Predictive modeling is fundamental for extracting value from large clinical data sets, or “big clinical data,” advancing clinical research, and improving healthcare. Machine learning is a powerful approach to predictive modeling. Two factors make machine learning challenging for healthcare researchers. First, before training a machine learning model, the values of one or more model parameters called hyper-parameters must typically be specified. Due to their inexperience with machine learning, it is hard for healthcare researchers to choose an appropriate algorithm and hyper-parameter values. Second, many clinical data are stored in a special format. These data must be iteratively transformed into the relational table format before conducting predictive modeling. This transformation is time-consuming and requires computing expertise.
Inappropriate ordering and acquisition of urine cultures leads to unnecessary treatment of asymptomatic bacteriuria (ASB). Treatment of ASB contributes to antimicrobial resistance particularly among hospital-acquired organisms. Our objective was to investigate urine culture ordering and collection practices among nurses to identify key system-level and human factor barriers and facilitators that affect optimal ordering and collection practices.
- Proceedings of the National Academy of Sciences of the United States of America
- Published about 4 years ago
Coastal hypoxia (dissolved oxygen ≤ 2 mg/L) is a growing problem worldwide that threatens marine ecosystem services, but little is known about economic effects on fisheries. Here, we provide evidence that hypoxia causes economic impacts on a major fishery. Ecological studies of hypoxia and marine fauna suggest multiple mechanisms through which hypoxia can skew a population’s size distribution toward smaller individuals. These mechanisms produce sharp predictions about changes in seafood markets. Hypoxia is hypothesized to decrease the quantity of large shrimp relative to small shrimp and increase the price of large shrimp relative to small shrimp. We test these hypotheses using time series of size-based prices. Naive quantity-based models using treatment/control comparisons in hypoxic and nonhypoxic areas produce null results, but we find strong evidence of the hypothesized effects in the relative prices: Hypoxia increases the relative price of large shrimp compared with small shrimp. The effects of fuel prices provide supporting evidence. Empirical models of fishing effort and bioeconomic simulations explain why quantifying effects of hypoxia on fisheries using quantity data has been inconclusive. Specifically, spatial-dynamic feedbacks across the natural system (the fish stock) and human system (the mobile fishing fleet) confound “treated” and “control” areas. Consequently, analyses of price data, which rely on a market counterfactual, are able to reveal effects of the ecological disturbance that are obscured in quantity data. Our results are an important step toward quantifying the economic value of reduced upstream nutrient loading in the Mississippi Basin and are broadly applicable to other coupled human-natural systems.
Communication about physical activity (PA) frames PA and influences what it means to people, including the role it plays in their lives. To the extent that PA messages can be designed to reflect outcomes that are relevant to what people most value experiencing and achieving in their daily lives, the more compelling and effective they will be. Aligned with self-determination theory, this study investigated proximal goals and values that are salient in everyday life and how they could be leveraged through new messaging to better support PA participation among women. The present study was designed to examine the nature of women’s daily goals and priorities and investigate women’s PA beliefs, feelings, and experiences, in order to identify how PA may compete with or facilitate women’s daily goals and priorities. Preliminary recommendations are proposed for designing new PA messages that align PA with women’s daily goals and desired experiences to better motivate participation.
- Proceedings of the National Academy of Sciences of the United States of America
- Published almost 3 years ago
Craving is thought to be a specific desire state that biases choice toward the desired object, be it chocolate or drugs. A vast majority of people report having experienced craving of some kind. In its pathological form craving contributes to health outcomes in addiction and obesity. Yet despite its ubiquity and clinical relevance we still lack a basic neurocomputational understanding of craving. Here, using an instantaneous measure of subjective valuation and selective cue exposure, we identify a behavioral signature of a food craving-like state and advance a computational framework for understanding how this state might transform valuation to bias choice. We find desire induced by exposure to a specific high-calorie, high-fat/sugar snack good is expressed in subjects' momentary willingness to pay for this good. This effect is selective but not exclusive to the exposed good; rather, we find it generalizes to nonexposed goods in proportion to their subjective attribute similarity to the exposed ones. A second manipulation of reward size (number of snack units available for purchase) further suggested that a multiplicative gain mechanism supports the transformation of valuation during laboratory craving. These findings help explain how real-world food craving can result in behaviors inconsistent with preferences expressed in the absence of craving and open a path for the computational modeling of craving-like phenomena using a simple and repeatable experimental tool for assessing subjective states in economic terms.
Arguably, the dissemination of science communication has recently entered a new age in which science must compete for public attention with fake news, alternate facts, and pseudoscience. This clash is particularly evident on social media. Facebook has taken a prime role in disseminating fake news, alternate facts, and pseudoscience, but is often ignored in the context of science outreach, especially among individual scientists. Based on new survey data, scientists appear in large Facebook networks but seldom post information about general science, their own scientific research, or culturally controversial topics in science. The typical individual scientist’s audience is large and personally connected, potentially leading to both a broad and deep engagement in science. Moreover, this media values individual expertise, allowing scientists to serve as a “Nerd of Trust” for their online friend and family networks. Science outreach via social media demands a renewed interest, and Facebook may be an overlooked high-return, low-risk science outreach tool in which scientists can play a valuable role to combat disinformation.
Formal metrics for monitoring the quality and safety of healthcare have a valuable role, but may not, by themselves, yield full insight into the range of fallibilities in organizations. ‘Soft intelligence’ is usefully understood as the processes and behaviours associated with seeking and interpreting soft data-of the kind that evade easy capture, straightforward classification and simple quantification-to produce forms of knowledge that can provide the basis for intervention. With the aim of examining current and potential practice in relation to soft intelligence, we conducted and analysed 107 in-depth qualitative interviews with senior leaders, including managers and clinicians, involved in healthcare quality and safety in the English National Health Service. We found that participants were in little doubt about the value of softer forms of data, especially for their role in revealing troubling issues that might be obscured by conventional metrics. Their struggles lay in how to access softer data and turn them into a useful form of knowing. Some of the dominant approaches they used risked replicating the limitations of hard, quantitative data. They relied on processes of aggregation and triangulation that prioritised reliability, or on instrumental use of soft data to animate the metrics. The unpredictable, untameable, spontaneous quality of soft data could be lost in efforts to systematize their collection and interpretation to render them more tractable. A more challenging but potentially rewarding approach involved processes and behaviours aimed at disrupting taken-for-granted assumptions about quality, safety, and organizational performance. This approach, which explicitly values the seeking out and the hearing of multiple voices, is consistent with conceptual frameworks of organizational sensemaking and dialogical understandings of knowledge. Using soft intelligence this way can be challenging and discomfiting, but may offer a critical defence against the complacency that can precede crisis.
The possibility that market interaction may erode moral values is a long-standing, but controversial, hypothesis in the social sciences, ethics, and philosophy. To date, empirical evidence on decay of moral values through market interaction has been scarce. We present controlled experimental evidence on how market interaction changes how human subjects value harm and damage done to third parties. In the experiment, subjects decide between either saving the life of a mouse or receiving money. We compare individual decisions to those made in a bilateral and a multilateral market. In both markets, the willingness to kill the mouse is substantially higher than in individual decisions. Furthermore, in the multilateral market, prices for life deteriorate tremendously. In contrast, for morally neutral consumption choices, differences between institutions are small.
Feeling connected to nature has been shown to be beneficial to wellbeing and pro-environmental behaviour. General nature contact and knowledge based activities are often used in an attempt to engage people with nature. However the specific routes to nature connectedness have not been examined systematically. Two online surveys (total n = 321) of engagement with, and value of, nature activities structured around the nine values of the Biophila Hypothesis were conducted. Contact, emotion, meaning, and compassion, with the latter mediated by engagement with natural beauty, were predictors of connection with nature, yet knowledge based activities were not. In a third study (n = 72), a walking intervention with activities operationalising the identified predictors, was found to significantly increase connection to nature when compared to walking in nature alone or walking in and engaging with the built environment. The findings indicate that contact, emotion, meaning, compassion, and beauty are pathways for improving nature connectedness. The pathways also provide alternative values and frames to the traditional knowledge and identification routes often used by organisations when engaging the public with nature.
U.S. sewage sludges were analyzed for 58 regulated and non-regulated elements by ICP-MS and electron microscopy to explore opportunities for removal and recovery. Sludge/water distribution coefficients (KD, L/kg dry weight) spanned five orders of magnitude, indicating significant metal accumulation in biosolids. Rare-earth elements and minor metals (Y, La, Ce, Pr, Nd, Pm, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu) detected in sludges showed enrichment factors (EFs) near unity, suggesting dust or soils as likely dominant sources. In contrast, most platinum group elements (i.e., Ru, Rh, Pd, Pt) showed high EF and KD values, indicating anthropogenic sources. Numerous metallic and metal oxide colloids (<100-500 nm diameter) were detected; the morphology of abundant aggregates of primary particles measuring <100 nm provided clues to their origin. For a community of 1 million people, metals in biosolids were valued at up to US$13 million annually. A model incorporating a parameter (KD x EF x $Value) to capture the relative potential for economic value from biosolids revealed the identity of the 13 most lucrative elements (Ag, Cu, Au, P, Fe, Pd, Mn, Zn, Ir, Al, Cd, Ti, Ga and Cr) with a combined value of US $280/ton of sludge.