Abstract:To develop a Natural Language Processing (NLP) and Machine Learning (ML) pipeline that can be integrated into an Incident Learning System (ILS) to assist radiation oncology incident learning by semi-automating incident classification. Our goal was to develop ML models that can generate label recommendations, arranged according to their likelihoods, for three data elements in Canadian NSIR-RT taxonomy. Methods: Over 6000 incident reports were gathered from the Canadian national ILS as well as our local ILS data… Show more
“…The running time of training our model is 350 s, and the inference time is less than 0.1 s. To train the DecisionTree model, we used the default parameters from Python's Scikit-Learn module. For SVR, the algorithm does not support multiple outputs for regression problems, and we implemented multi-objective support vector regression via a correlation regression chain [44,45]. We used the RBF (radial basis function kernel) kernel, and other parameters were set as default values.…”
Sinter composition optimization is an important process of iron and steel companies. To increase companies’ profits, they often rely on innovative technology or the workers’ operating experience to improve final productions. However, the former is costly because of patents, and the latter is error-prone. In addition, traditional linear programming optimization methods of sinter compositions are inefficient in the face of large-scale problems and complex nonlinear problems. In this paper, we are the first to propose a regressive convolutional neural network (RCNN) approach for the sinter composition optimization (SCORN). Our SCORN is a single input and multiple outputs regression model. Sinter plant production is used as the input of the SCORN model, and the outputs are the optimized sintering compositions. The SCORN model can predict the optimal sintering compositions to reduce the input of raw materials consumption to save costs and increase profits. By constructing a new neural network structure, the RCNN model is trained to increase its feature extraction capability for sintering production. The SCORN model has a better performance compared with several regressive approaches. The practical application of this predictive model can not only formulate corresponding production plans without feeding materials but also give better input parameters of sintered raw materials during the sintering process.
“…The running time of training our model is 350 s, and the inference time is less than 0.1 s. To train the DecisionTree model, we used the default parameters from Python's Scikit-Learn module. For SVR, the algorithm does not support multiple outputs for regression problems, and we implemented multi-objective support vector regression via a correlation regression chain [44,45]. We used the RBF (radial basis function kernel) kernel, and other parameters were set as default values.…”
Sinter composition optimization is an important process of iron and steel companies. To increase companies’ profits, they often rely on innovative technology or the workers’ operating experience to improve final productions. However, the former is costly because of patents, and the latter is error-prone. In addition, traditional linear programming optimization methods of sinter compositions are inefficient in the face of large-scale problems and complex nonlinear problems. In this paper, we are the first to propose a regressive convolutional neural network (RCNN) approach for the sinter composition optimization (SCORN). Our SCORN is a single input and multiple outputs regression model. Sinter plant production is used as the input of the SCORN model, and the outputs are the optimized sintering compositions. The SCORN model can predict the optimal sintering compositions to reduce the input of raw materials consumption to save costs and increase profits. By constructing a new neural network structure, the RCNN model is trained to increase its feature extraction capability for sintering production. The SCORN model has a better performance compared with several regressive approaches. The practical application of this predictive model can not only formulate corresponding production plans without feeding materials but also give better input parameters of sintered raw materials during the sintering process.
“…In an interesting study with potential applicability to other areas, Mathew et al developed NLP-ML models for incident classification in radiation oncology. They integrated these into the incident learning system to generate a drop-down menu such that the model as a semi-automated feature could improve the usability, accuracy and efficiency of the incident reporting system overall [101]. Hong et al had two independent reviewers identify National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) v5.0 symptoms from 100 randomly selected notes for on-treatment visits during radiation therapy with adjudication by a third reviewer.…”
Section: Response Toxicity and Patient-reported Outcomesmentioning
Oncology like most medical specialties, is undergoing a data revolution at the center of which lie vast and growing amounts of clinical data in unstructured, semi-structured and structed formats. Artificial intelligence approaches are widely employed in research endeavors in an attempt to harness electronic medical records data to advance patient outcomes. The use of clinical oncologic data, although collected on large scale, particularly with the increased implementation of electronic medical records, remains limited due to missing, incorrect or manually entered data in registries and the lack of resource allocation to data curation in real world settings. Natural Language Processing (NLP) may provide an avenue to extract data from electronic medical records and as a result has grown considerably in medicine to be employed for documentation, outcome analysis, phenotyping and clinical trial eligibility. Barriers to NLP persist with inability to aggregate findings across studies due to use of different methods and significant heterogeneity at all levels with important parameters such as patient comorbidities and performance status lacking implementation in AI approaches. The goal of this review is to provide an updated overview of natural language processing (NLP) and the current state of its application in oncology for clinicians and researchers that wish to implement NLP to augment registries and/or advance research projects.
“…Research on using NLP for medical errors in radiation oncology has received limited attention, although recent work shows promise in developing models that are effective in error labeling/classification [ 13 , 14 ]. Previous work has been focused on safety assurance and error reduction, but few studies have incorporated NLP into their methodology.…”
A report published in 2000 from the Institute of Medicine revealed that medical errors were a leading cause of patient deaths, and urged the development of error detection and reporting systems. The field of radiation oncology is particularly vulnerable to these errors due to its highly complex process workflow, the large number of interactions among various systems, devices, and medical personnel, as well as the extensive preparation and treatment delivery steps. Natural language processing (NLP)-aided statistical algorithms have the potential to significantly improve the discovery and reporting of these medical errors by relieving human reporters of the burden of event type categorization and creating an automated, streamlined system for error incidents. In this paper, we demonstrate text-classification models developed with clinical data from a full service radiation oncology center (test center) that can predict the broad level and first level category of an error given a free-text description of the error. All but one of the resulting models had an excellent performance as quantified by several metrics. The results also suggest that more development and more extensive training data would further improve future results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.