Predicting Waiting Times in Radiation Oncology Using Machine Learning

Abstract

This thesis describes a study of machine learning and its application to waiting times in radiation oncology. Specifically, an evaluation of waiting time estimates for daily radiation treatment appointments at the McGill University Health Centre was conducted and two unique communication tools for conveying these waiting time estimates were developed. To evaluate waiting time estimates, a subset of previously-treated patient records was used for training and modelling by several off-the-shelf machine learning algorithms and tested using treatment records unseen by the algorithms. Furthermore, machine learning was explicitly used to predict treatment durations in order to calculate an overall waiting time estimate. It was found that the random forest regression algorithm provided the best model for daily radiation treatment durations. On average, the model is able to predict treatment durations to within 7.2 minutes. This is a significant improvement on the rough estimates currently given to patients, and also on the estimates one would obtain by conducting simple averages on all patients. One of the tools developed to Cependant, une recherche distincte examinant la distribution de renseignements personnels sur la santé, includant les estimations de temps d'attente via une application mobile, est présentement en cours. Ceci est discutée dans cette dissertation.ii ACKNOWLEDGEMENTS

Artificial intelligence in radiation oncology: How far have we reached?

“…Patient scheduling for radiation treatment and on-treatment assessment can be made more efficient by utilizing AI approaches to identify the most important contributing factors to long waiting times. [22] Accurate treatment setup is one of the most crucial steps in overall radiation workflow and depends heavily on integrated cone beam CT (CBCT) devices. Although CBCT has revolutionized radiation treatment delivery by facilitating image-guided radiation therapy, poor image quality is a significant issue affecting the overall setup verification and treatment delivery time.…”

A predictive model for the post-pandemic delay in elective treatment

“…Joseph et al. [20] and Goncalves et al. [21] both adopt the Random Forest Regression methodology to predict waiting time and pinpoint the variables with the highest predictive power.…”

Heart Failure Detection Using Quantum‐Enhanced Machine Learning and Traditional Machine Learning Techniques for Internet of Artificially Intelligent Medical Things

“…5 Wireless Communications and Mobile Computing (b) When combined with quantum computing, machine learning algorithms can assist physicians in understanding therapy outcomes (c) Machine learning is used to detect irregularities in the human body, while quantum computing aids in the interpretation of therapy outcomes [42] (d) Radiation beams are utilized in quantum-enhanced machine learning to kill or halt the proliferation of damaged cells [43] (e) Quantum computers enable clinicians to discover the optimal therapy for each simulation [10] (f) The capacity of quantum computing to process algorithms has drawn the attention of administrators from a variety of businesses. According to one estimate, the quantum computing business was worth $93 million in 2019 and is expected to grow to $283 million by 2024 [44] (g) The potential for quantum computing to identify treatments targeting specific forms of cancer significantly adds to its rise in the healthcare business.…”