Abstract

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.

Highlights

  • Radiation therapy (RT) is a popular cancer treatment speciality that involves coordinated interactions between various clinical staff such as, dosimetrists, physicists, radiation therapists, nurses, and physicians

  • We introduce a sixth category for the application of natural language processing (NLP) in radiation oncology: analysis of radiotherapy incident reports

  • We used universal language model fine-tuning (ULMFiT) to build the transfer learning based approach to predict the severity of incident reports in radiation oncology

Read more

Summary

Introduction

Radiation therapy (RT) is a popular cancer treatment speciality that involves coordinated interactions between various clinical staff such as, dosimetrists, physicists, radiation therapists, nurses, and physicians. Radiation Oncology Incident Learning System (RO-ILS) to enable documentation and analyses of incident reports in the radiation oncology domain. Healthcare incident reports, including the radiotherapy incidents submitted into the RIRAS software, are similar to the safety reports of various industrial environments in that their narratives are reported in an unstructured free-text format. To the best of our knowledge, there is no work reported in the field of radiotherapy to identify the severity of the incidents reported using incident description. There have been well reported research in other industries such as aviation, and nuclear [8,9,10,11,12] to classify the incidents reported in the respective fields. A team in Canada has done a study on identifying the incident types from

Objectives
Methods
Results
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.