, 5682 structures were exact matches (ie, following local naming convention), 284 were matched via a synonym, and 3 required manual matching. This original radiation therapy structure names therefore had a naming inconsistency rate of 4.81%. For the HNSCC cohort, Stature mapped a total of 2956 structures (2638 exact, 304 synonym, 14 manual; 10.76% inconsistency rate) and required 7.5 clinician hours. The clinician hours required were one-fifth of those that would be required for manual relabeling. The accuracy of Stature was 99.97% (PCa) and 99.61% (HNSCC).

Conclusions

The Stature approach was highly accurate and had significant resource efficiencies compared with manual curation.

Performance/outcomes data and physician process challenges for practical big data efforts in radiation oncology

It is an exciting time for big data efforts in radiation oncology. The use of big data to help aid both outcomes and decision-making research is becoming a reality. However, there are true challenges that exist in the space of gathering and utilizing performance and outcomes data. Here, we summarize the current state of big data in radiation oncology with respect to outcomes and discuss some of the efforts and challenges in radiation oncology big data.

Treatment data and technical process challenges for practical big data efforts in radiation oncology

The term Big Data has come to encompass a number of concepts and uses within medicine. This paper lays out the relevance and application of large collections of data in the radiation oncology community. We describe the potential importance and uses in clinical practice. The important concepts are then described and how they have been or could be implemented are discussed. Impediments to progress in the collection and use of sufficient quantities of data are also described. Finally, recommendations for how the community can move forward to achieve the potential of big data in radiation oncology are provided.

Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges

Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the "HPV" challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the "local recurrence" challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.

Selection of external beam radiotherapy approaches for precise and accurate cancer treatment

Physically precise external-beam radiotherapy (EBRT) technologies may not translate to the best outcome in individual patients. On the other hand, clinical considerations alone are often insufficient to guide the selection of a specific EBRT approach in patients. We examine the ways in which to compare different EBRT approaches based on physical, biological and clinical considerations, and how they can be enhanced with the addition of biophysical models and machine-learning strategies. The process of selecting an EBRT modality is expected to improve in tandem with knowledge-based treatment planning.

Data collection of patient outcomes: one institution's experience

Patient- and provider-reported outcomes are recognized as important in evaluating quality of care, guiding health care policy, comparative effectiveness research, and decision-making in radiation oncology. Combining patient and provider outcome data with a detailed description of disease and therapy is the basis for these analyses. We report on the combination of technical solutions and clinical process changes at our institution that were used in the collection and dissemination of this data. This initiative has resulted in the collection of treatment data for 23 541 patients, 20 465 patients with provider-based adverse event records, and patient-reported outcome surveys submitted by 5622 patients. All of the data is made accessible using a self-service web-based tool.

Big Data in Designing Clinical Trials: Opportunities and Challenges

Emergence of big data analytics resource systems (BDARSs) as a part of routine practice in Radiation Oncology is on the horizon. Gradually, individual researchers, vendors, and professional societies are leading initiatives to create and demonstrate use of automated systems. What are the implications for design of clinical trials, as these systems emerge? Gold standard, randomized controlled trials (RCTs) have high internal validity for the patients and settings fitting constraints of the trial, but also have limitations including: reproducibility, generalizability to routine practice, infrequent external validation, selection bias, characterization of confounding factors, ethics, and use for rare events. BDARS present opportunities to augment and extend RCTs. Preliminary modeling using single- and muti-institutional BDARS may lead to better design and less cost. Standardizations in data elements, clinical processes, and nomenclatures used to decrease variability and increase veracity needed for automation and multi-institutional data pooling in BDARS also support ability to add clinical validation phases to clinical trial design and increase participation. However, volume and variety in BDARS present other technical, policy, and conceptual challenges including applicable statistical concepts, cloud-based technologies. In this summary, we will examine both the opportunities and the challenges for use of big data in design of clinical trials.

Incorporating big data into treatment plan evaluation: Development of statistical DVH metrics and visualization dashboards

Purpose

To develop statistical dose-volume histogram (DVH)–based metrics and a visualization method to quantify the comparison of treatment plans with historical experience and among different institutions.

Methods and materials

The descriptive statistical summary (ie, median, first and third quartiles, and 95% confidence intervals) of volume-normalized DVH curve sets of past experiences was visualized through the creation of statistical DVH plots. Detailed distribution parameters were calculated and stored in JavaScript Object Notation files to facilitate management, including transfer and potential multi-institutional comparisons. In the treatment plan evaluation, structure DVH curves were scored against computed statistical DVHs and weighted experience scores (WESs). Individual, clinically used, DVH-based metrics were integrated into a generalized evaluation metric (GEM) as a priority-weighted sum of normalized incomplete gamma functions. Historical treatment plans for 351 patients with head and neck cancer, 104 with prostate cancer who were treated with conventional fractionation, and 94 with liver cancer who were treated with stereotactic body radiation therapy were analyzed to demonstrate the usage of statistical DVH, WES, and GEM in a plan evaluation. A shareable dashboard plugin was created to display statistical DVHs and integrate GEM and WES scores into a clinical plan evaluation within the treatment planning system. Benchmarking with normal tissue complication probability scores was carried out to compare the behavior of GEM and WES scores.

Results

DVH curves from historical treatment plans were characterized and presented, with difficult-to-spare structures (ie, frequently compromised organs at risk) identified. Quantitative evaluations by GEM and/or WES compared favorably with the normal tissue complication probability Lyman-Kutcher-Burman model, transforming a set of discrete threshold-priority limits into a continuous model reflecting physician objectives and historical experience.

Conclusions

Statistical DVH offers an easy-to-read, detailed, and comprehensive way to visualize the quantitative comparison with historical experiences and among institutions. WES and GEM metrics offer a flexible means of incorporating discrete threshold-prioritizations and historic context into a set of standardized scoring metrics. Together, they provide a practical approach for incorporating big data into clinical practice for treatment plan evaluations.