Results for “predicted” — Page 27

DOE OSTI2022

Mechanical loading prediction through accelerometry data during walking and running

ABSTRACT Currently, there is no way to assess mechanical loading variables such as peak ground reaction forces (pGRF) and peak loading rate (pLR) in clinical settings. The purpose of this study was to develop accelerometry‐based equations to predict both pGRF and pLR during walking and running. One hundred and thirty one subjects (79 females; 76.9 ± 19.6 kg) walked and ran at different speeds (2–14 km·h −1 ) on a force plate–instrumented treadmill while wearing accelerometers at their ankle, lower back and hip. Regression equations were developed to predict pGRF and pLR from accelerometry data. Leave‐one‐out cross‐validation was used to calculate prediction accuracy and Bland–Altman plots. Our pGRF prediction equation was compared with a reference equation previously published. Body mass and peak acceleration were included for pGRF prediction and body mass and peak acceleration rate for pLR prediction. All pGRF equation coefficients of determination were above 0.96, and a good agreement between actual and predicted pGRF was observed, with a mean absolute percent error (MAPE) below 7.3%. Accuracy indices from our equations were better than previously developed equations. All pLR prediction equations presented a lower accuracy compared to those developed to predict pGRF. Walking and running pGRF can be predicted with high accuracy by accelerometry‐based equations, representing an easy way to determine mechanical loading in free‐living conditions. The pLR prediction equations yielded a somewhat lower prediction accuracy compared with the pGRF equations.

Veras, Lucas↗

DOE OSTI2016

SU-F-R-04: Radiomics for Survival Prediction in Glioblastoma (GBM)

Purpose: To develop a quantitative radiomics approach for survival prediction of glioblastoma (GBM) patients treated with chemoradiotherapy (CRT). Methods: 28 GBM patients who received CRT at our institution were retrospectively studied. 255 radiomic features were extracted from 3 gadolinium-enhanced T1 weighted MRIs for 2 regions of interest (ROIs) (the surgical cavity and its surrounding enhancement rim). The 3 MRIs were at pre-treatment, 1-month and 3-month post-CRT. The imaging features comprehensively quantified the intensity, spatial variation (texture), geometric property and their spatial-temporal changes for the 2 ROIs. 3 demographics features (age, race, gender) and 12 clinical parameters (KPS, extent of resection, whether concurrent temozolomide was adjusted/stopped and radiotherapy related information) were also included. 4 Machine learning models (logistic regression (LR), support vector machine (SVM), decision tree (DT), neural network (NN)) were applied to predict overall survival (OS) and progression-free survival (PFS). The number of cases and percentage of cases predicted correctly were collected and AUC (area under the receiver operating characteristic (ROC) curve) were determined after leave-one-out cross-validation. Results: From univariate analysis, 27 features (1 demographic, 1 clinical and 25 imaging) were statistically significant (p<0.05) for both OS and PFS. Two sets of features (each contained 24 features) were algorithmically selected from all features to predict OS and PFS. High prediction accuracy of OS was achieved by using NN (96%, 27 of 28 cases were correctly predicted, AUC = 0.99), LR (93%, 26 of 28 cases were correctly predicted, AUC = 0.95) and SVM (93%, 26 of 28 cases were correctly predicted, AUC = 0.90). When predicting PFS, NN obtained the highest prediction accuracy (89%, 25 of 28 cases were correctly predicted, AUC = 0.92). Conclusion: Radiomics approach combined with patients’ demographics and clinical parameters can accurately predict survival in GBM patients treated with CRT.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Predicting Volume of Distribution in Humans: Performance of In Silico Methods for a Large Set of Structurally Diverse Clinical Compounds

Volume of distribution at steady state (V D,ss ) is one of the key pharmacokinetic parameters estimated during the drug discovery process. Despite considerable efforts to predict V D,ss , accuracy and choice of prediction methods remain a challenge, with evaluations constrained to a small set (<150) of compounds. To address these issues, a series of in silico methods for predicting human V D,ss directly from structure were evaluated using a large set of clinical compounds. Machine learning (ML) models were built to predict V D,ss directly and to predict input parameters required for mechanistic and empirical V D,ss predictions. In addition, log D, fraction unbound in plasma (fup), and blood-to-plasma partition ratio (BPR) were measured on 254 compounds to estimate the impact of measured data on predictive performance of mechanistic models. Furthermore, the impact of novel methodologies such as measuring partition (Kp) in adipocytes and myocytes (n = 189) on V D,ss predictions was also investigated. In predicting V D,ss directly from chemical structures, both mechanistic and empirical scaling using a combination of predicted rat and dog V D,ss demonstrated comparable performance (62%–71% within 3-fold). The direct ML model outperformed other in silico methods (75% within 3-fold, r 2 = 0.5, AAFE = 2.2) when built from a larger data set. Scaling to human from predicted V D,ss of either rat or dog yielded poor results (<47% within 3-fold). Measured fup and BPR improved performance of mechanistic V D,ss predictions significantly (81% within 3-fold, r 2 = 0.6, AAFE = 2.0). Adipocyte intracellular Kp showed good correlation to the V D,ss but was limited in estimating the compounds with low V D,ss .

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Long term predictions of coal fired power plant data using evolved recurrent neural networks

Abstract This work presents an investigation into the ability of recurrent neural networks (RNNs) to provide long term predictions of time series data generated by coal fired power plants. While there are numerous studies which have used artificial neural networks (ANNs) to predict coal plant parameters, to the authors’ knowledge these have almost entirely been restricted to predicting values at the next time step, and not farther into the future. Using a novel neuro-evolution strategy called Evolutionary eXploration of Augmenting Memory Models (EXAMM), we evolved RNNs with advanced memory cells to predict per-minute plant parameters and per-hour boiler parameters up to 8 hours into the future. These data sets were challenging prediction tasks as they involve spiking behavior in the parameters being predicted. While the evolved RNNs were able to successfully predict the spikes in the hourly data they did not perform very well in accurately predicting their severity. The per-minute data proved even more challenging as medium range predictions miscalculated the beginning and ending of spikes, and longer range predictions reverted to long term trends and ignored the spikes entirely. We hope this initial study will motivate further study into this highly challenging prediction problem. The use of fuel properties data generated by a new Coal Tracker Optimization (CTO) program was also investigated and this work shows that their use improved predictive ability of the evolved RNNs.

Automation & Control Systems↗

DOE OSTI2018

Teaching Game Theory to Kids and Limits of Prediction

I have once been asked to read a lecture to a group of 6th graders on Game Theory. After agreeing to it, I realized that explaining the game theory basics to 6th graders my be difficult, given that terms such as Nash equilibrium, minimax, maximin, optimization may not resonate in a 6th grade classroom. Instead I've introduced game theory using the rock-paper-scissors (RPS) game. Turns out kids are excellent gametheoreticians. In RPS, they understood both the benefits of randomizing their own strategy and of predicting their opponent's moves. They offered a number of heuristics both for the prediction and opening move. These heuristics included optimizing against past opponent moves, such as not playing rock if the opponent just played scissors, and playing a specific opening hand, such as "paper". Visualizing the effects of such strategic choices on-the-fly would be interesting and educational. This brief essay attempts demonstrating and visualizing the value of a few different strategic options in RPS. Specifically, we would like to illustrate the following: 1) what is the value of being unpredictable?; and 2) what is the value of being able to predict your opponent? In regard to prediction of human players, the question 2) has been reflected in Jon McLoone's entry in Wolfram Blog from January 20, 2014[1]. McLoone created a predictive algorithm for playing against human opponents, that learns to beat human opponents reliably after approximately 30 - 40 games. I use McLoone's implementation to represent a predictive and random strategies. The rest of this documents 1) investigates performance of this predictive strategy against a random strategy (which is optimal in RPS) and in 2) attempts to turn this predictive power against the predictive strategy by allowing the opponent the full knowledge of the predictor's strategy (but not the choices made using the strategy). This exposes a weakness in predictions made without taking risks into account by illustrating that predictive strategy may make the predictor predictable as well.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

Validation of finite element and boundary element methods for predicting structural vibration and radiated noise

Analytical and experimental validation of methods to predict structural vibration and radiated noise are presented. A rectangular box excited by a mechanical shaker was used as a vibrating structure. Combined finite element method (FEM) and boundary element method (BEM) models of the apparatus were used to predict the noise radiated from the box. The FEM was used to predict the vibration, and the surface vibration was used as input to the BEM to predict the sound intensity and sound power. Vibration predicted by the FEM model was validated by experimental modal analysis. Noise predicted by the BEM was validated by sound intensity measurements. Three types of results are presented for the total radiated sound power: (1) sound power predicted by the BEM modeling using vibration data measured on the surface of the box; (2) sound power predicted by the FEM/BEM model; and (3) sound power measured by a sound intensity scan. The sound power predicted from the BEM model using measured vibration data yields an excellent prediction of radiated noise. The sound power predicted by the combined FEM/BEM model also gives a good prediction of radiated noise except for a shift of the natural frequencies that are due to limitations in the FEM model.

Seybert, A. F.↗

NASA NTRSDate not supplied

Accuracy Assessment of Two Gps Fidelity Prediction Services in Urban Terrain

Low altitude flight in urban areas is susceptible to degraded GNSS-based navigation system performance due to terrain interference with radio signals from orbital positioning satellites. Predictive navigation performance fidelity tools are needed a) in preflight planning to assist in the creation of safe flight paths and b) in-flight to provide contingency management agents with the navigation risk of proximal flight corridors. Two navigation fidelity prediction services are validated by comparison with over 6000 readings from GNSS sensors collected along a five-mile path through urban areas of Corpus Christi, Texas, on three dates in 2022. Predictions are based on satellite line of sight through 3D terrain data collected in 2018. Each service predicts a set of navigation fidelity metrics over a user-specified time period. One metric estimated by both is the number of visible satellites. A direct comparison of the number of predicted visible satellites with the number sensed by the receiver is used to validate the prediction services. Results show an exact match in the number of predicted satellites for 60% of the measurements, and a match within +/- 4 satellites for 95% of the measurements. As expected, agreement improves away from vertical blocking terrain. Most cases of mismatch are due a lower predicted count than measured (false negatives), and can be accounted for by receiver pickup of stray signals caused by multipath propagation. About 10% of mismatches are false positives and are mostly accounted for by foliage effects. The two services predict visibility of the same set of satellites 80% of the time, differ by two or less satellites 95% of the time, and can compute predictions for one hour of observations in one minute or less. Validation is analyzed statistically and in detailed case studies of selected observation times. The prediction services validated in this study run fast enough for preflight safety planning. The more stringent challenge of inflight navigation fidelity prediction for contingency management requires both a speedup of the current level of modeling and equally fast stray signal modeling.

Andrew Moore↗

NASA NTRSDate not supplied

Accuracy Assessment of Two GPS Fidelity Prediction Services in Urban Terrain

Low altitude flight in urban areas is susceptible to degraded GNSS-based navigation system performance due to terrain interference with radio signals from orbital positioning satellites. Predictive navigation performance fidelity tools are needed a) in preflight planning to assist in the creation of safe flight paths and b) in-flight to provide contingency management agents with the navigation risk of proximal flight corridors. Two navigation fidelity prediction services are validated by comparison with over 6000 readings from GNSS sensors collected along a five-mile path through urban areas of Corpus Christi, Texas, on three dates in 2022. Predictions are based on satellite line of sight through 3D terrain data collected in 2018. Each service predicts a set of navigation fidelity metrics over a user-specified time period. One metric estimated by both is the number of visible satellites. A direct comparison of the number of predicted visible satellites with the number sensed by the receiver is used to validate the prediction services. Results show an exact match in the number of predicted satellites for 60% of the measurements, and a match within +/- 4 satellites for 95% of the measurements. As expected, agreement improves away from vertical blocking terrain. Most cases of mismatch are due a lower predicted count than measured (false negatives), and can be accounted for by receiver pickup of stray signals caused by multipath propagation. About 10% of mismatches are false positives and are mostly accounted for by foliage effects. The two services predict visibility of the same set of satellites 80% of the time, differ by two or less satellites 95% of the time, and can compute predictions for one hour of observations in one minute or less. Validation is analyzed statistically and in detailed case studies of selected observation times. The prediction services validated in this study run fast enough for preflight safety planning. The more stringent challenge of inflight navigation fidelity prediction for contingency management requires both a speedup of the current level of modeling and equally fast stray signal modeling.

Andrew J. Moore↗

NASA NTRS2024

Celebrating 10 Years of the Sub-Seasonal to Seasonal Prediction Project and Looking to the Future

The conference clearly demonstrated the increasing interest and growth of the scientific community working on the development and application of sub-seasonal to seasonal prediction since the start of the World Weather Research Programme (WWRP)/World Climate Research Programme (WCRP) sub-seasonal to seasonal (S2S) prediction project in 2013. The conference, which was held at the University of Reading (United Kingdom), was organized into three main themes as briefly summarized below, with eleven invited talks, 74 oral contributed talks, and 101 posters. The conference also included a two-hour breakout session, wherein eight groups discussed the current state and prospect for S2S prediction, and an early career researcher event. A summary of these discussions and recommendations is presented below. The conference web page (https://research.reading.ac.uk/s2s-summit2023/) is archived at the University of Reading. Introductory comments by representatives of the World Meteorological Organization (WMO) WWRP and WCRP emphasized the importance of the weather–climate linkage, targeted by S2S forecasts (from 2 weeks to a season ahead), addressing the challenges of creating “end-to-end” forecasts that encompass the entire climate-services chain from the prediction science and forecast, to the development and issuing of forecast products tailored to informing user-decisions. They also emphasized the efficacy of multi-model ensemble efforts and databases to foster collaborations internationally and between operational centres and academia. Although the WWRP/WCRP S2S project comes to an end in 2023, S2S prediction will remain an important focus for WWRP and WCRP. In WWRP, a new project called SAGE (Sub-seasonal to seasonal predictions for Agriculture and Environment) will start in 2024. Another important legacy of the S2S project will be the maintenance of the S2S database (Vitart et al. 2017) and the establishment of a WMO Lead Center for sub-seasonal prediction multi-model ensemble (LC-SSPMME) which will provide real-time multi-model S2S climate information. In two keynote presentations, Prof. Brian Hoskins (University of Reading) and Dr. Gilbert Brunet (Australian Bureau of Meteorology) discussed the potential of S2S predictability and the ongoing journey for understanding and improving these predictions. This conference was a sequel to the International Conference on Sub-seasonal to Seasonal Prediction (Robertson et al., 2014) which took place in College Park (Maryland, USA) in February 2014 to celebrate the start of the WWRP/WCRP S2S project, and to WCRP and WWRP conferences in Boulder, USA, in 2018 (Merryfield et al., 2020). A significant development compared to the previous S2S conferences was the large number of presentations on research to operation (R2O) and S2S applications and on the use of artificial intelligence and machine learning (AI/ML) methods for S2S prediction. Some of these methods provide empirical S2S forecasts which are competitive with state-of-the-art dynamical models. Other presentations demonstrated that AI/ML can provide alternative calibration of dynamical model outputs to traditional methods. Several talks and posters highlighted the increasing use of AI/ML, including deep learning, in S2S forecast post-processing and using AI to identify higher flow-dependent skill. Finally, some presentations demonstrated the value of AI/ML methods for a better understanding of S2S sources of predictability and attribution of extreme events.

S. J. Woolnough↗

DOE OSTI2021

CyProduct: A software tool for accurately predicting the byproducts of human cytochrome P450 metabolism

In silico metabolism prediction is a cheminformatic task of autonomously predicting the set of metabolic byproducts produced from a specified molecule and a set of enzymes or reactions. Here we describe a novel machine-learned in silico cytochrome P450 (CYP450) metabolism prediction suite, called CyProduct, that accurately predicts metabolic byproducts for a specified molecule and a human CYP450 isoform. It includes three modules: (1) CypReact, a tool that predicts if the query compound reacts with a given CYP450 enzyme; (2) CypBoM, a tool that accurately predicts the “bond site” of the reaction (i.e., which specific bonds within the query molecule react with the CYP isoform); and (3) MetaboGen, a tool that generates the metabolic byproducts based on CypBoM’s bond-site prediction. CyProduct predicts metabolic biotransformation products for each of the nine most important human CYP450 enzymes. CypBoM uses an important new concept called “Bond of Metabolism” (BoM), which extends the traditional “Site of Metabolism" (SoM) by specifying the information about the set of chemical bonds that is modified or formed in a metabolic reaction (rather than the specific atom). We created a BoM database for 3487 CYP450-mediated Phase I reactions, then used this to train the CypBoM Predictor to predict the reactive bond locations on substrate molecules. CypBoM Predictor’s cross-validated Jaccard score for reactive bond prediction ranged from 0.380 to 0.452 over the nine CYP450 enzymes. Over variants of a test set of 72 known CYP450 substrates and 30 non-reactants, CyProduct outperformed the other packages -- including ADMET Predictor, BioTransformer and GLORY -- by an average of 200% (wrt Jaccard score) in terms of predicting metabolites. The CyProduct suite and the datasets are freely available at https://bitbucket.org/wishartlab/cyproduct/src/master/.

Machine learning, Cytochrome P450, Metabolism pred↗

DOE OSTI2020

Ensemble transfer learning for the prediction of anti-cancer drug response

Abstract Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the power of transfer learning for three drug response prediction applications including drug repurposing, precision oncology, and new drug development, through different data partition schemes in cross-validation. We extend the classic transfer learning framework through ensemble and demonstrate its general utility with three representative prediction algorithms including a gradient boosting model and two deep neural networks. The ensemble transfer learning framework is tested on benchmark in vitro drug screening datasets. The results demonstrate that our framework broadly improves the prediction performance in all three drug response prediction applications with all three prediction algorithms.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Tandem Predictions for HPC Jobs

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

HPC↗

DOE OSTI2025

Tandem Predictions for HPC Jobs: Preprint

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Sensitivity analysis for characterizing the impact of HNGD model on the prediction of hydrogen redistribution in Zircaloy cladding using BISON code

Hydrogen in zirconium cladding is able to precipitate into zirconium hydrides which impacts cladding integrity. The Hydride Nucleation-Growth-Dissolution (HNGD) model in the BISON code accounts for the precipitation and dissolution kinetics of hydride in Zircaloy material. This paper presents global sensitivity analyses of the HNGD model aiming to enhance our understanding of the hydride precipitation phenomena by quantifying the variance that key parameters have on the prediction of hydrogen behavior under various environmental conditions. Here, model predictions are compared to experimental data obtained under two different conditions: 1) with uniformly precharged specimens subjected to a linear thermal gradient, and 2) specimens precharged with a cathodically applied hydride rim at one end of the sample and subjected to an asymmetric thermal gradient. The Sobol sensitivity analysis identifies the key parameters in the HNGD model for both types of specimens. For linear temperature cases, the heat of transport dominates the accuracy of predictions when no precipitation occurs at the cold end, while Terminal Solid Solubility for Dissolution (TSSD) is the most important parameter when precipitation occurs. A large variation in the predicted hydrogen concentration profiles is found in the range of high TSSD due to the occurrence of precipitation. For asymmetric temperature cases, the solubility coefficient gives the largest impact on the predicted hydrogen distribution, as it determines the amount of solute hydrogen dissolved from the initially applied hydride rim. A large discrepancy in hydrogen distribution between simulations and experiments exists with the asymmetric specimens because BISON simulations fail to predict the precipitation of hydride at the cooler end. Comparative studies using former and updated models verifies the significant impact of the hydride growth mechanism on predicted hydrogen concentration profiles. In particular, when hydride initially exists, changes in TSSD generate a large variation in the predicted amount of precipitation by hydride growth, giving large uncertainty in predicting the hydrogen distribution over the sample length. The outputs characterize the significant impact of the hydride growth mechanism in the HNGD model on predicting hydrogen behavior, and improve the understanding of the precipitation of hydride in Zircaloy cladding within a range of expected environmental conditions. The analyses indicate work is still needed to improve the hydride solvus models in the BISON code to accurately predict experimentally observed hydride concentrations and distributions.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Learning-Based Inversion-Free Model-Data Integration to Advance Ecosystem Model Prediction

Ecosystem model prediction is important for understanding ecosystem responses to climate change and for management support. Model prediction and quantification of predictive uncertainty of ecosystems have long been investigated. The traditional workflow, which calibrates models to match observations and then uses the calibrated models for predictions, relies heavily on inverse modeling to constrain uncertain parameters in complex forward models. This inversion-based prediction approach is infeasible for complex models with heterogeneous parameter uncertainties and incapable of rapid integration of streaming and multiple sources of data because of the difficulty and computational cost in the model inversion, which is typically ill-posed and can require hundreds of thousands of expensive forward simulations to be performed iteratively. We propose to circumvent inverse modeling by precomputing an ensemble of unconstrained forward simulations and then using machine learning (ML) methods to learn the statistical relationship between simulated observation and prediction quantities. Once the ML model has learned the relationship, it can be used to make predictions of future system behavior with uncertainty quantification based on observations. The proposed learningbased inversion-free model prediction (LIMP) framework is computationally efficient which only requires a few thousands of fully parallelizable forward simulations. Additionally, LIMP can continually update predictions based on streaming observations from multiple locations and sources without necessarily requiring extra model simulations. In this study, we apply LIMP to a regional terrestrial ecosystem model with 47 parameters for testing, refining, and evaluating the approach. We demonstrate that LIMP can be used for efficient model prediction, rapid data assimilation, and cost-effective experimental design for improving robust predictive understanding of ecosystems.

Lu, Dan↗

DOE OSTI2016

SU-D-BRB-01: A Comparison of Learning Methods for Knowledge Based Dose Prediction for Coplanar and Non-Coplanar Liver Radiotherapy

Purpose: The predictive power of knowledge based planning (KBP) has considerable potential in the development of automated treatment planning. Here, we examine the predictive capabilities and accuracy of previously reported KBP methods, as well as an artificial neural networks (ANN) method. Furthermore, we compare the predictive accuracy of these methods on coplanar volumetric-modulated arc therapy (VMAT) and non-coplanar 4π radiotherapy. Methods: 30 liver SBRT patients previously treated using coplanar VMAT were selected for this study. The patients were re-planned using 4π radiotherapy, which involves 20 optimally selected non-coplanar IMRT fields. ANNs were used to incorporate enhanced geometric information including liver and PTV size, prescription dose, patient girth, and proximity to beams. The performance of ANN was compared to three methods from statistical voxel dose learning (SVDL), wherein the doses of voxels sharing the same distance to the PTV are approximated by either taking the median of the distribution, non-parametric fitting, or skew-normal fitting. These three methods were shown to be capable of predicting DVH, but only median approximation can predict 3D dose. Prediction methods were tested using leave-one-out cross-validation tests and evaluated using residual sum of squares (RSS) for DVH and 3D dose predictions. Results: DVH prediction using non-parametric fitting had the lowest average RSS with 0.1176(4π) and 0.1633(VMAT), compared to 0.4879(4π) and 1.8744(VMAT) RSS for ANN. 3D dose prediction with median approximation had lower RSS with 12.02(4π) and 29.22(VMAT), compared to 27.95(4π) and 130.9(VMAT) for ANN. Conclusion: Paradoxically, although the ANNs included geometric features in addition to the distances to the PTV, it did not perform better in predicting DVH or 3D dose compared to simpler, faster methods based on the distances alone. The study further confirms that the prediction of 4π non-coplanar plans were more accurate than VMAT. NIH R43CA183390 and R01CA188300.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2016

SU-F-J-219: Predicting Ventilation Change Due to Radiation Therapy: Dependency On Pre-RT Ventilation and Effort Correction

Purpose: Ventilation change caused by radiation therapy (RT) can be predicted using four-dimensional computed tomography (4DCT) and image registration. This study tested the dependency of predicted post-RT ventilation on effort correction and pre-RT lung function. Methods: Pre-RT and 3 month post-RT 4DCT images were obtained for 13 patients. The 4DCT images were used to create ventilation maps using a deformable image registration based Jacobian expansion calculation. The post-RT ventilation maps were predicted in four different ways using the dose delivered, pre-RT ventilation, and effort correction. The pre-RT ventilation and effort correction were toggled to determine dependency. The four different predicted ventilation maps were compared to the post-RT ventilation map calculated from image registration to establish the best prediction method. Gamma pass rates were used to compare the different maps with the criteria of 2mm distance-to-agreement and 6% ventilation difference. Paired t-tests of gamma pass rates were used to determine significant differences between the maps. Additional gamma pass rates were calculated using only voxels receiving over 20 Gy. Results: The predicted post-RT ventilation maps were in agreement with the actual post-RT maps in the following percentage of voxels averaged over all subjects: 71% with pre-RT ventilation and effort correction, 69% with no pre-RT ventilation and effort correction, 60% with pre-RT ventilation and no effort correction, and 58% with no pre-RT ventilation and no effort correction. When analyzing only voxels receiving over 20 Gy, the gamma pass rates were respectively 74%, 69%, 65%, and 55%. The prediction including both pre- RT ventilation and effort correction was the only prediction with significant improvement over using no prediction (p<0.02). Conclusion: Post-RT ventilation is best predicted using both pre-RT ventilation and effort correction. This is the only prediction that provided a significant improvement on agreement. Research support from NIH grants CA166119 and CA166703, a gift from Roger Koch, and a Pilot Grant from University of Iowa Carver College of Medicine.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

PPCM: Combing Multiple Classifiers to Improve Protein-Protein Interaction Prediction

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using an assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. This pipeline will be useful for predicting PPI in nonmodel species.

59 BASIC BIOLOGICAL SCIENCES↗