Search NASA⌕ Search

SEARCH · Search NASA

Results for “random testing”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

A Phase 3 Trial of 2 Years of Androgen Suppression and Radiation Therapy With or Without Adjuvant Chemotherapy for High-Risk Prostate Cancer: Final Results of Radiation Therapy Oncology Group Phase 3 Randomized Trial NRG Oncology RTOG 9902

Purpose: Long-term (LT) androgen suppression (AS) with radiation therapy (RT) is a standard treatment of high-risk, localized prostate cancer (PCa). Radiation Therapy Oncology Group 9902 was a randomized trial testing the hypothesis that adjuvant combination chemotherapy (CT) with paclitaxel, estramustine, and oral etoposide plus LT AS plus RT would improve overall survival (OS). Methods and Materials: Patients with high-risk PCa (prostate-specific antigen 20-100 ng/mL and Gleason score [GS] ≥7 or clinical stage ≥T2 and GS ≥8) were randomized to RT and AS (AS + RT) alone or with adjuvant CT (AS + RT + CT). CT was given as four 21-day cycles, delivered beginning 28 days after 70.2 Gy of RT. AS was given as luteinizing hormone-releasing hormone for 24 months, beginning 2 months before RT plus an oral antiandrogen for 4 months before and during RT. The study was designed based on a 6% improvement in OS from 79% to 85% at 5 years, with 90% power and a 2-sided alpha of 0.05. Results: A total of 397 patients (380 eligible) were randomized. The patients had high-risk PCa, 68% with GS 8 to 10 and 34% T3 to T4 tumors, and median prostate-specific antigen of 22.6 ng/mL. The median follow-up period was 9.2 years. The trial closed early because of excess thromboembolic toxicity in the CT arm. The 10-year results for all randomized patients revealed no significant difference between the AS + RT and AS + RT + CT arms in OS (65% vs 63%; P=.81), biochemical failure (58% vs 54%; P=.82), local progression (11% vs 7%; P=.09), distant metastases (16% vs 14%; P=.42), or disease-free survival (22% vs 26%; P=.61). Conclusions: NRG Oncology RTOG 9902 showed no significant differences in OS, biochemical failure, local progression, distant metastases, or disease-free survival with the addition of adjuvant CT to LT AS + RT. The trial results provide valuable data regarding the natural history of high-risk PCa treated with LT AS + RT and have implications for the feasibility of clinical trial accrual and tolerability using CT for PCa.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2017

An Investigation into Solution Verification for CFD-DEM

This report presents the study of the convergence behavior of the computational fluid dynamicsdiscrete element method (CFD-DEM) method, specifically National Energy Technology Laboratory’s (NETL) open source MFiX code (MFiX-DEM) with a diffusion based particle-tocontinuum filtering scheme. In particular, this study focused on determining if the numerical method had a solution in the high-resolution limit where the grid size is smaller than the particle size. To address this uncertainty, fixed particle beds of two primary configurations were studied: i) fictitious beds where the particles are seeded with a random particle generator, and ii) instantaneous snapshots from a transient simulation of an experimentally relevant problem. Both problems considered a uniform inlet boundary and a pressure outflow. The CFD grid was refined from a few particle diameters down to 1/6 th of a particle diameter. The pressure drop between two vertical elevations, averaged across the bed cross-section was considered as the system response quantity of interest. A least-squares regression method was used to extrapolate the grid-dependent results to an approximate “grid-free” solution in the limit of infinite resolution. The results show that the diffusion based scheme does yield a converging solution. However, the convergence is more complicated than encountered in simpler, single-phase flow problems showing strong oscillations and, at times, oscillations superimposed on top of globally non-monotonic behavior. The challenging convergence behavior highlights the importance of using at least four grid resolutions in solution verification problems so that (over-determined) regression-based extrapolation methods may be applied to approximate the grid-free solution. The grid-free solution is very important in solution verification and VVUQ exercise in general as the difference between it and the reference solution largely determines the numerical uncertainty. By testing different randomized particle configurations of the same general problem (for the fictitious case) or different instances of freezing a transient simulation, the numerical uncertainties appeared to be on the same order of magnitude as ensemble or time averaging uncertainties. By testing different drag laws, almost all cases studied show that model form uncertainty in this one, very important closure relation was larger than the numerical uncertainty, at least with a reasonable CFD grid, roughly five particle diameters. In this study, the diffusion width (filtering length scale) was mostly set at a constant of six particle diameters. A few exploratory tests were performed to show that similar convergence behavior was observed for diffusion widths greater than approximately two particle diameters. However, this subject was not investigated in great detail because determining an appropriate filter size is really a validation question which must be determined by comparison to experimental or highly accurate numerical data. Future studies are being considered targeting solution verification of transient simulations as well as validation of the filter size with direct numerical simulation data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Nanoindentation of HMX and Idoxuridine to Determine Mechanical Similarity

Assessing the mechanical behavior (elastic properties, plastic properties, and fracture phenomena) of molecular crystals is often complicated by the difficulty in preparing samples. Pharmaceuticals and energetic materials in particular are often used in composite structures or tablets, where the individual grains can strongly impact the solid behavior. Nanoindentation is a convenient method to experimentally assess these properties, and it is used here to demonstrate the similarity in the mechanical properties of two distinct systems: individual crystals of the explosive cyclotetramethylene tetranitramine (HMX) and the pharmaceutical idoxuridine were tested in their as-precipitated state, and the effective average modulus and hardness (which can be orientation dependent) were determined. Both exhibit a hardness of 1.0 GPa, with an effective reduced modulus of 25 and 23 GPa for the HMX and idoxuridine, respectively. They also exhibit similar yield point behavior. This indicates idoxuridine may be a suitable mechanical surrogate (or “mock”) for HMX. While the methodology to assess elastic and plastic properties was relatively insensitive to specific crystal orientation (i.e., a uniform distribution in properties was observed for all random crystals tested), the indentation-induced fracture properties appear to be much more sensitive to tip-crystal orientation, and an unloading slope analysis is used to demonstrate the need for further refinement in relating toughness to orientation in these materials with relatively complex slip systems and crystal structures. View Full-Text

36 MATERIALS SCIENCE↗
DOE OSTI2023

Comparison of quantum advantage experiments using random circuit sampling

Random circuit sampling, the task of sampling bit strings from a random unitary operator, has been implemented to demonstrate quantum advantage on the Sycamore quantum processor with 53 qubits and on the Zuchongzhi quantum processor with 56 and 61 qubits. Recently, it was claimed that classical computers using tensor network simulation could catch on to current noisy quantum processors for random circuit sampling. While the linear cross-entropy benchmark fidelity was used to certify all these claims, it may not capture statistical properties of outputs in detail. Here, we compare the bit strings sampled from classical computers using tensor network simulation by Pan et al. [F. Pan, K. Chen, and P. Zhang, Phys. Rev. Lett. 129, 090502 (2022)] and by Kalachev et al. [G. Kalachev, P. Panteleev, P. Zhou, and M.-H. Yung, arXiv:2112.15083] with the bit strings from the Sycamore quantum processor. It is shown that all of Kalachev et al.'s samples passed the NIST random number tests. The heat maps of bit strings show that Pan et al.'s and Kalachev et al.'s samples are quite different from the Sycamore or Zuchongzhi samples. The analysis with the Marchenko-Pastur distribution and the Wasssertein distances demonstrates that Kalachev et al.'s samples are statistically closer to the Sycamore samples than Pan et al.'s while the three datasets have similar values for the linear cross-entropy fidelity. In conclusion, our finding implies that further study is needed to certify or beat the claims of quantum advantage using random circuit sampling.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Effects of spatial variability in vegetation phenology, climate, landcover, biodiversity, topography, and soil property on soil respiration across a coastal ecosystem

Coastal terrestrial-aquatic interfaces (TAIs) are crucial contributors to global biogeochemical cycles and carbon exchange. A systematic evaluation of the interaction between coastal catchment properties and carbon dioxide (CO2) emission by soil respiration is significant for assessing carbon dynamics and predicting the future trajectory of atmospheric CO2 concentrations in coastal TAIs. The soil CO2 efflux in these transition zones is however poorly understood due to the high spatiotemporal dynamics of TAIs, as various sub-ecosystems in this region are compressed and expanded by complex influences of tides, changes in river levels, climate, and land use. We focus on the Chesapeake Bay region to (i) investigate the spatial heterogeneity of the coastal ecosystem and identify spatial zones with similar environmental characteristics based on the spatial data layers, including vegetation index (kNDVI), climate, landcover, diversity, topography, soil property, and relative tidal elevation; (ii) understand the primary driving factors affecting soil respiration within sub-ecosystems of the coastal ecosystem. Specifically, we employed hierarchical clustering analysis to identify spatial regions with distinct environmental characteristics, followed by the determination of main driving factors using Random Forest regression and SHapley Additive exPlanations. Maximum and minimum temperature are the main drivers common to all sub-ecosystems, while each region also has additional unique major drivers that differentiate them from one another. Precipitation exerts an influence on vegetated lands, while soil pH value holds importance specifically in forested lands. In croplands characterized by high clay content and low sand content, the significant role is attributed to bulk density. Wetlands demonstrate the importance of both elevation and sand content, with clay content being more relevant in non-inundated wetlands than in inundated wetlands. The topographic wetness index significantly contributes to the mixed vegetation areas, including shrub, grass, pasture, and forest. Additionally, our research reveals that dense vegetation land covers and urban/developed areas exhibit distinct soil property drivers. Overall, there is no one-size-fits-all approach to modeling carbon fluxes in coastal TAIs, and our study highlights the importance of further research and monitoring practices to improve our understanding of carbon dynamics and promote the sustainable management of coastal TAIs.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

A data-driven CO 2 leakage detection using seismic data and spatial–temporal densely connected convolutional neural networks

In carbon capture and sequestration (also known as carbon capture and storage, or CCS), developing effective monitoring methods is needed to detect and respond to CO 2 leakage. CO 2 leakage detection methods rely on geophysical observations and monitoring sensor network. However, traditional methods usually require the development of site-specific physical models and expert interpretation, and the effectiveness of these methods can be limited to different application locations, operational scenarios, and conditions. Here, we developed a novel data-driven leakage detection method based on densely connected convolutional neural networks. Our method is an end-to-end detection approach, that differs from conventional leakage monitoring methods by directly learning a mapping relationship between seismic data and the CO 2 leakage mass. To account for the spatial and temporal characteristics of seismic data, our novel networks architecture combines 1D and 2D convolutional neural networks. To overcome the computational expense of solving optimization problems, we apply a densely-connecting strategy in our network architecture that reduces the number of network parameters. Based on the features generated by our convolutional neural networks, we further incorporate a long short-term memory network to utilize time-sequential information, which further improves the detection accuracy. Lastly, we employ our detection method to synthetic seismic datasets generated based on flow simulations of a hypothetical CO 2 storage scenario with injection into a partially compartmentalized sandstone storage reservoir. To evaluate method performance, we conducted multiple experiments including a random leakage test, a sequential test, and a robustness test. Numerical results show that our CO 2 leakage detection method successfully detects the leakage and accurately predicts the leakage mass, suggesting that it has the potential for application in monitoring of real CO 2 storage sites.

58 GEOSCIENCES↗
DOE OSTI2022

Multiscale spatial analysis of fracture arrangement and pattern reconstruction using Ripley's K-function

This work presents novel multiscale spatial data analytics using Ripley's K-function, as a measure of spatial interaction, to study one-dimensional arrangement of fractures. Fracture spatial arrangements are classified into clustered, anticlustered, or indistinguishable from random by testing statistical significance of the calculated Ripley's K-function. Characterizations of fracture arrangements are performed as a function of length scale and position. Analysis of the K-function along the study interval identifies where fracture clustering and anticlustering occur. Here, a simulation technique is also introduced here to statistically reconstruct spatial arrangements and to generate fracture realizations that are spatially similar to the fractures observed in the field. With this simulation technique, one can also fill spatial gaps in fracture measurements where data are absent, unreliable, or unused. Synthetic as well as field-measured 1D fracture datasets are used for testing and demonstration. Methods introduced in this work can be readily applied to fracture datasets observed in outcrops, borehole image logs, and cores.

58 GEOSCIENCES↗
DOE OSTI2023

Predicting the superconducting critical temperature in transition metal carbides and nitrides using machine learning

Transition metal carbides and nitrides have unique mechanical and chemical characteristics. At low temperatures many of them also exhibit superconductivity, which can be controlled by substitutions into both the transition metal and carbon/nitrogen sites. To investigate the factors governing the superconducting state, we apply machine learning methods. Here we collected a dataset containing 147 materials, which was used to create a pipeline for predicting their superconducting critical temperature. When this pipeline is applied to a randomly selected test set, it shows a good performance, with of 0.82 and RMSE of 1.9 K. To explore the limits of the machine learning approach, we also use it to predict entire substitution series within the dataset. This represents a realistic test for the predictive models, which can be extremely useful when applied to new substitutions in materials systems. The performance of the pipeline in this case is much more uneven, with good predictions for some series, while for others the model shows minimal predictive power. We discuss possible reasons for these results, as well as methods to estimate the performance of machine learning on new substitution series.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

MArVD2: a machine learning enhanced tool to discriminate between archaeal and bacterial viruses in viral datasets

Abstract Our knowledge of viral sequence space has exploded with advancing sequencing technologies and large-scale sampling and analytical efforts. Though archaea are important and abundant prokaryotes in many systems, our knowledge of archaeal viruses outside of extreme environments is limited. This largely stems from the lack of a robust, high-throughput, and systematic way to distinguish between bacterial and archaeal viruses in datasets of curated viruses. Here we upgrade our prior text-based tool (MArVD) via training and testing a random forest machine learning algorithm against a newly curated dataset of archaeal viruses. After optimization, MArVD2 presented a significant improvement over its predecessor in terms of scalability, usability, and flexibility, and will allow user-defined custom training datasets as archaeal virus discovery progresses. Benchmarking showed that a model trained with viral sequences from the hypersaline, marine, and hot spring environments correctly classified 85% of the archaeal viruses with a false detection rate below 2% using a random forest prediction threshold of 80% in a separate benchmarking dataset from the same habitats.

Vik, Dean (ORCID:000000027546899X)↗
DOE OSTI2023

Investigating boosted decision trees as a guide for inertial confinement fusion design

Inertial confined fusion experiments at the National Ignition Facility have recently entered a new regime approaching ignition. Improved modeling and exploration of the experimental parameter space were essential to deepening our understanding of the mechanisms that degrade and amplify the neutron yield. The growing prevalence of machine learning in fusion studies opens a new avenue for investigation. Here in this paper, we have applied the Gradient-Boosted Decision Tree machine-learning architecture to further explore the parameter space and find correlations with the neutron yield, a key performance indicator. We find reasonable agreement between the measured and predicted yield, with a mean absolute percentage error on a randomly assigned test set of 35.5%. This model finds the characteristics of the laser pulse to be the most influential in prediction, as well as the hohlraum laser entrance hole diameter and an enhanced capsule fabrication technique. We used the trained model to scan over the design space of experiments from three different campaigns to evaluate the potential of this technique to provide design changes that could improve the resulting neutron yield. While these data-driven model cannot predict ignition without examples of ignited shots in the training set, it can be used to indicate that an unseen shot design will at least be in the upper range of previously observed neutron yields.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Investigating performance and variability of NIF ICF experiments with deep learning

The parameter space involved in designing an inertial confinement fusion shot at the National Ignition Facility (NIF) is massively multi-dimensional and the cost of a single shot makes a comprehensive set of sensitivity studies in the laboratory impractical. The use of machine learning to overcome these challenges has gained popularity and has had several successful applications by the scientific community. We extend on these efforts by training a neural network (NN) on information about the experimental design, engineering elements, and drive asymmetry to predict with uncertainty the neutron yield of an experiment. We find the measured and model predicted values are in good agreement, with an R 2 value of 0.91 for a randomly selected test dataset. Almost all the predicted 95% credible intervals contain the corresponding measured value for both training and test datasets. We identify correlations picked up by the NN between the shot design, yield, and variability and use them to motivate shot sensitivity studies. The first shot to exceed the Lawson-like ignition criteria (N210808) was conducted at the NIF and subsequent shots studied the design’s robustness. In a follow-up shot to N210808, our model predicts capsule quality to be the main performance degradation mechanism that prevented the shot from repeating previous performance levels. Shot N221204 was the first shot to exceed a target energy gain of 1. Our model predicts increased yield with reduced coast time for a N221204 study and greater variability for designs with lower peak powers at constant yield. The model’s fast prediction speed and uncertainty prediction are useful for identifying interesting design paths that could warrant further investigation with conventional simulations to search for robust high yield designs.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Benchmarking SARS CoV-2 Infection in the Workplace to Support Continuity of Operations

Objective: The COVID-19 pandemic jeopardizes continuity of operations of workplaces and the health and safety of workers. Exemplar workplace-related SARS-CoV-2 benchmarks are described and illustrated with empirical data. Methods: Benchmarks were collected over a 9-month period on a large workplace (N = 5500+). These ranged from quantitative indices associated with RT-qPCR targeted testing and random surveillance screening, surveillance for new variants of SARS-CoV-2, intensive contact tracing, case management, return to work procedures, to monitoring of antibody seropositive status. Results: Data and analyses substantiated effectiveness of interventions. This was evidenced in suppressed infection rates, rapid case identification and isolation, acceptance of the program by employees, documentation of presumptive immunity, and working relationships with senior management. Conclusions: These SARS-CoV-2 exemplar benchmarks provided an evidence-base for practice and contributed strategically to organizational decisions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

The Quantum Alternating Operator Ansatz for Satisfiability Problems

Here, we comparatively study, through large-scale numerical simulation, the performance across a large set of Quantum Alternating Operator Ansatz (QAOA) implementations for finding approximate and optimum solutions to unconstrained combinatorial optimization problems. Our survey includes over 100 different mixing unitaries, and we combine each mixer with both the standard phase separator unitary representing the objective function and a thresholded version. Our numerical tests for randomly chosen instances of the unconstrained optimization problems Max 2-SAT and Max 3-SAT reveal that the traditional transverse-field mixer with the standard phase separator performs best for problem sizes of 8 through 14 variables, while the recently introduced Grover mixer with thresholding wins at problems of size 6. This result (i) corrects earlier work suggesting that the Grover mixer is a superior mixer based only on results from problems of size 6, thus illustrating the need to push numerical simulation to larger problem sizes to more accurately predict performance; and (ii) it suggests that more complicated mixers and phase separators may not improve QAOA performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Comparison of theory with the experimental characterization of the spatial frequency response of interferometers using a binary pseudo-random array sample

Experimental evaluations of the surface height response of an interference microscope using a binary pseudo-random array test sample are compared with a theory based on a Fourier optics model. Measurements of key instrument characteristics, including the illumination, imaging, and obscuring apertures of three different Mirau objectives, support the theoretical calculations. Agreement between experimental and theoretical modeling confirms the predictability of the spatial frequency response for the purpose of specification and optimization of instrument configuration for specific metrology tasks. The results also provide confidence in methods of compensating for the decrease in instrument response with spatial frequency.

Calibration↗
DOE OSTI2015

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↗
DOE OSTI2023

pnnl/mlxrd

A multi-task neural network for the simultaneous identification of multiple compounds from XRD data obtained in a synchrotron-based hydrothermal fluid system. To enhance the alignment between the training and test datasets, random noise is introduced into the synthetic training dataset, and minor labeled experimental data is incorporated. Additionally, we employ a weighted cross-entropy loss function to address data imbalances and ensure smoother model training.

Li, Ang↗
DOE OSTI2022

Dataset for 'Ombadi, M. & Varadharajan, C. (2022). Urbanization and aridity mediate distinct salinity response to floods in rivers and streams across the Contiguous United States, Water Research'

This package contains data sets and code used to obtain the results in Ombadi, M., & Varadharajan, C. (2022). Urbanization and aridity mediate distinct salinity response to floods in rivers and streams across the Contiguous United States. Water Research, 118664. The folder "data" contains 259 .csv files, each of which has daily time series of concurrent streamflow (Q) and specific conductance (SC) for each of the sites used in this study originally downloaded from the USGS National Water Information System (NWIS; USGS, 2016). The number of data points in each of the files is at least 3650 (i.e. 10 years of daily measurements). The folder "RF_single_data" contains 259 .csv files, each of which include data used to train and test the Random Forest models at individual sites for predicting SC during days of floods. The folder "RF_regional_data" contains 3 .csv files, each of which include scaled data compiled from all sites within each climate zone (arid, temperate and wet). "metadata.csv" contains the physical properties of the 259 catchments corresponding to the sites used in this study; this data was extracted from GAGES-II dataset (Falcone et al., 2010). "RF_implementation.ipynb" is a Jupyter notebook with the code needed to implement the analysis using Random Forest models either for individual sites or for the regional models (for each climate zone). The code utilizes the data in the two folders: "RF_single_data" and "RF_regional_data" and the metadata.csv file.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2015

SU-E-T-131: Artificial Neural Networks Applied to Overall Survival Prediction for Patients with Periampullary Carcinoma

Purpose: Artificial neural networks (ANN) can be used to discover complex relations within datasets to help with medical decision making. This study aimed to develop an ANN method to predict two-year overall survival of patients with peri-ampullary cancer (PAC) following resection. Methods: Data were collected from 334 patients with PAC following resection treated in our institutional pancreatic tumor registry between 2006 and 2012. The dataset contains 14 variables including age, gender, T-stage, tumor differentiation, positive-lymph-node ratio, positive resection margins, chemotherapy, radiation therapy, and tumor histology.After censoring for two-year survival analysis, 309 patients were left, of which 44 patients (∼15%) were randomly selected to form testing set. The remaining 265 cases were randomly divided into training set (211 cases, ∼80% of 265) and validation set (54 cases, ∼20% of 265) for 20 times to build 20 ANN models. Each ANN has one hidden layer with 5 units. The 20 ANN models were ranked according to their concordance index (c-index) of prediction on validation sets. To further improve prediction, the top 10% of ANN models were selected, and their outputs averaged for prediction on testing set. Results: By random division, 44 cases in testing set and the remaining 265 cases have approximately equal two-year survival rates, 36.4% and 35.5% respectively. The 20 ANN models, which were trained and validated on the 265 cases, yielded mean c-indexes as 0.59 and 0.63 on validation sets and the testing set, respectively. C-index was 0.72 when the two best ANN models (top 10%) were used in prediction on testing set. The c-index of Cox regression analysis was 0.63. Conclusion: ANN improved survival prediction for patients with PAC. More patient data and further analysis of additional factors may be needed for a more robust model, which will help guide physicians in providing optimal post-operative care. This project was supported by PA CURE Grant.

60 APPLIED LIFE SCIENCES↗