ImportanceHealthy nutrition and appropriate supplementation during preconception have important implications for the health of the mother and newborn. The best way to deliver preconception care to address health risks related to nutrition is unknown.MethodsWe conducted a secondary analysis of data from a randomized controlled trial designed to study the impact of conversational agent technology in 13 domains of preconception care among 528 non-pregnant African American and Black women. This analysis is restricted to those 480 women who reported at least one of the ten risks related to nutrition and dietary supplement use.InterventionsAn online conversational agent, called “Gabby”, assesses health risks and delivers 12 months of tailored dialogue for over 100 preconception health risks, including ten nutrition and supplement risks, using behavioral change techniques like shared decision making and motivational interviewing. The control group received a letter listing their preconception risks and encouraging them to talk to a health care provider.ResultsAfter 6 months, women using Gabby (a) reported progressing forward on the stage of change scale for, on average, 52.9% (SD, 35.1%) of nutrition and supplement risks compared to 42.9% (SD, 35.4) in the control group (IRR 1.22, 95% CI 1.03–1.45, P = 0.019); and (b) reported achieving the action and maintenance stage of change for, on average, 52.8% (SD 37.1) of the nutrition and supplement risks compared to 42.8% (SD, 37.9) in the control group (IRR 1.26, 96% CI 1.08–1.48, P = 0.004). For subjects beginning the study at the contemplation stage of change, intervention subjects reported progressing forward on the stage of change scale for 75.0% (SD, 36.3%) of their health risks compared to 52.1% (SD, 47.1%) in the control group (P = 0.006).ConclusionThe scalability of Gabby has the potential to improve women’s nutritional health as an adjunct to clinical care or at the population health level. Further studies are needed to determine if improving nutrition and supplement risks can impact clinical outcomes including optimization of weight.Clinical Trial RegistrationClinicalTrials.gov, identifier NCT01827215.

Background: Postoperative gastrointestinal leak and venous thromboembolism (VTE) are devastating complications of bariatric surgery. The performance of currently available predictive models for these complications remains wanting, while machine learning has shown promise to improve on traditional modeling approaches. The purpose of this study was to compare the ability of two machine learning strategies, artificial neural networks (ANNs) and gradient boosting machines (XGBs), to conventional models using logistic regression (LR) in predicting leak and VTE after bariatric surgery. Methods: ANN, XGB, and LR prediction models for leak and VTE among adults undergoing initial elective weight loss surgery were trained and validated using preoperative data from the 2015-2017 Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program database. Data was randomly split into training, validation, and testing populations. Model performance was measured by the area under the receiver-operating characteristic curve (AUC) on the testing data for each model. Results:The study cohort contained 436,807 patients. The incidences of leak and VTE were 0.70% and 0.46%. ANN (AUC 0.75, 95% CI, 0.73 -0.78) was the best-performing model for predicting leak, followed by XGB (AUC 0.70, 95% CI, 0.68 -0.72) and then LR (AUC 0.63, 95% CI, 0.61 -0.65, p < 0.001 for all comparisons). In detecting VTE, ANN, XGB, and LR achieved similar AUCs of 0.65 (95% CI, 0.63-0.68), 0.67 (95% CI, 0.64-0.70), and 0.64 (95% CI, 0.61-0.66) respectively; the performance difference between XGB and LR was statistically significant (p = 0.001).Conclusions: ANN and XGB outperformed traditional LR in predicting leak. These resultssuggest that ML has the potential to improve risk stratification for bariatric surgery, especially as techniques to extract more granular data from medical records improve. Further studies investigating the merits of machine learning to improve patient selection and risk management in bariatric surgery are warranted.

The U.S. military is facing a plethora of challenges as a result of tightening procurement budgets and the need to acquire new capabilities to operate in modern war environments. This requires integrating legacy systems with developing technologies in what is loosely defined to be a System of Systems. Most Systems of Systems require some integrator to manage and operate the system interfaces. In addition to technical integration challenges, these system integrators have the difficult undertaking of integrating various organizations. The boundary object framework proposed by this paper provides a tool for systems integrators working in System of Systems or any type of complex system to identify and categorize communication, coordination, and collaboration interfaces and address possible failures.

No abstract

1. Abstract The Student Nitric Oxide Explorer (SNOE) is a small scientific spacecraft designed for launch on a Pegasus™ XL launch vehicle for the USRA Student Explorer Demonstration Initiative. Its scientific goals are to measure nitric oxide density in the lower thermosphere and analyze the energy inputs to that region from the sun and magnetosphere that create it and cause its abundance to vary dramatically. These inputs are energetic solar photons in the EUV and X -ray spectral regions, and energetic electrons that are accelerated into the polar regions, where they cause auroral disturbances and displays. Both of these phenomena are aspects of solar variability; thermospheric nitric oxide responds to that variability and in tum determines key temperature and compositional aspects of the thermosphere and ionosphere through its radiative and chemical properties.The SNOE ("snowy") spacecraft and its instrument complement is being designed, built, and operated entirely at the University of Colorado, Laboratory for Atmospheric and Space Physics (CUILASP). The spacecraft is a compact hexagonal structure, 37" high and 39" across its widest dimension, weighing approximately 220 Ibs. It will be launched into a circular orbit, 550±50 km altitude, at 97.5° inclination for sun-synchronous precession at 10:30-22:30 solar time. It will spin at 5 rpm with the spin axis normal to the orbit plane. It carries three instruments: An ultraviolet spectrometer to measure nitric oxide altitude profiles, a two-channel ultraviolet photometer to measure auroral emissions beneath the spacecraft, and a five-channel solar soft X-ray photometer.The spacecraft structure is aluminum, with a center platform section for the instruments and primary components and truss work to hold the solar arrays. Power is regulated using switched arrays and a partial shunt. The attitude determination and control system uses a magnetometer, two torque rods, and two horizon crossing indicators to measure spin rate and orientation. Attitude control is implemented open-loop by ground commands. The command and data handling system is implemented using a single spacecraft microprocessor that handles all spacecraft and communications functions and instrument data. The communications system is NASA compatible for downlink using the Autonomous Ground Services station at Poker Flat; all mission operations, data processing, and analysis will be performed using a project operations control center (POCC) at the LASP Space Technology Research building.2. Introduction The Student Explorer Demonstration Initiative (STEDI) is a program administrated by the Universities Space Research Association (USRA) and funded by NASA. Its goal is to demonstrate that significant scientific and/or technology experiments can be accomplished with small satellites and constrained budgets. The original design parameters for low-earthorbit experiments were "300 pounds to 300 nautical miles" for one year in polar or near-polar orbit. A firm budget limit of $4.3M was applied to the spacecraft, i...