Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learned”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,099 records · Page 61

A Transductive Graph Neural Network learning for Grid Resilience Analysis

Power grids are critical infrastructures that require robust resilience analysis to ensure reliable and uninterrupted electricity supply. Traditional simulation-based methods for grid resilience analysis suffer from computational complexity and limited ability to capture the full spectrum of potential disruptions. This paper presents a novel approach to enhance grid resilience by leveraging transductive graph neural network (GNN) learning to identify critical nodes and links. By leveraging the graph structure and system features, GNNs effectively learn resilience metrics and accurately identify critical nodes based on actual grid operational behavior. The efficacy of the proposed approach is demonstrated through case studies on node criticality scoring and critical node/line identification in cascading outage scenarios. The results highlight the advantages of learning-based methods over traditional simulation-based approaches and their potential to revolutionize grid resilience analysis. The contributions of this paper include a graph-based scalable approach for fast cascading analysis, an inductive formulation for training GNN models, and a transfer learning-based approach to scale the model to largescale power systems.

grid resilience, graph neural networks, transducti↗

Accelerating Hydraulic Fracture Imaging by Deep Transfer Learning

Deep transfer learning has a great success story in computer vision (CV), natural language processing, and many other fields. In this communication, we are going to push forward the deep transfer learning to the hydraulic fracture imaging problem by proposing a two-step approach: 1) train a convolutional neural network (CNN) to reconstruct target geometries by a relatively large amount of approximated field patterns generated from a simplified model and 2) fine-tune the top layers of transferred CNN by a small amount of true field patterns generated through a full model. The advantages include the rapid generation of large amount of data through the simplified model and the high reconstruction accuracy through a careful design of the deep transfer learning. Here, the CNN trained through the deep transfer learning can accurately reconstruct the lateral extent and direction of fractures with unseen conductivity and white Gaussian noise, showing a notable acceleration/accuracy enhancement over the previous CNN trained by mixing a small number of true data into the approximated data as data augmentation.

02 PETROLEUM↗

Iterative Learning Control for Video-rate Atomic Force Microscopy

We present a control scheme for video-rate atomic force microscopy with rosette pattern. The controller structure involves a feedback internal-model-based controller and a feedforward iterative learning controller. The iterative learning controller is designed to improve tracking performance of the feedback-controlled scanner by rejecting the repetitive disturbances arising from the system nonlinearities. We investigate the performance of two inversion techniques for constructing the learning filter. We conduct tracking experiments using a two-degree-of-freedom microelectromechanical system (MEMS) nanopositioner at frame rates ranging from 5 to 20 frames per second. Furthermore, the results reveal that the algorithm converges rapidly and the iterative learning controller significantly reduces both the transient and steady-state tracking errors. We acquire and report a series of high-resolution time-lapsed video-rate AFM images with the rosette pattern.

42 ENGINEERING↗

Risk-Aware Reinforcement Learning Framework for User-Centric O-RAN

The evolution of Open Radio Access Networks (O-RAN) presents an opportunity to enhance network performance by enabling dynamic orchestration of configuration and optimization parameters (COPs) through online learning methods. However, leveraging this potential requires overcoming the limitations of traditional cell-centric RAN architectures, which lack the necessary flexibility. On the other hand, despite their recent popularity, the practical deployment of online learning frameworks, such as Deep Reinforcement Learning (DRL)-based COP optimization solutions, remains limited due to their risk of deteriorating network performance during the exploration phase. In this article, we propose and analyze a novel risk-aware DRL framework for user-centric RAN (UC-RAN), which offers both the architectural flexibility and COP optimization to exploit this flexibility. We investigate and identify UC-RAN COPs that can be optimized via a soft actor-critic algorithm implementable as an O-RAN application (rApp) to jointly maximize latency satisfaction, reliability satisfaction, area spectral efficiency, and energy efficiency. We use the offline learning on UC-RAN to reliably accelerate DRL training, thus minimizing the risk of DRL deteriorating cellular network performance. Results show that our proposed solution approaches near-optimal performance in just a few hundred iterations with a decrease in risk score by a factor of ten.

6G and beyond↗

Neural Lyapunov Control for Power System Transient Stability: A Deep Learning-Based Approach

We report that power system control and transient stability analysis play essential roles in secure system operation. Control of power systems typically involves highly nonlinear and complex dynamics. Most of the existing works address such problems with additional assumptions in system dynamics, leading to a requirement for a complete and general solution. This paper, therefore, proposes a novel control framework for various power system control and stability problems leveraging a learning-based approach. The proposed framework includes a two-module structure that iteratively and jointly learns the candidate Lyapunov function and control law via deep neural networks in a learning module. Meanwhile, it guides the learning procedure towards valid results satisfying Lyapunov conditions in a falsification module. The introduced termination criteria ensure provable system stability. This control framework is verified through several studies handling different types of power system control problems. The results show that the proposed framework is generalizable and can simplify the control design for complex power systems with the stability guarantee and enlarged region of attraction.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

97 MATHEMATICS AND COMPUTING↗

Robust Decentralized Learning Using ADMM With Unreliable Agents

Many signal processing and machine learning problems can be formulated as consensus optimization problems which can be solved efficiently via a cooperative multi-agent system. However, the agents in the system can be unreliable due to a variety of reasons: noise, faults and attacks. Providing erroneous updates leads the optimization process in a wrong direction, and degrades the performance of distributed machine learning algorithms. This paper considers the problem of decentralized learning using ADMM in the presence of unreliable agents. First, we rigorously analyze the effect of erroneous updates (in ADMM learning iterations) on the convergence behavior of the multi-agent system. We show that the algorithm linearly converges to a neighborhood of the optimal solution under certain conditions and characterize the neighborhood size analytically. Next, we provide guidelines for network design to achieve a faster convergence to the neighborhood. Here, we also provide conditions on the erroneous updates for exact convergence to the optimal solution. Finally, to mitigate the influence of unreliable agents, we propose ROAD , a robust variant of ADMM, and show its resilience to unreliable agents with an exact convergence to the optimum.

97 MATHEMATICS AND COMPUTING↗

Machine learning to classify animal species in camera trap images: Applications in ecology

Motion-activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, typically by visually observing each image, in order to extract data that can be used in ecological analyses. We trained machine learning models using convolutional neural networks with the ResNet-18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an independent subset of images not seen during training from the United States and on an out-of-sample (or “out-of-distribution” in the machine learning literature) dataset of ungulate images from Canada. We also tested the ability of our model to distinguish empty images from those with animals in another out-of-sample dataset from Tanzania, containing a faunal community that was novel to the model. The trained model classified approximately 2,000 images per minute on a laptop computer with 16 gigabytes of RAM. The trained model achieved 98% accuracy at identifying species in the United States, the highest accuracy of such a model to date. Out-of-sample validation from Canada achieved 82% accuracy and correctly identified 94% of images containing an animal in the dataset from Tanzania. We provide an r package (Machine Learning for Wildlife Image Classification) that allows the users to (a) use the trained model presented here and (b) train their own model using classified images of wildlife from their studies. The use of machine learning to rapidly and accurately classify wildlife in camera trap images can facilitate non-invasive sampling designs in ecological studies by reducing the burden of manually analysing images. Our r package makes these methods accessible to ecologists.

54 ENVIRONMENTAL SCIENCES↗

Prevention of a wrong-location misadministration through the use of an intradepartmental incident learning system

Purpose: A series of examples are presented in which potential errors in the delivery of radiation therapy were prevented through use of incident learning. These examples underscore the value of reporting near miss incidents. Methods: Using a departmental incident learning system, eight incidents were noted over a two-year period in which fields were treated 'out-of-sequence,' that is, fields from a boost phase were treated, while the patient was still in the initial phase of treatment. As a result, an error-prevention policy was instituted in which radiation treatment fields are 'hidden' within the oncology information system (OIS) when they are not in current use. In this way, fields are only available to be treated in the intended sequence and, importantly, old fields cannot be activated at the linear accelerator control console. Results: No out-of-sequence treatments have been reported in more than two years since the policy change. Furthermore, at least three near-miss incidents were detected and corrected as a result of the policy change. In the first two, the policy operated as intended to directly prevent an error in field scheduling. In the third near-miss, the policy operated 'off target' to prevent a type of error scenario that it was not directly intended to prevent. In this incident, an incorrect digitally reconstructed radiograph (DRR) was scheduled in the OIS for a patient receiving lung cancer treatment. The incorrect DRR had an isocenter which was misplaced by approximately two centimeters. The error was a result of a field from an old plan being scheduled instead of the intended new plan. As a result of the policy described above, the DRR field could not be activated for treatment however and the error was discovered and corrected. Other quality control barriers in place would have been unlikely to have detected this error. Conclusions: In these examples, a policy was adopted based on incident learning, which prevented several errors, at least one of which was potentially severe. These examples underscore the need for a rigorous, systematic incident learning process within each clinic. The experiences reported in this technical note demonstrate the value of near-miss incident reporting to improve patient safety.

60 APPLIED LIFE SCIENCES↗

SU-E-P-04: Transport Theory Learning Module in the Maple Environment

Purpose: The medical physics graduate program at the University of Miami is developing a computerized instructional module which provides an interactive mechanism for students to learn transport theory. While not essential in the medical physics curriculum, transport theory should be taught because the conceptual level of transport theory is fundamental, a substantial literature exists and ought to be accessible, and students should understand commercial software which solves the Boltzmann equation.But conventional teaching and learning of transport theory is challenging. Students may be under prepared to appreciate its methods, results, and relevance, and it is not substantially addressed in textbooks for the medical physicists. Other resources an instructor might reasonably use, while excellent, may be too briskly paced for beginning students. The purpose of this work is to render teaching of transport theory more tractable by making learning highly interactive. Methods: The module is being developed in the Maple mathematics environment by instructors and graduate students. It will refresh the students' knowledge of vector calculus and differential equations, and will develop users' intuition for phase space concepts. Scattering concepts will be developed with animated simulations using tunable parameters characterizing interactions, so that students may develop a “feel” for cross section. Transport equations for one and multiple types of radiation will be illustrated with phase space animations. Numerical methods of solution will be illustrated. Results: Attempts to teach rudiments of transport theory in radiation physics and dosimetry courses using conventional classroom techniques at the University of Miami have had small success, because classroom time is limited and the material has been hard for our students to appreciate intuitively. Conclusion: A joint effort of instructor and students to teach and learn transport theory by building an interactive description of it will lead to deeper appreciation of the transport theoretical underpinnings of dosimetry.

61 RADIATION PROTECTION AND DOSIMETRY↗

MO-G-17A-05: PET Image Deblurring Using Adaptive Dictionary Learning

Purpose: The aim of this work is to deblur PET images while suppressing Poisson noise effects using adaptive dictionary learning (DL) techniques. Methods: The model that relates a blurred and noisy PET image to the desired image is described as a linear transform y=Hm+n where m is the desired image, H is a blur kernel, n is Poisson noise and y is the blurred image. The approach we follow to recover m involves the sparse representation of y over a learned dictionary, since the image has lots of repeated patterns, edges, textures and smooth regions. The recovery is based on an optimization of a cost function having four major terms: adaptive dictionary learning term, sparsity term, regularization term, and MLEM Poisson noise estimation term. The optimization is solved by a variable splitting method that introduces additional variables. We simulated a 128×128 Hoffman brain PET image (baseline) with varying kernel types and sizes (Gaussian 9×9, σ=5.4mm; Uniform 5×5, σ=2.9mm) with additive Poisson noise (Blurred). Image recovery was performed once when the kernel type was included in the model optimization and once with the model blinded to kernel type. The recovered image was compared to the baseline as well as another recovery algorithm PIDSPLIT+ (Setzer et. al.) by calculating PSNR (Peak SNR) and normalized average differences in pixel intensities (NADPI) of line profiles across the images. Results: For known kernel types, the PSNR of the Gaussian (Uniform) was 28.73 (25.1) and 25.18 (23.4) for DL and PIDSPLIT+ respectively. For blinded deblurring the PSNRs were 25.32 and 22.86 for DL and PIDSPLIT+ respectively. NADPI between baseline and DL, and baseline and blurred for the Gaussian kernel was 2.5 and 10.8 respectively. Conclusion: PET image deblurring using dictionary learning seems to be a good approach to restore image resolution in presence of Poisson noise. GE Health Care.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

WE-G-18A-04: 3D Dictionary Learning Based Statistical Iterative Reconstruction for Low-Dose Cone Beam CT Imaging

Purpose: To develop a 3D dictionary learning based statistical reconstruction algorithm on graphic processing units (GPU), to improve the quality of low-dose cone beam CT (CBCT) imaging with high efficiency. Methods: A 3D dictionary containing 256 small volumes (atoms) of 3x3x3 voxels was trained from a high quality volume image. During reconstruction, we utilized a Cholesky decomposition based orthogonal matching pursuit algorithm to find a sparse representation on this dictionary basis of each patch in the reconstructed image, in order to regularize the image quality. To accelerate the time-consuming sparse coding in the 3D case, we implemented our algorithm in a parallel fashion by taking advantage of the tremendous computational power of GPU. Evaluations are performed based on a head-neck patient case. FDK reconstruction with full dataset of 364 projections is used as the reference. We compared the proposed 3D dictionary learning based method with a tight frame (TF) based one using a subset data of 121 projections. The image qualities under different resolutions in z-direction, with or without statistical weighting are also studied. Results: Compared to the TF-based CBCT reconstruction, our experiments indicated that 3D dictionary learning based CBCT reconstruction is able to recover finer structures, to remove more streaking artifacts, and is less susceptible to blocky artifacts. It is also observed that statistical reconstruction approach is sensitive to inconsistency between the forward and backward projection operations in parallel computing. Using high a spatial resolution along z direction helps improving the algorithm robustness. Conclusion: 3D dictionary learning based CBCT reconstruction algorithm is able to sense the structural information while suppressing noise, and hence to achieve high quality reconstruction. The GPU realization of the whole algorithm offers a significant efficiency enhancement, making this algorithm more feasible for potential clinical application. A high zresolution is preferred to stabilize statistical iterative reconstruction. This work was supported in part by NIH(1R01CA154747-01), NSFC((No. 61172163), Research Fund for the Doctoral Program of Higher Education of China (No. 20110201110011), China Scholarship Council.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Automatic learning-based beam angle selection for thoracic IMRT

Purpose: The treatment of thoracic cancer using external beam radiation requires an optimal selection of the radiation beam directions to ensure effective coverage of the target volume and to avoid unnecessary treatment of normal healthy tissues. Intensity modulated radiation therapy (IMRT) planning is a lengthy process, which requires the planner to iterate between choosing beam angles, specifying dose–volume objectives and executing IMRT optimization. In thorax treatment planning, where there are no class solutions for beam placement, beam angle selection is performed manually, based on the planner’s clinical experience. The purpose of this work is to propose and study a computationally efficient framework that utilizes machine learning to automatically select treatment beam angles. Such a framework may be helpful for reducing the overall planning workload. Methods: The authors introduce an automated beam selection method, based on learning the relationships between beam angles and anatomical features. Using a large set of clinically approved IMRT plans, a random forest regression algorithm is trained to map a multitude of anatomical features into an individual beam score. An optimization scheme is then built to select and adjust the beam angles, considering the learned interbeam dependencies. The validity and quality of the automatically selected beams evaluated using the manually selected beams from the corresponding clinical plans as the ground truth. Results: The analysis included 149 clinically approved thoracic IMRT plans. For a randomly selected test subset of 27 plans, IMRT plans were generated using automatically selected beams and compared to the clinical plans. The comparison of the predicted and the clinical beam angles demonstrated a good average correspondence between the two (angular distance 16.8° ± 10°, correlation 0.75 ± 0.2). The dose distributions of the semiautomatic and clinical plans were equivalent in terms of primary target volume coverage and organ at risk sparing and were superior over plans produced with fixed sets of common beam angles. The great majority of the automatic plans (93%) were approved as clinically acceptable by three radiation therapy specialists. Conclusions: The results demonstrated the feasibility of utilizing a learning-based approach for automatic selection of beam angles in thoracic IMRT planning. The proposed method may assist in reducing the manual planning workload, while sustaining plan quality.

60 APPLIED LIFE SCIENCES↗

SU-A-210-01: Why Should We Learn Radiation Oncology Billing?

The purpose of this student annual meeting is to address topics that are becoming more relevant to medical physicists, but are not frequently addressed, especially for students and trainees just entering the field. The talk is divided into two parts: medical billing and regulations. Hsinshun Wu – Why should we learn radiation oncology billing? Many medical physicists do not like to be involved with medical billing or coding during their career. They believe billing is not their responsibility and sometimes they even refuse to participate in the billing process if given the chance. This presentation will talk about a physicist’s long career and share his own experience that knowing medical billing is not only important and necessary for every young medical physicist, but that good billing knowledge could provide a valuable contribution to his/her medical physics development. Learning Objectives: The audience will learn the basic definition of Current Procedural Terminology (CPT) codes performed in a Radiation Oncology Department. Understand the differences between hospital coding and physician-based or freestanding coding. Apply proper CPT coding for each Radiation Oncology procedure. Each procedure with its specific CPT code will be discussed in detail. The talk will focus on the process of care and use of actual workflow to understand each CPT code. Example coding of a typical Radiation Oncology procedure. Special procedure coding such as brachytherapy, proton therapy, radiosurgery, and SBRT. Maryann Abogunde – Medical physics opportunities at the Nuclear Regulatory Commission (NRC) The NRC’s responsibilities include the regulation of medical uses of byproduct (radioactive) materials and oversight of medical use end-users (licensees) through a combination of regulatory requirements, licensing, safety oversight including inspection and enforcement, operational experience evaluation, and regulatory support activities. This presentation will explore the career options for medical physicists in the NRC, how the NRC interacts with clinical medical physicists, and a physicist’s experience as a regulator. Learning Objectives: Explore non-clinical career pathways for medical physics students and trainees at the Nuclear Regulatory Commission. Overview of NRC medical applications and medical use regulations. Understand the skills needed for physicists as regulators. Abogunde is funded to attend the meeting by her employer, the NRC.

07 ISOTOPE AND RADIATION SOURCES↗

WE-G-BRA-01: Patient Safety and Treatment Quality Improvement Through Incident Learning: Experience of a Non-Academic Proton Therapy Center

Purpose: Incident learning has been proven to improve patient safety and treatment quality in conventional radiation therapy. However, its application in proton therapy has not been reported yet to our knowledge. In this study, we report our experience in developing and implementation of an in-house incident learning system. Methods: An incident learning system was developed based on published principles and tailored for our clinical practice and available resource about 18 months ago. The system includes four layers of error detection and report: 1) dosimetry peer review; 2) physicist plan quality assurance (QA); 3) treatment delivery issue on call and record; and 4) other incident report. The first two layers of QA and report were mandatory for each treatment plan through easy-to-use spreadsheets that are only accessible by the dosimetry and physicist departments. The treatment delivery issues were recorded case by case by the on call physicist. All other incidents were reported through an online incident report system, which can be anonymous. The incident report includes near misses on planning and delivery, process deviation, machine issues, work flow and documentation. Periodic incident reviews were performed. Results: In total, about 116 errors were reported through dosimetry review, 137 errors through plan QA, 83 treatment issues through physics on call record, and 30 through the online incident report. Only 8 incidents (2.2%) were considered to have a clinical impact to patients, and the rest of errors were either detected before reaching patients or had negligible dosimetric impact (<5% dose variance). Personnel training & process improvements were implemented upon periodic incident review. Conclusion: An incident learning system can be helpful in personnel training, error reduction, and patient safety and treatment quality improvement. The system needs to be catered for each clinic’s practice and available resources. Incident and knowledge sharing among proton centers are encouraged.

60 APPLIED LIFE SCIENCES↗

MO-DE-207A-05: Dictionary Learning Based Reconstruction with Low-Rank Constraint for Low-Dose Spectral CT

Purpose: Spectral CT enabled by an energy-resolved photon-counting detector outperforms conventional CT in terms of material discrimination, contrast resolution, etc. One reconstruction method for spectral CT is to generate a color image from a reconstructed component in each energy channel. However, given the radiation dose, the number of photons in each channel is limited, which will result in strong noise in each channel and affect the final color reconstruction. Here we propose a novel dictionary learning method for spectral CT that combines dictionary-based sparse representation method and the patch based low-rank constraint to simultaneously improve the reconstruction in each channel and to address the inter-channel correlations to further improve the reconstruction. Methods: The proposed method has two important features: (1) guarantee of the patch based sparsity in each energy channel, which is the result of the dictionary based sparse representation constraint; (2) the explicit consideration of the correlations among different energy channels, which is realized by patch-by-patch nuclear norm-based low-rank constraint. For each channel, the dictionary consists of two sub-dictionaries. One is learned from the average of the images in all energy channels, and the other is learned from the average of the images in all energy channels except the current channel. With average operation to reduce noise, these two dictionaries can effectively preserve the structural details and get rid of artifacts caused by noise. Combining them together can express all structural information in current channel. Results: Dictionary learning based methods can obtain better results than FBP and the TV-based method. With low-rank constraint, the image quality can be further improved in the channel with more noise. The final color result by the proposed method has the best visual quality. Conclusion: The proposed method can effectively improve the image quality of low-dose spectral CT. This work is partially supported by the National Natural Science Foundation of China (No. 61302136), and the Natural Science Basic Research Plan in Shaanxi Province of China (No. 2014JQ8317).

60 APPLIED LIFE SCIENCES↗

Poster - 27: Incident Learning Practices in Ontario

Purpose: The Radiation Incident and Safety Committee (RISC), established and supported by Cancer Care Ontario (CCO), is responsible for advising the Provincial Head of the Radiation Treatment program on matters relating to provincial reporting of radiation incidents with the goal of improved risk mitigation. Methods: The committee is made up of Radiation Incident Leads (RILs) with representation from each of the 14 radiation medicine programs in the province. RISC routinely meets to review recent critical incidents and to discuss provincial reporting processes and future directions of the committee. Regular face to face meetings have provided an excellent venue for sharing incident learning practices. A summary of the incident learning practices across Ontario has been compiled. Results: Almost all programs in Ontario employ an incident learning committee to review incidents and identify corrective actions or process improvements. Tools used for incident reporting include: paper based reporting, a number of different commercial products and software solutions developed in-house. A wide range of classification schema (data taxonomies) are employed, although most have been influenced by national guidance documents. The majority of clinics perform root cause analyses but utilized methodologies vary significantly. Conclusions: Most programs in Ontario employ a committee approach to incident learning. However, the reporting tools and taxonomies in use vary greatly which represents a significant challenge to provincial reporting. RISC is preparing to adopt the National System for Incident Reporting – Radiation Therapy (NSIR-RT) which will standardize incident reporting and facilitate data analyses aimed at identifying targeted improvement initiatives.

60 APPLIED LIFE SCIENCES↗

Sci-Fri AM: Quality, Safety, and Professional Issues 04: Predicting waiting times in Radiation Oncology using machine learning

We describe a method for predicting waiting times in radiation oncology. Machine learning is a powerful predictive modelling tool that benefits from large, potentially complex, datasets. The essence of machine learning is to predict future outcomes by learning from previous experience. The patient waiting experience remains one of the most vexing challenges facing healthcare. Waiting time uncertainty can cause patients, who are already sick and in pain, to worry about when they will receive the care they need. In radiation oncology, patients typically experience three types of waiting: Waiting at home for their treatment plan to be prepared Waiting in the waiting room for daily radiotherapy Waiting in the waiting room to see a physician in consultation or follow-up These waiting periods are difficult for staff to predict and only rough estimates are typically provided, based on personal experience. In the present era of electronic health records, waiting times need not be so uncertain. At our centre, we have incorporated the electronic treatment records of all previously-treated patients into our machine learning model. We found that the Random Forest Regression model provides the best predictions for daily radiotherapy treatment waiting times (type 2). Using this model, we achieved a median residual (actual minus predicted value) of 0.25 minutes and a standard deviation residual of 6.5 minutes. The main features that generated the best fit model (from most to least significant) are: Allocated time, median past duration, fraction number and the number of treatment fields.

60 APPLIED LIFE SCIENCES↗