No abstract

No abstract

No 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 database. Incident descriptions from these reports were processed using various NLP techniques. The processed data with the expert-generated labels were used to train and evaluate over 500 multi-output ML algorithms. The top three models were identified and tuned for each of three different taxonomy data elements, namely: (1) process step where the incident occurred, (2) problem type of the incident and (3) the contributing factors of the incident. The best-performing model after tuning was identified for each data element and tested on unseen data. Results: The MultiOutputRegressor extended Linear SVR models performed best on the three data elements. On testing, our models ranked the most appropriate label 1.48 ± 0.03, 1.73 ± 0.05 and 2.66 ± 0.08 for process-step, problemtype and contributing factors respectively. Conclusions: We developed NLP-ML models that can perform incident classification. These models will be integrated into our ILS to generate a drop-down menu. This semi-automated feature has the potential to improve the usability, accuracy and efficiency of our radiation oncology ILS.

This study examines if single-cell DNA sequencing may be used to study the mutational effects of ionizing radiation. As the action of ionizing radiation is a stochastic process, each cell in an irradiated sample experiences its own unique radiation-induced DNA damage. As a result, conventional sequencing methods such as bulk cell sequencing cannot be used to identify individual mutations. In this work, Epstein-Barr virus (EBV) transformed B-lymphoblastoid cells were irradiated with 6 MV X-ray radiation using a medical linear accelerator. Four samples of cells from the same population (400,000 cells/ml) were exposed to sham irradiation (0 Gray [Gy]; control), 0.5 Gy, 1.5 Gy and 3.0 Gy respectively at a common dose rate of about 600 cGy/min. Irradiated samples were incubated for 24 hrs and subsequently underwent single-cell whole-genome DNA sequencing to characterize the radiation impact. Mutational profiles of approximately 500 cells, randomly selected from each sample, were individually analyzed and compared to identify the variation of several mutational parameters as a function of dose. We quantified the copy number variations (CNV) for each cell in our samples. Additionally, we segregated insertion CNVs and deletion CNVs and independently analyzed their dose dependences. We found that the total number of CNVs (insertion and deletion combined) increased with dose, and the number of deletion CNVs consistently increased most. We have repeated the experiment and a new round of single-cell DNA sequencing is underway. If confirmed, our results will demonstrate that the mutational effects of ionizing radiation may be examined directly using single-cell sequencing. Citation Format: Felix Mathew, Jonathan Yeo, Luc Galarneau, Norma Ybarra, Patricia Tonin, Yu Chang Wang, Ioannis Ragoussis, John Kildea. Single-cell DNA sequencing as a means to directly examine the size and frequency of radiation-induced mutations - An exploratory study [abstract]. In: Proceedings of the AACR Virtual Special Conference on Radiation Science and Medicine; 2021 Mar 2-3. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(8_Suppl):Abstract nr PO-021.