Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “regression models”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Estimating Leaf Area Index in Row Crops Using Wheel-Based and Airborne Discrete Return Light Detection and Ranging Data

Leaf area index (LAI) is an important variable for characterizing plant canopy in crop models. It is traditionally defined as the total one-sided leaf area per unit ground area and is estimated by both direct and indirect methods. This paper explores the effectiveness of using light detection and ranging (LiDAR) data to estimate LAI for sorghum and maize with different treatments at multiple times during the growing season from both a wheeled vehicle and Unmanned Aerial Vehicles. Linear and nonlinear regression models are investigated for prediction utilizing statistical and plant structure-based features extracted from the LiDAR point cloud data with ground reference obtained from an in-field plant canopy analyzer (indirect method). Results based on the value of the coefficient of determination ( R 2 ) and root mean squared error for predictive models ranged from ∼0.4 in the early season to ∼0.6 for sorghum and ∼0.5 to 0.80 for maize from 40 Days after Sowing to harvest.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

SOC Microstructural Property Estimator

This pre-trained ML model is a tool that uses basic compositional parameters for porous solid oxide cell (SOC) electrodes - the phase fractions and mean particle/pore diameters – as inputs and uses them to estimate additional electrochemical performance parameters: active (i.e., connected) TPB density, all tortuosity factors, and phase pair specific interfacial areas. The electrode is assumed to be composed of two solid phases and a pore phase. The property calculations are performed using neural network regression models trained on a large bank of synthetic electrode microstructural data that NETL has generated using the program DREAM3D (that bank is also hosted on EDX: https://edx.netl.doe.gov/dataset/soc-synthetic-microstructure-bank). This means the generated parameters are based on training from actual measured properties from 3D microstructures, not estimated from geometric simplifications. This tool was developed and is intended to replace percolation theory calculations in models that use hypothetical electrode properties. An example use case would be running SOC performance simulations across a parametric sweep of electrode designs (e.g., varying phase fractions and particle sizes) and assessing how it impacts the electrochemical performance of the SOC. Within the parameter space of the training data (statistics of that parameter space is provided in the readme file), this model achieves sub-5% mean absolute percent errors, an order of magnitude less error than percolation theory across the same parameter space. However, be aware that this tool was developed with parametric simulations in mind, and users are encouraged to assess accuracy for their own specific use case rather than taking accuracy metrics at face value. More info, including a usage guide, is in the included readme file. This tool should be cited with the DOI number provided.

Electrode Microstructure↗
DOE OSTI2022

A novel methodology to integrate outcomes regarding perioperative pain experience into a composite score: Prediction model development and validation

Abstract Background An integrated score that globally assesses perioperative pain experience and rationally weights each component has not yet been developed. Methods A development dataset specific to adult Chinese patients undergoing orthopaedic surgery was obtained from PAIN OUT (1985 qualified patients of 2244). A more recent validation dataset obeying the same conditions was obtained from the Chinese Anaesthesia Shared‐database Platform (1004 qualified patients of 1032). Outcomes were assessed using the International Pain Outcomes Questionnaire (IPO‐Q), which comprises key patient‐level outcomes of perioperative pain management, including pain experience and perceptions of care. Using principal component analysis and regression models, a composite score (CS) was inferred to integrate pain experience. The discrimination of the CS for dissatisfaction and desire for more pain treatment was compared with that of the worst pain score. Results A CS was developed from the 12 items of the IPO‐Q regarding pain experience. The weight for calculating the CS was worst pain 11, least pain 17, time spent in severe pain 11, interference with activity in bed 9, interference with breathing deeply or coughing 10, interference with sleep 9, anxiety 12, helplessness 12, nausea 0, drowsiness 2, itch 5 and dizziness 2. In external validation, the CS indicated superior discrimination to the worst pain in predicting dissatisfaction ( p < 0.001) and desire for more pain treatment ( p < 0.001). Conclusions This study introduced a methodology to integrate outcomes regarding perioperative pain experience into a CS, which was based on the weight of each item. Significance This novel methodology sheds additional light on the riveting issue of carefully integrating several measures into a composite endpoint, which may be useful for quality improvement purposes when addressing the impact of a change in clinical practice.

Jiang, Bailin↗
DOE OSTI2025

Climate change and federal aid disbursements after Hurricane Harvey: an extreme event attribution analysis

The role climate change plays in increasing the burden placed on governments and insurers to pay for recovery has not been extensively explored and is the focus of this study. This study examines the impacts of climate change attributed flooding on federal disaster aid disbursement in Harris County, Texas following Hurricane Harvey in 2017. Our approach uses flood models to estimate the amount of flood damages attributable and not attributable to climate change under two climate change attribution scenarios from peer reviewed studies: 20% and 38% increases in rainfall associated with the hurricane due to climate change. These estimates are combined with census tract-level disbursement data for FEMA’s National Flood Insurance Program (NFIP) and the Individual Assistance (IA) part of the Individuals and Households Program. We employ spatial lag regression models with direct and spatial spillover effects to analyze the relationship between a tract’s flood damages—both attributed and not attributed to climate change—and federal disaster aid. We find that both types of flood damage shape federal aid disbursements, but that climate change attributed damages tend to have larger effect sizes (elasticities) especially for IA. Specifically, for a 1% increase in additional climate change attributed damages per household in a census tract (under the 20% scenario), expected NFIP levels in that census tract are 0.26% higher and IA levels are 0.3% higher. Implications center on federal funding in an era of climate change.

FEMA↗
DOE OSTI2022

Nonsynonymous amino acid changes in the α-chain of complement component 5 influence longitudinal susceptibility to Plasmodium falciparum infections and severe malarial anemia in kenyan children

Background: Severe malarial anemia (SMA; Hb < 5.0 g/dl) is a leading cause of childhood morbidity and mortality in holoendemic Plasmodium falciparum transmission regions such as western Kenya. Methods: We investigated the relationship between two novel complement component 5 (C5) missense mutations [rs17216529:C>T, p(Val145Ile) and rs17610:C>T, p(Ser1310Asn)] and longitudinal outcomes of malaria in a cohort of Kenyan children (under 60 mos, n = 1,546). Molecular modeling was used to investigate the impact of the amino acid transitions on the C5 protein structure. Results: Prediction of the wild-type and mutant C5 protein structures did not reveal major changes to the overall structure. However, based on the position of the variants, subtle differences could impact on the stability of C5b. The influence of the C5 genotypes/haplotypes on the number of malaria and SMA episodes over 36 months was determined by Poisson regression modeling. Genotypic analyses revealed that inheritance of the homozygous mutant (TT) for rs17216529:C>T enhanced the risk for both malaria (incidence rate ratio, IRR = 1.144, 95%CI: 1.059–1.236, p = 0.001) and SMA (IRR = 1.627, 95%CI: 1.201–2.204, p = 0.002). In the haplotypic model, carriers of TC had increased risk of malaria (IRR = 1.068, 95%CI: 1.017–1.122, p = 0.009), while carriers of both wild-type alleles (CC) were protected against SMA (IRR = 0.679, 95%CI: 0.542–0.850, p = 0.001). Conclusion: Collectively, these findings show that the selected C5 missense mutations influence the longitudinal risk of malaria and SMA in immune-naïve children exposed to holoendemic P. falciparum transmission through a mechanism that remains to be defined.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

A modeling pipeline to relate municipal wastewater surveillance and regional public health data

As COVID-19 becomes endemic, public health departments require improved passive indicators, which are independent of voluntary testing data, to estimate the prevalence of COVID-19 in local communities. Quantification of SARS-CoV-2 RNA from wastewater has the potential to be a powerful passive indicator. However, connecting measured SARS-CoV-2 RNA to community prevalence is challenging. We have developed a generalized methodology to improve the predictive power of wastewater measurements and applied it to data collected from treatment plants in the Chicago area. We built and compared a set of multi-linear regression models, which incorporate pepper mild mottle virus (PMMoV) as a population biomarker, Bovine coronavirus (BCoV) as a recovery control, and wastewater system flow rate into a corrected estimate for SARS-CoV-2 RNA concentration. For our data, models with BCoV performed better than those with PMMoV, but all model estimates of prevalence significantly improved correlation compared to doing no correction. We also investigate the utility of RNA measurements in wastewater as a leading indicator of COVID-19 trends. We do this in a rolling manner for corrected wastewater data and for other prevalence indicators, and statistically compare the temporal relationship between new increases in the wastewater data and those in other prevalence indicators. We find that wastewater trends often lead other COVID-19 indicators in predicting new surges.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Data-Driven Surrogate Modeling with Microstructure-Sensitivity of Viscoplastic Creep in Grade 91 Steel

Abstract To support the development of advanced steel alloys tailored to withstand extreme conditions, it is imperative to account for the mechanical performance of components, while considering the influence of local microstructure on the macroscopic response. To this end, this study focuses on the development of microstructure-sensitive constitutive models for the mechanical response of Grade 91 steel exposed to extreme thermo-mechanical environments. Polynomial chaos expansion (PCE) surrogates are used to emulate high-fidelity polycrystal simulations of the viscoplastic response of Grade 91 steel as a function of the microstructure fingerprint (e.g., dislocations and precipitates). To cover a wide temperature–stress domain, two separate PCE surrogates—one that captures softening and the other that captures hardening behavior—are combined using another (sparse) Gaussian process regression model. The resulting constitutive creep surrogate model is integrated within the MOOSE finite element framework to simulate the intricate effects of microstructure, in particular MX-phase precipitates, on a component with a graded microstructure. Surrogate sensitivity analysis is applied to quantify the relevant impact of spatially varying microstructure on the creep response in a test-case involving a Grade 91 alloy with a prototypical weld.

36 MATERIALS SCIENCE↗
DOE OSTI2025

How does ion temperature gradient turbulence depend on magnetic geometry? Insights from data and machine learning

Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyse this dependence using multiple machine learning methods and a dataset of >200 000 nonlinear gyrokinetic simulations of ion-temperature-gradient turbulence in diverse non-axisymmetric geometries. The dataset is generated using a large collection of both optimised and randomly generated stellarator equilibria. At fixed gradients and other input parameters, the turbulent heat flux varies between geometries by several orders of magnitude. Trends are apparent among the configurations with particularly high or particularly low heat flux. Regression and classification techniques from machine learning are then applied to extract patterns in the dataset. Due to a symmetry of the gyrokinetic equation, the heat flux and regressions thereof should be invariant to translations of the raw features in the parallel coordinate, similar to translation invariance in computer vision applications. Multiple regression models including convolutional neural networks (CNNs) and decision trees can achieve reasonable predictive power for the heat flux in held-out test configurations, with highest accuracy for the CNNs. Using Spearman correlation, sequential feature selection and Shapley values to measure feature importance, it is consistently found that the most important geometric lever on the heat flux is the flux surface compression in regions of bad curvature. The second most important geometric feature relates to the magnitude of geodesic curvature. These two features align remarkably with surrogates that have been proposed based on theory, while the methods here allow a natural extension to more features for increased accuracy. The dataset, released with this publication, may also be used to test other proposed surrogates, and we find that many previously published proxies do correlate well with both the heat flux and stability boundary.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Development of a prediction model for radiotherapy response among patients with head and neck squamous cell carcinoma based on the tumor immune microenvironment and hypoxia signature

Abstract Introduction The immune system and hypoxia are major factors influencing radiosensitivity in patients with different cancer types. This study aimed at developing a model to predict radiotherapy response in patients with head and neck squamous cell carcinoma (HNSCC) based on the tumor immune microenvironment and hypoxia signature. Materials and Methods We first evaluated the hypoxia status and tumor immune microenvironment in the Cancer Genome Atlas (TCGA) cohort by using transcriptomic data. Differentially expressed genes (DEGs) were identified between the “high immunity and low hypoxia” and “low immunity and high hypoxia” groups and those DEGs significantly associated with disease‐specific survival in the univariate Cox regression analysis were selected as the prognostic DEGs. We selected the immune hypoxia–related genes (IHRGs) by intersecting prognostic DEGs with immune and hypoxia gene sets. We used the IHRGs to train a multivariate Cox regression model in the TCGA cohort, based on which we calculated the IHRG prognostic index (IHRGPI) for each patient and validated its efficacy in predicting radiotherapy response in the Gene Expression Omnibus cohorts. Furthermore, we explored potential mechanisms and effective combinational treatment strategies for different IHRGPI groups. Results Five IHRGs were used to construct the IHRGPI, which was used to dichotomize the cohorts. The patients with lower IHRGPI showed a better radiotherapy response across different cohorts and endpoints, including overall survival, progression‐free survival, and recurrence‐free survival ( p < 0.05). Patients with higher IHRGPI showed greater hypoxia and lesser immune cell infiltration. A lower IHRGPI indicated a better immunotherapy response, while a higher IHRGPI indicated a better chemotherapy response. Conclusions IHRGPI is promising for predicting radiotherapy response and guiding combinational treatment strategies in patients with HNSCC.

Zhu, Guang‐Li↗
DOE OSTI2020

Augmenting machine learning of energy landscapes with local structural information

We present a machine learning approach for accurately predicting formation energies of binary compounds in the context of crystal structure predictions. The success of any machine learning model depends significantly on the choice of representation used to encode the relevant physical information into machine-learnable data. We test different representation schemes based on partial radial and angular distribution functions (RDF+ADF) on Al–Ni and Cd–Te structures generated using our genetic algorithm for structure prediction. We observe a remarkable improvement in predictive accuracy upon transitioning from global to atom-centered representations, resulting in a threefold decrease in prediction errors. We show that a support vector regression model using a combination of atomic radial and angular distribution functions performs best at the formation energy prediction task, providing small root mean squared errors of 3.9 meV/atom and 10.9 meV/atom for Al–Ni and Cd–Te, respectively. We test the performance of our models against common traditional descriptors and find that RDF- and ADF-based representations significantly outperform many of those in the prediction of formation energies. The high accuracy of predictions makes our machine learning models great candidates for the exploration of energy landscapes.

Honrao, Shreyas J. (ORCID:0000000166155257)↗
DOE OSTI2025

Investigating the effects of local environment on nitrogen vacancies in high-entropy metal nitrides

High-entropy metal nitrides are an important material class in a variety of applications, and the role of nitrogen vacancies is of great importance for understanding their stability and mechanical properties. Here, we study six different high-entropy nitrides with eight different metal species to build a predictive model of the nitrogen-vacancy formation energy. We construct sets of supercells that maximize the number of unique nitrogen environments for a given chemistry, and then use density-functional theory to calculate the energy density for all nitrogen sites, and the vacancy formation energies for the highest, lowest, and a median subset based on the energy densities. The energy density of nitrogen sites correlates with the vacancy formation energies, for binary, ternary, and high-entropy nitrides. A linear regression model predicts the vacancy formation energies using only the nearest-neighbor composition; across our eight metals, we find the largest vacancy formation energies next to Hf, then Zr, Ti, V, Cr, Ta, Nb, and the lowest near Mo. Additionally, we see that binary nitride data show qualitatively similar vacancy formation energy trends for high-entropy nitrides; however, the binary data alone are insufficient to predict the complex nitride behavior. Our model is both predictive and easily interpretable, and correlates with experimental data.

DeSilva, Charith R. [Univ. of Illinois at Urbana-C↗
DOE OSTI2023

Limited potential of irrigation to prevent potato yield losses in Germany under climate change

Climate models project higher temperatures and a substantial net water deficit during the summer months over Germany until the end of the 21st century. The agricultural sector is particularly vulnerable to changing weather and climate conditions. In this study, we examine the role of irrigation for potato yields as a climate change adaptation measure in Northeast Lower Saxony (Germany). The region represents the largest irrigated area in Germany and is one of the main growing areas of potatoes. We develop a statistical multivariate regression model to investigate whether regional climate and irrigation data at the monthly and county level are suitable to describe potato yield variability from 1978 to 2018. Irrigation is estimated based on the climatic water balance and crop water demand. These estimates are calibrated against irrigation data from local agencies to account for realistic monthly water withdrawals. We analyze future yield changes based on climate model projections for the 21st century and different irrigation scenarios. We find that the potato yield will decrease significantly by 18% on average until 2050 with climate projection uncertainty of ±6.4% under the high emission scenario RCP 8.5 and without irrigation. Irrigation at current levels could compensate for about 54% of these yield losses. Doubling the amount of irrigation minimizes yield losses by as much as 80%. Under the low (middle) emission scenario RCP 2.6 (RCP 4.5), potato yield are projected to decrease moderately by 4.5% ± 3.4% (5.4% ± 2.8%) with irrigation at current levels. We show that the yield losses mainly originate from higher temperatures during the summer. Our analysis indicates that the capacity of irrigation to minimize yield losses is limited. Strengthening climate change mitigation efforts may be more effective in preventing yield losses. However, the effect of elevated CO 2 might buffer the high yield losses, especially in RCP 8.5. The studies supports farmers and decision makers in assessing future risks in potato yields. It can guide policymakers in allocating economic resources to cope with climate change.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

The Q 10 of in situ microbial soil respiration varies with mean annual temperature, precipitation, pH, and plant cover: a meta-analysis and spatial prediction of Q 10

The temperature sensitivity of soil microbial respiration, commonly quantified using the Q 10 coefficient, is a key parameter in carbon cycle models. Uncovering how environmental factors affect in situ Q 10 values can therefore provide critical insight into potential shifts in global carbon stocks under climate change. We collected data from previously published field experiments that measured soil microbial respiration across a range of temperatures. We hypothesized that the Q 10 coefficient of in situ soil microbial respiration would vary based on environmental factors including mean annual temperature (MAT), mean annual precipitation (MAP), plant cover type, pH, soil C:N, and latitude. Linear regression revealed that Q 10 correlates negatively with MAT and MAP and positively with pH and absolute latitude. Additionally, average Q 10 varied significantly across different plant cover types; it was highest in mountain grasslands and lowest in tropical moist forests. Variation in microbial Q 10 across environmental factors may arise from underlying mechanisms such as enzyme kinetics, substrate availability and complexity, and microbial adaptation. To capture patterns in Q 10 more comprehensively, we developed a multiple linear regression model of Q 10 based on the most individually significant environmental drivers and applied it to public datasets to generate a global map of predicted Q 10 . Q 10 was higher in high-latitude and high-altitude regions, where large permafrost carbon stores are vulnerable to thawing and decomposition. We also compared fits between the Q 10 equation and a model produced from macromolecular rate theory (MMRT). We found that the MMRT model had the superior fit and may be better suited to model temperature sensitivity of complex biological reactions. Overall, our results emphasize that relationships between microbial Q 10 and environmental variables should be accounted for in climate models. Incorporating these variations in the Q 10 parameter, rather than using a fixed value, will help predict whether CO 2 emissions will be buffered or exacerbated by soil microbial respiration under climate change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Uniting Surface Properties With Hydrodynamic Roughness in Shallow Overland Flow Models

Describing flow resistance from the properties of an underlying surface is a challenge in surface hydrology. Runoff models must specify a resistance formulation or “roughness scheme”—describing the functional relationship between flow resistance and flow depth/velocity—and its parameters. Uncertainty in runoff predictions derives from both the selected roughness scheme (e.g., Darcy Weisbach, Manning's, or laminar flow equations), and its parameterization with a roughness coefficient (e.g., Manning's n). Both choices are informed by model calibration to data, usually discharge, and, if available, velocity. In this study, a Saint Venant Equation-based runoff model is calibrated to discharge and velocity data from 112 rainfall simulator experiments. The results are used to identify the optimal roughness scheme among four widely-used options for each experiment, and to explore whether surface properties can be used to select the optimal roughness scheme and its coefficient. Among the tested roughness schemes, a transitional flow equation provided the best fit to the plurality of experiments. The most suitable roughness scheme for a given experiment was not related to measured surface properties. Regression models predicted the calibrated roughness coefficients with adjusted values between 0.48 and 0.54, depending on the roughness scheme used. Litter cover was the best predictor of the roughness coefficient, followed by soil cover and average canopy gap size. The results suggest that selection of an optimal roughness scheme based on surface properties alone remains difficult, but that once a scheme is selected, roughness coefficients can be estimated from surface properties.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Electrocardiographic changes predate Parkinson’s disease onset

Autonomic nervous system involvement precedes the motor features of Parkinson’s disease (PD). Our goal was to develop a proof-of-concept model for identifying subjects at high risk of developing PD by analysis of cardiac electrical activity. We used standard 10-s electrocardiogram (ECG) recordings of 60 subjects from the Honolulu Asia Aging Study including 10 with prevalent PD, 25 with prodromal PD, and 25 controls who never developed PD. Various methods were implemented to extract features from ECGs including simple heart rate variability (HRV) metrics, commonly used signal processing methods, and a Probabilistic Symbolic Pattern Recognition (PSPR) method. Extracted features were analyzed via stepwise logistic regression to distinguish between prodromal cases and controls. Stepwise logistic regression selected four features from PSPR as predictors of PD. The final regression model built on the entire dataset provided an area under receiver operating characteristics curve (AUC) with 95% confidence interval of 0.90 [0.80, 0.99]. The five-fold cross-validation process produced an average AUC of 0.835 [0.831, 0.839]. We conclude that cardiac electrical activity provides important information about the likelihood of future PD not captured by classical HRV metrics. Machine learning applied to ECGs may help identify subjects at high risk of having prodromal PD.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Simple Statistical Models for Predicting Overpressure Due to CO2 and Low-Salinity Waste-Fluid Injection into Deep Saline Formations

Deep saline aquifers have been used for waste-fluid disposal for decades and are the proposed targets for large-scale CO2 storage to mitigate CO2 concentration in the atmosphere. Due to relatively limited experience with CO2 injection in deep saline formations and given that the injection targets for CO2 sometimes are the same as waste-fluid disposal formations, it could be beneficial to model and compare both practices and learn from the waste-fluid disposal industry. In this paper, we model CO2 injection in the Patterson Field, which has been proposed as a site for storage of 50 Mt of industrial CO2 over 25 years. We propose general models that quickly screen the reservoir properties and calculate pressure changes near and far from the injection wellbore, accounting for variable reservoir properties. The reservoir properties we investigated were rock compressibility, injection rate, vertical-to-horizontal permeability ratio, average reservoir permeability and porosity, reservoir temperature and pressure, and the injectant total dissolved solids (TDS) in cases of waste-fluid injection. We used experimental design to select and perform simulation runs, performed a sensitivity analysis to identify the important variables on pressure build-up, and then fit a regression model to the simulation runs to obtain simple proxy models for changes in average reservoir pressure and bottomhole pressure. The CO2 injection created more pressure compared to saline waste-fluids, when similar mass was injected. However, we found a more significant pressure buildup at the caprock-reservoir interface and lower pressure buildup at the bottom of the reservoir when injecting CO2 compared with waste-fluid injection.

Ansari, Esmail↗
DOE OSTI2026

Predictive analytics to direct clinical attention to complex patients with elevated suicide risk: enhancement of the Veterans Health Administration REACH VET model

Suicide is a major public health concern, particularly among Veterans. The U.S. Department of Veterans Affairs Veterans Health Administration (VHA) employs the Recovery Engagement and Coordination for Health–Veterans Enhanced Treatment (REACH VET) model to prioritise high-risk patients for targeted clinical attention. REACH VET 1.0 (RV 1.0) was developed on 2008–2011 data. To reflect changes in clinical practice and populations, VHA updated it to REACH VET 2.0 (RV 2.0). This study describes its development and validation. RV 2.0 used longitudinal data from 7,248,170 VHA patients (4,967 suicide deaths) in 2018–2019, with 650 time-varying demographic, clinical and area-level predictors derived from a 2-year lookback (2016–2019). An ensemble of Elastic-Net logistic regression models was trained on 2018 data and evaluated monthly at the population level in 2019, focusing on the top 0.1% intervention risk tier. Analyses assessed model discrimination, suicide detection, risk concentration, subgroup consistency (sex, age and race/ethnicity) and performance relative to RV 1.0 using the same percentile-based risk strata. RV 2.0 outperformed RV 1.0 across all risk strata, with better discrimination (C-statistic 0.76 vs 0.69) and consistent performance across demographic subgroups. Within the top 0.1% of predicted risk, RV 2.0 identified more deaths, higher suicide rates and greater mortality risk concentration both when averaged across the 12 monthly 2019 test sets (5.6 vs 3.6; 83.6 vs 53.7 per 100,000 person-years; 21.0 vs 14.1) and when annualised for 2019 (67 vs 43; 2.7% vs 1.7%; 1,003 vs 644 per 100,000 person-years; 26.7 vs 17.1). RV 2.0 improves suicide risk stratification among Veterans, demonstrating better performance and consistent prediction across subgroups and highlighting the need for regular model updates and evaluation.

Peluso, Alina [Oak Ridge National Laboratory (ORNL↗
DOE OSTI2020

Comparison of Social Media, Syndromic Surveillance, and Microbiologic Acute Respiratory Infection Data: Observational Study

Internet data can be used to improve infectious disease models. However, the representativeness and individual-level validity of internet-derived measures are largely unexplored as this requires ground truth data for study. This study sought to identify relationships between Web-based behaviors and/or conversation topics and health status using a ground truth, survey-based dataset. This study leveraged a unique dataset of self-reported surveys, microbiological laboratory tests, and social media data from the same individuals toward understanding the validity of individual-level constructs pertaining to influenza-like illness in social media data. Logistic regression models were used to identify illness in Twitter posts using user posting behaviors and topic model features extracted from users’ tweets. Of 396 original study participants, only 81 met the inclusion criteria for this study. Of these participants’ tweets, we identified only two instances that were related to health and occurred within 2 weeks (before or after) of a survey indicating symptoms. It was not possible to predict when participants reported symptoms using features derived from topic models (area under the curve [AUC]=0.51; P=.38), though it was possible using behavior features, albeit with a very small effect size (AUC=0.53; P≤.001). Individual symptoms were also generally not predictable either. The study sample and a random sample from Twitter are predictably different on held-out data (AUC=0.67; P≤.001), meaning that the content posted by people who participated in this study was predictably different from that posted by random Twitter users. Individuals in the random sample and the GoViral sample used Twitter with similar frequencies (similar @ mentions, number of tweets, and number of retweets; AUC=0.50; P=.19). To our knowledge, this is the first instance of an attempt to use a ground truth dataset to validate infectious disease observations in social media data. The lack of signal, the lack of predictability among behaviors or topics, and the demonstrated volunteer bias in the study population are important findings for the large and growing body of disease surveillance using internet-sourced data.

59 BASIC BIOLOGICAL SCIENCES↗