Optimization of treatment workflow for 0.35T MR-Linac system.

PURPOSE: This study presents a novel and comprehensive framework for evaluating magnetic resonance guided radiotherapy (MRgRT) workflow by integrating the Failure Modes and Effects Analysis (FMEA) approach with Time-Driven Activity-Based Costing (TDABC). We assess the workflow for safety, quality, and economic implications, providing a holistic understanding of the MRgRT implementation. The aim is to offer valuable insights to healthcare practitioners and administrators, facilitating informed decision-making regarding the 0.35T MRIdian MR-Linac system's clinical workflow. METHODS: For FMEA, a multidisciplinary team followed the TG-100 methodology to assess the MRgRT workflow's potential failure modes. Following the mitigation of primary failure modes and workflow optimization, a treatment process was established for TDABC analysis. The TDABC was applied to both MRgRT and computed tomography guided RT (CTgRT) for typical five-fraction stereotactic body RT (SBRT) treatments, assessing total workflow and costs associated between the two treatment workflows. RESULTS: A total of 279 failure modes were identified, with 31 categorized as high-risk, 55 as medium-risk, and the rest as low-risk. The top 20% risk priority numbers (RPN) were determined for each radiation oncology care team member. Total MRgRT and CTgRT costs were assessed. Implementing technological advancements, such as real-time multi leaf collimator (MLC) tracking with volumetric modulated arc therapy (VMAT), auto-segmentation, and increasing the Linac dose rate, led to significant cost savings for MRgRT. CONCLUSION: In this study, we integrated FMEA with TDABC to comprehensively evaluate the workflow and the associated costs of MRgRT compared to conventional CTgRT for five-fraction SBRT treatments. FMEA analysis identified critical failure modes, offering insights to enhance patient safety. TDABC analysis revealed that while MRgRT provides unique advantages, it may involve higher costs. Our findings underscore the importance of exploring cost-effective strategies and key technological advancements to ensure the widespread adoption and financial sustainability of MRgRT in clinical practice.

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.

Identification of Key Elements in Prostate Cancer for Ontology Building via a Multidisciplinary Consensus Agreement.

BACKGROUND: Clinical data collection related to prostate cancer (PCa) care is often unstructured or heterogeneous among providers, resulting in a high risk for ambiguity in its meaning when sharing or analyzing data. Ontologies, which are shareable formal (i.e., computable) representations of knowledge, can address these challenges by enabling machine-readable semantic interoperability. The purpose of this study was to identify PCa-specific key data elements (KDEs) for standardization in clinic and research. METHODS: A modified Delphi method using iterative online surveys was performed to report a consensus agreement on KDEs by a multidisciplinary panel of 39 PCa specialists. Data elements were divided into three themes in PCa and included (1) treatment-related toxicities (TRT), (2) patient-reported outcome measures (PROM), and (3) disease control metrics (DCM). RESULTS: The panel reached consensus on a thirty-item, two-tiered list of KDEs focusing mainly on urinary and rectal symptoms. The Expanded Prostate Cancer Index Composite (EPIC-26) questionnaire was considered most robust for PROM multi-domain monitoring, and granular KDEs were defined for DCM. CONCLUSIONS: This expert consensus on PCa-specific KDEs has served as a foundation for a professional society-endorsed, publicly available operational ontology developed by the American Association of Physicists in Medicine (AAPM) Big Data Sub Committee (BDSC).

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.

Consensus Quality Measures and Dose Constraints for Lung Cancer From the Veterans Affairs Radiation Oncology Quality Surveillance Program and ASTRO Expert Panel.

PURPOSE: For patients with lung cancer, it is critical to provide evidence-based radiation therapy to ensure high-quality care. The US Department of Veterans Affairs (VA) National Radiation Oncology Program partnered with the American Society for Radiation Oncology (ASTRO) as part of the VA Radiation Oncology Quality Surveillance to develop lung cancer quality metrics and assess quality of care as a pilot program in 2016. This article presents recently updated consensus quality measures and dose-volume histogram (DVH) constraints. METHODS AND MATERIALS: A series of measures and performance standards were reviewed and developed by a Blue-Ribbon Panel of lung cancer experts in conjunction with ASTRO in 2022. As part of this initiative, quality, surveillance, and aspirational metrics were developed for (1) initial consultation and workup; (2) simulation, treatment planning, and treatment delivery; and (3) follow-up. The DVH metrics for target and organ-at-risk treatment planning dose constraints were also reviewed and defined. RESULTS: Altogether, a total of 19 lung cancer quality metrics were developed. There were 121 DVH constraints developed for various fractionation regimens, including ultrahypofractionated (1, 3, 4, or 5 fractions), hypofractionated (10 and 15 fractionations), and conventional fractionation (30-35 fractions). CONCLUSIONS: The devised measures will be implemented for quality surveillance for veterans both inside and outside of the VA system and will provide a resource for lung cancer-specific quality metrics. The recommended DVH constraints serve as a unique, comprehensive resource for evidence- and expert consensus-based constraints across multiple fractionation schemas.

3D deep convolution neural network for radiation pneumonitis prediction following stereotactic body radiotherapy.

In this study, we investigated 3D convolutional neural networks (CNNs) with input from radiographic and dosimetric datasets of primary lung tumors and surrounding lung volumes to predict the likelihood of radiation pneumonitis (RP). Pre-treatment, 3- and 6-month follow-up computed tomography (CT) and 3D dose datasets from one hundred and ninety-three NSCLC patients treated with stereotactic body radiotherapy (SBRT) were retrospectively collected and analyzed for this study. DenseNet-121 and ResNet-50 models were selected for this study as they are deep neural networks and have been proven to have high accuracy for complex image classification tasks. Both were modified with 3D convolution and max pooling layers to accept 3D datasets. We used a minority class oversampling approach and data augmentation to address the challenges of data imbalance and data scarcity. We built two sets of models for classification of three (No RP, Grade 1 RP, Grade 2 RP) and two (No RP, Yes RP) classes as outputs. The 3D DenseNet-121 models performed better (F1 score [0.81], AUC [0.91] [three class]; F1 score [0.77], AUC [0.84] [two class]) than the 3D ResNet-50 models (F1 score [0.54], AUC [0.72] [three-class]; F1 score [0.68], AUC [0.71] [two-class]) (p = 0.017 for three class predictions). We also attempted to identify salient regions within the input 3D image dataset via integrated gradient (IG) techniques to assess the relevance of the tumor surrounding volume for RP stratification. These techniques appeared to indicate the significance of the tumor and surrounding regions in the prediction of RP. Overall, 3D CNNs performed well to predict clinical RP in our cohort based on the provided image sets and radiotherapy dose information.

Consensus Quality Measures and Dose Constraints for Prostate Cancer From the Veterans Affairs Radiation Oncology Quality Surveillance Program and American Society for Radiation Oncology Expert Panel.

PURPOSE: There are no agreed upon measures to comprehensively determine the quality of radiation oncology (RO) care delivered for prostate cancer. Consequently, it is difficult to assess the implementation of scientific advances and adherence to best practices in routine clinical practice. To address this need, the US Department of Veterans Affairs (VA) National Radiation Oncology Program established the VA Radiation Oncology Quality Surveillance (VA ROQS) Program to develop clinical quality measures to assess the quality of RO care delivered to Veterans with cancer. This article reports the prostate cancer consensus measures. METHODS AND MATERIALS: The VA ROQS Program contracted with the American Society for Radiation Oncology to commission a Blue Ribbon Panel of prostate cancer experts to develop a set of evidence-based measures and performance expectations. From February to June 2021, the panel developed quality, aspirational, and surveillance measures for (1) initial consultation and workup, (2) simulation, treatment planning, and delivery, and (3) follow-up. Dose-volume histogram (DVH) constraints to be used as quality measures for definitive and post-prostatectomy radiation therapy were selected. The panel also identified the optimal Common Terminology Criteria for Adverse Events, version 5.0 (CTCAE V5.0), toxicity terms to assess in follow-up. RESULTS: Eighteen prostate-specific measures were developed (13 quality, 2 aspirational, and 3 surveillance). DVH metrics tailored to conventional, moderately hypofractionated, and ultrahypofractionated regimens were identified. Decision trees to determine performance for each measure were developed. Eighteen CTCAE V5.0 terms were selected in the sexual, urinary, and gastrointestinal domains as highest priority for assessment during follow-up. CONCLUSIONS: This set of measures and DVH constraints serves as a tool for assessing the comprehensive quality of RO care for prostate cancer. These measures will be used for ongoing quality surveillance and improvement among veterans receiving care across VA and community sites. These measures can also be applied to clinical settings outside of those serving veterans.

Consensus Quality Measures and Dose Constraints for Breast Cancer From the Veterans Affairs Radiation Oncology Quality Surveillance Program and American Society for Radiation Oncology Expert Panel.

PURPOSE: Using evidence-based radiation therapy to direct care for patients with breast cancer is critical to standardize practice, improve safety, and optimize outcomes. To address this need, the Veterans Affairs (VA) National Radiation Oncology Program (NROP) established the VA Radiation Oncology Quality Surveillance Program to develop clinical quality measures (QMs). The VA NROP contracted with the American Society for Radiation Oncology to commission 5 Blue Ribbon Panels for breast, lung, prostate, rectal, and head and neck cancers. METHODS AND MATERIALS: The Breast Cancer Blue Ribbon Panel experts worked collaboratively with the NROP to develop consensus QMs for use throughout the VA system, establishing a set of QMs for patients in several areas, including consultation and work-up; simulation, treatment planning, and treatment; and follow-up care. As part of this initiative, consensus dose-volume histogram (DVH) constraints were outlined. RESULTS: In total, 36 QMs were established. Herein, we review the process used to develop QMs and final consensus QMs pertaining to all aspects of radiation patient care, as well as DVH constraints. CONCLUSIONS: The QMs and expert consensus DVH constraints are intended for ongoing quality surveillance within the VA system and centers providing community care for Veterans. They are also available for use by greater non-VA community measures of quality care for patients with breast cancer receiving radiation.

Quality and Safety With Technological Advancements in Radiotherapy: An Overview and Journey Narrative From a Low- and Middle-Income Country Institution.

PURPOSE: To present an overview of quality and safety in radiotherapy from the context of low- and middle-income countries on the basis of a recently conducted annual meeting of our institution and our experience of implementing an error management system at our center. METHODS: The minutes of recently concluded annual Evidence-Based Medicine (EBM-2021) meeting on the basis of technology in radiation oncology were reviewed. The session on quality and safety, which had international experts as speakers, was reviewed. Along with this, we reviewed the literature for preventive and reactive measures proposed to manage errors including error reporting and learning systems (ILSs). Concise summary for the same was prepared for this article. RESULTS: We also reviewed the journey of development of our institutional ILS and present here a summary of achievements, challenges, and future vision. CONCLUSION: Preventive and reactive measures must be followed to achieve high-quality and safe radiotherapy. Despite resource constraints, a successful ILS program can be developed in a low- and middle-income country center by first understanding the patterns of error and developing one that suits the working ecosystem.

Consensus Quality Measures and Dose Constraints for Rectal Cancer From the Veterans Affairs Radiation Oncology Quality Surveillance Program and American Society for Radiation Oncology (ASTRO) Expert Panel.

PURPOSE: Ensuring high quality, evidence-based radiation therapy for patients with cancer is of the upmost importance. To address this need, the Veterans Affairs (VA) Radiation Oncology Program partnered with the American Society for Radiation Oncology and established the VA Radiation Oncology Quality Surveillance program. As part of this ongoing effort to provide the highest quality of care for patients with rectal cancer, a blue-ribbon panel comprised of rectal cancer experts was formed to develop clinical quality measures. METHODS AND MATERIALS: The Rectal Cancer Blue Ribbon panel developed quality, surveillance, and aspirational measures for (a) initial consultation and workup, (b) simulation, treatment planning, and treatment, and (c) follow-up. Twenty-two rectal cancer specific measures were developed (19 quality, 1 aspirational, and 2 surveillance). In addition, dose-volume histogram constraints for conventional and hypofractionated radiation therapy were created. CONCLUSIONS: The quality measures and dose-volume histogram for rectal cancer serves as a guideline to assess the quality of care for patients with rectal cancer receiving radiation therapy. These quality measures will be used for quality surveillance for veterans receiving care both inside and outside the VA system to improve the quality of care for these patients.

Consensus Quality Measures and Dose Constraints for Head and Neck Cancer with an emphasis on Oropharyngeal and Laryngeal Cancer from the Veterans Affairs Radiation Oncology Quality Surveillance Program and American Society for Radiation Oncology Expert Panel.

PURPOSE: Safeguarding high-quality care using evidence-based radiation therapy for patients with head and neck cancer is crucial to improving oncologic outcomes, including survival and quality of life. METHODS AND MATERIALS: The Veterans Administration (VA) National Radiation Oncology Program established the VA Radiation Oncology Quality Surveillance Program (VAROQS) to develop clinical quality measures (QM) in head and neck cancer. As part of the development of QM, the VA commissioned, along with the American Society for Radiation Oncology, a blue-ribbon panel comprising experts in head and neck cancer, to develop QM. RESULTS: We describe the methods used to develop QM and the final consensus QM, as well as aspirational and surveillance QM, which capture all aspects of the continuum of patient care from initial patient work-up, radiation treatment planning and delivery, and follow-up care, as well as dose volume constraints. CONCLUSION: These QM are intended for use as part of ongoing quality surveillance for veterans receiving radiation therapy throughout the VA as well as outside the VA. They may also be used by the non-VA community as a basic measure of quality care for head and neck cancer patients receiving radiation.

Veterans Affairs Radiation Oncology Quality Surveillance Program and American Society for Radiation Oncology Quality Measures Initiative.

PURPOSE: Ensuring high quality, evidence-based radiation therapy for patients is of the upmost importance. As a part of the largest integrated health system in America, the Department of Veterans Affairs National Radiation Oncology Program (VA-NROP) established a quality surveillance initiative to address the challenge and necessity of providing the highest quality of care for veterans treated for cancer. METHODS AND MATERIALS: As part of this initiative, the VA-NROP contracted with the American Society for Radiation Oncology to commission 5 Blue Ribbon Panels for lung, prostate, rectal, breast, and head and neck cancers experts. This group worked collaboratively with the VA-NROP to develop consensus quality measures. In addition to the site-specific measures, an additional Blue Ribbon Panel comprised of the chairs and other members of the disease sites was formed to create 18 harmonized quality measures for all 5 sites (13 quality, 4 surveillance, and 1 aspirational). CONCLUSIONS: The VA-NROP and American Society for Radiation Oncology collaboration have created quality measures spanning 5 disease sites to help improve patient outcomes. These will be used for the ongoing quality surveillance of veterans receiving radiation therapy through the VA and its community partners.

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.

Multi-View Data Integration Methods for Radiotherapy Structure Name Standardization.

Standardization of radiotherapy structure names is essential for developing data-driven personalized radiotherapy treatment plans. Different types of data are associated with radiotherapy structures, such as the physician-given text labels, geometric (image) data, and Dose-Volume Histograms (DVH). Prior work on structure name standardization used just one type of data. We present novel approaches to integrate complementary types (views) of structure data to build better-performing machine learning models. We present two methods, namely (a) intermediate integration and (b) late integration, to combine physician-given textual structure name features and geometric information of structures. The dataset consisted of 709 prostate cancer and 752 lung cancer patients across 40 radiotherapy centers administered by the U.S. Veterans Health Administration (VA) and the Department of Radiation Oncology, Virginia Commonwealth University (VCU). We used randomly selected data from 30 centers for training and ten centers for testing. We also used the VCU data for testing. We observed that the intermediate integration approach outperformed the models with a single view of the dataset, while late integration showed comparable performance with single-view results. Thus, we demonstrate that combining different views (types of data) helps build better models for structure name standardization to enable big data analytics in radiation oncology.

Machine-Learning Models for Multicenter Prostate Cancer Treatment Plans.

Clinical factors, including T-stage, Gleason score, and baseline prostate-specific antigen, are used to stratify patients with prostate cancer (PCa) into risk groups. This provides prognostic information for a heterogeneous disease such as PCa and guides treatment selection. In this article, we hypothesize that nonclinical factors may also impact treatment selection and their adherence to treatment guidelines. A total of 552 patients with intermediate- and high-risk PCa treated with definitive radiation with or without androgen deprivation therapy (ADT) between 2010 and 2017 were identified from 34 medical centers within the Veterans Health Administration. Medical charts were manually reviewed, and details regarding each patient's clinical history and treatment were extracted. Support Vector Machine and Random forest-based classification was used to identify clinical and nonclinical predictors of adherence to the treatment guidelines from the National Comprehensive Cancer Network (NCCN). We created models for predicting both initial treatment intent and treatment alterations. Our results demonstrate that besides clinical factors, the center in which the patient was treated (nonclinical factor) played a significant role in adherence to NCCN guidelines. Furthermore, the treatment center served as an important predictor to decide on whether or not to prescribe ADT; however, it was not associated with ADT duration and weakly associated with treatment alterations. Such center-bias motivates further investigation on details of center-specific barriers to both NCCN guideline adherence and on oncological outcomes. In addition, we demonstrate that publicly available data sets, for example, that from Surveillance, Epidemiology, and End Results (SEERs), may not be well equipped to build such predictive models on treatment plans.

An efficient planning technique for low dose whole lung radiation therapy for covid-19 pandemic patients.

This study aimed to establish an efficient planning technique for low dose whole lung treatment that can be implemented rapidly and safely. The treatment technique developed here relied only on chest radiograph and a simple empirical monitor unit calculation formula. The 3D dose calculation in real patient anatomy, including both nonCOVID and COVID-19 patients, which took into account tissue heterogeneity showed that the dose delivered to lungs had reasonable uniformity even with this simple and quick setup.

Automatic Incident Triage in Radiation Oncology Incident Learning System.

The Radiotherapy Incident Reporting and Analysis System (RIRAS) receives incident reports from Radiation Oncology facilities across the US Veterans Health Affairs (VHA) enterprise and Virginia Commonwealth University (VCU). In this work, we propose a computational pipeline for analysis of radiation oncology incident reports. Our pipeline uses machine learning (ML) and natural language processing (NLP) based methods to predict the severity of the incidents reported in the RIRAS platform using the textual description of the reported incidents. These incidents in RIRAS are reviewed by a radiation oncology subject matter expert (SME), who initially triages some incidents based on the salient elements in the incident report. To automate the triage process, we used the data from the VHA treatment centers and the VCU radiation oncology department. We used NLP combined with traditional ML algorithms, including support vector machine (SVM) with linear kernel, and compared it against the transfer learning approach with the universal language model fine-tuning (ULMFiT) algorithm. In RIRAS, severities are divided into four categories; A, B, C, and D, with A being the most severe to D being the least. In this work, we built models to predict High (A & B) vs. Low (C & D) severity instead of all the four categories. Models were evaluated with macro-averaged precision, recall, and F1-Score. The Traditional ML machine learning (SVM-linear) approach did well on the VHA dataset with 0.78 F1-Score but performed poorly on the VCU dataset with 0.5 F1-Score. The transfer learning approach did well on both datasets with 0.81 F1-Score on VHA dataset and 0.68 F1-Score on the VCU dataset. Overall, our methods show promise in automating the triage and severity determination process from radiotherapy incident reports.

A Machine Learning method for relabeling arbitrary DICOM structure sets to TG-263 defined labels.

PURPOSE: To present a Machine Learning pipeline for automatically relabeling anatomical structure sets in the Digital Imaging and Communications in Medicine (DICOM) format to a standard nomenclature that will enable data abstraction for research and quality improvement. METHODS: DICOM structure sets from approximately 1200 lung and prostate cancer patients across 40 treatment centers were used to build predictive models to automate the relabeling of clinically specified structure labels to standardized labels as defined by the American Association of Physics in Medicine's (AAPM) Task Group 263 (TG-263). Volumetric bitmaps were created based on the delineated volumes and were combined with associated bony anatomy data to build feature vectors. Feature reduction was performed with singular value decomposition and the resulting vectors were used for predicting the label of each structure using five different classifier algorithms on the Apache Spark platform with 5-fold cross-validation. Undersampling methods were used to deal with underlying class imbalance that hindered the performance of classifiers. Experiments were performed on both a curated version of the data, which included only annotated structures, and the non-curated data that included all structures from the original treatment plans. RESULTS: Random Forest provided the highest accuracies with F1 scores of 98.77 for lung and 95.06 for prostate on the curated data sets. Scores were lower with 95.67 for lung and 90.22 for prostate on the non-curated data sets, highlighting some of the challenges of classifying real clinical data. Including bony anatomy data and pooling information from all structures for the same patient both increased accuracies. In some cases, undersampling with k-Means clustering for class balancing improved classifier accuracy but in all experiments it significantly reduced run time compared to random undersampling. CONCLUSION: This work shows that structure sets can be relabeled using our approach with accuracies over 95% for many structure types when presented with curated data. Although accuracies dropped when using the full non-curated data sets, some structure types were still correctly labeled over 90% of the time. With similar results obtained on an external test data set, we can infer that the proposed models are likely to work on other clinical data sets.

Integrated Natural Language Processing and Machine Learning Models for Standardizing Radiotherapy Structure Names.

The lack of standardized structure names in radiotherapy (RT) data limits interoperability, data sharing, and the ability to perform big data analysis. To standardize radiotherapy structure names, we developed an integrated natural language processing (NLP) and machine learning (ML) based system that can map the physician-given structure names to American Association of Physicists in Medicine (AAPM) Task Group 263 (TG-263) standard names. The dataset consist of 794 prostate and 754 lung cancer patients across the 40 different radiation therapy centers managed by the Veterans Health Administration (VA). Additionally, data from the Radiation Oncology department at Virginia Commonwealth University (VCU) was collected to serve as a test set. Domain experts identified as anatomically significant nine prostate and ten lung organs-at-risk (OAR) structures and manually labeled them according to the TG-263 standards, and remaining structures were labeled as Non_OAR. We experimented with six different classification algorithms and three feature vector methods, and the final model was built with fastText algorithm. Multiple validation techniques are used to assess the robustness of the proposed methodology. The macro-averaged F 1 score was used as the main evaluation metric. The model achieved an F 1 score of 0.97 on prostate structures and 0.99 for lung structures from the VA dataset. The model also performed well on the test (VCU) dataset, achieving an F 1 score of 0.93 for prostate structures and 0.95 on lung structures. In this work, we demonstrate that NLP and ML based approaches can used to standardize the physician-given RT structure names with high fidelity. This standardization can help with big data analytics in the radiation therapy domain using population-derived datasets, including standardization of the treatment planning process, clinical decision support systems, treatment quality improvement programs, and hypothesis-driven clinical research.