Objective: We explored whether use of deep learning to model temporal relations among events in electronic health records (EHRs) would improve model performance in predicting initial diagnosis of ...heart failure (HF) compared to conventional methods that ignore temporality.
Materials and Methods: Data were from a health system’s EHR on 3884 incident HF cases and 28 903 controls, identified as primary care patients, between May 16, 2000, and May 23, 2013. Recurrent neural network (RNN) models using gated recurrent units (GRUs) were adapted to detect relations among time-stamped events (eg, disease diagnosis, medication orders, procedure orders, etc.) with a 12- to 18-month observation window of cases and controls. Model performance metrics were compared to regularized logistic regression, neural network, support vector machine, and K-nearest neighbor classifier approaches.
Results: Using a 12-month observation window, the area under the curve (AUC) for the RNN model was 0.777, compared to AUCs for logistic regression (0.747), multilayer perceptron (MLP) with 1 hidden layer (0.765), support vector machine (SVM) (0.743), and K-nearest neighbor (KNN) (0.730). When using an 18-month observation window, the AUC for the RNN model increased to 0.883 and was significantly higher than the 0.834 AUC for the best of the baseline methods (MLP).
Conclusion: Deep learning models adapted to leverage temporal relations appear to improve performance of models for detection of incident heart failure with a short observation window of 12–18 months.
Lignin is the only large-volume renewable source of aromatic chemicals. Efficient depolymerization and deoxygenation of lignin while retaining the aromatic functionality are attractive but extremely ...challenging. Here we report the selective production of arenes via direct hydrodeoxygenation of organosolv lignin over a porous Ru/Nb
O
catalyst that enabled the complete removal of the oxygen content from lignin. The conversion of birch lignin to monomer C
-C
hydrocarbons is nearly quantitative based on its monomer content, with a total mass yield of 35.5 wt% and an exceptional arene selectivity of 71 wt%. Inelastic neutron scattering and DFT calculations confirm that the Nb
O
support is catalytically unique compared with other traditional oxide supports, and the disassociation energy of C
-OH bonds in phenolics is significantly reduced upon adsorption on Nb
O
, resulting in its distinct selectivity to arenes. This one-pot process provides a promising approach for improved lignin valorization with general applicability.
Pharmaceuticals have been considered ‘contaminants of emerging concern’ for more than 20 years. In that time, many laboratory studies have sought to identify hazard and assess risk in the aquatic ...environment, whilst field studies have searched for targeted candidates and occurrence trends using advanced analytical techniques. However, a lack of a systematic approach to the detection and quantification of pharmaceuticals has provided a fragmented literature of serendipitous approaches. Evaluation of the extent of the risk for the plethora of human and veterinary pharmaceuticals available requires the reliable measurement of trace levels of contaminants across different environmental compartments (water, sediment, biota - of which biota has been largely neglected). The focus on pharmaceutical concentrations in surface waters and other exposure media have therefore limited both the characterisation of the exposome in aquatic wildlife and the understanding of cause and effect relationships. Here, we compile the current analytical approaches and available occurrence and accumulation data in biota to review the current state of research in the field. Our analysis provides evidence in support of the ‘Matthew Effect’ and raises critical questions about the use of targeted analyte lists for biomonitoring. We provide six recommendations to stimulate and improve future research avenues.
Display omitted
•Occurrence and accumulation of pharmaceuticals in aquatic fauna is presented.•Evidence of the Matthew Effect from biased pharmaceutical pre-selection.•Field versus laboratory derived accumulation factors showed a large disparity.•Specific accumulation is pronounced for liver and bile over other tissues.•Recommendations for advancements within environmental toxicology are proposed.
The determination of the pharmaceutical exposome in aquatic fauna is critical to understanding the extent of contamination and the potential risk in the environment.
Being the only sustainable source of organic carbon, biomass is playing an ever-increasingly important role in our energy landscape. The conversion of renewable lignocellulosic biomass into liquid ...fuels is particularly attractive but extremely challenging due to the inertness and complexity of lignocellulose. Here we describe the direct hydrodeoxygenation of raw woods into liquid alkanes with mass yields up to 28.1 wt% over a multifunctional Pt/NbOPO4 catalyst in cyclohexane. The superior performance of this catalyst allows simultaneous conversion of cellulose, hemicellulose and, more significantly, lignin fractions in the wood sawdust into hexane, pentane and alkylcyclohexanes, respectively. Investigation on the molecular mechanism reveals that a synergistic effect between Pt, NbOx species and acidic sites promotes this highly efficient hydrodeoxygenation of bulk lignocellulose. No chemical pretreatment of the raw woody biomass or separation is required for this one-pot process, which opens a general and energy-efficient route for converting raw lignocellulose into valuable alkanes.
The use and functionality of electronic health records (EHRs) have increased rapidly in the past decade. Although the primary purpose of EHRs is clinical, researchers have used them to conduct ...epidemiologic investigations, ranging from cross-sectional studies within a given hospital to longitudinal studies on geographically distributed patients. Herein, we describe EHRs, examine their use in population health research, and compare them with traditional epidemiologic methods. We describe diverse research applications that benefit from the large sample sizes and generalizable patient populations afforded by EHRs. These have included reevaluation of prior findings, a range of diseases and subgroups, environmental and social epidemiology, stigmatized conditions, predictive modeling, and evaluation of natural experiments. Although studies using primary data collection methods may have more reliable data and better population retention, EHR-based studies are less expensive and require less time to complete. Future EHR epidemiology with enhanced collection of social behavior measures, linkage with vital records, and integration of emerging technologies such as personal sensing could improve clinical care and population health.
This study combined high resolution mass spectrometry (HRMS), advanced chemometrics and pathway enrichment analysis to analyse the blood metabolome of patients attending the memory clinic: cases of ...mild cognitive impairment (MCI; n = 16), cases of MCI who upon subsequent follow-up developed Alzheimer's disease (MCI_AD; n = 19), and healthy age-matched controls (Ctrl; n = 37). Plasma was extracted in acetonitrile and applied to an Acquity UPLC HILIC (1.7μm x 2.1 x 100 mm) column coupled to a Xevo G2 QTof mass spectrometer using a previously optimised method. Data comprising 6751 spectral features were used to build an OPLS-DA statistical model capable of accurately distinguishing Ctrl, MCI and MCI_AD. The model accurately distinguished (R2 = 99.1%; Q2 = 97%) those MCI patients who later went on to develop AD. S-plots were used to shortlist ions of interest which were responsible for explaining the maximum amount of variation between patient groups. Metabolite database searching and pathway enrichment analysis indicated disturbances in 22 biochemical pathways, and excitingly it discovered two interlinked areas of metabolism (polyamine metabolism and L-Arginine metabolism) were differentially disrupted in this well-defined clinical cohort. The optimised untargeted HRMS methods described herein not only demonstrate that it is possible to distinguish these pathologies in human blood but also that MCI patients 'at risk' from AD could be predicted up to 2 years earlier than conventional clinical diagnosis. Blood-based metabolite profiling of plasma from memory clinic patients is a novel and feasible approach in improving MCI and AD diagnosis and, refining clinical trials through better patient stratification.
Background
Relatively little is known about the stability of a diagnosis of episodic migraine (EM) or chronic migraine (CM) over time. This study examines natural fluctuations in self-reported ...headache frequency as well as the stability and variation in migraine type among individuals meeting criteria for EM and CM at baseline.
Methods
The Chronic Migraine Epidemiology and Outcomes (CaMEO) Study was a longitudinal survey of US adults with EM and CM identified by a web-questionnaire. A validated questionnaire was used to classify respondents with EM (<15 headache days/month) or CM (≥15 headache days/month) every three months for a total of five assessments. We described longitudinal persistence of baseline EM and CM classifications. In addition, we modelled longitudinal variation in headache day frequency per month using negative binomial repeated measures regression models (NBRMR).
Results
Among the 5464 respondents with EM at baseline providing four or five waves of data, 5048 (92.4%) had EM in all waves and 416 (7.6%) had CM in at least one wave. Among 526 respondents with CM at baseline providing four or five waves of data, 140 (26.6%) had CM in every wave and 386 (73.4%) had EM for at least one wave. Individual plots revealed striking within-person variations in headache days per month. The NBRMR model revealed that the rate of headache days increased across waves of observation 19% more per wave for CM compared to EM (rate ratio RR, 1.19; 95% CI, 1.13–1.26). After adjustment for covariates, the relative difference changed to a 26% increase per wave (RR, 1.26; 95% CI, 1.2–1.33).
Conclusions
Follow-up at three-month intervals reveals a high level of short-term variability in headache days per month. As a consequence, many individuals cross the CM diagnostic boundary of ≥15 headache days per month.Nearly three quarters of persons with CM at baseline drop below this diagnostic boundary at least once over the course of a year. These findings are of interest in the consideration of headache classification and diagnosis, the design and interpretation of epidemiologic and clinical studies, and clinical management.
Display omitted
•The current environmental risk assessment does not include mechanistic evaluations.•We developed a pharmacology-informed framework to predict the risk of 25 NSAIDs.•The mechanistic ...promiscuity of the 25 NSAIDs enhances the risk of mixture effects.•Exposure to NSAIDs in the environment may cause adverse effects in wild fish.•Risk is increased by high population density, drug use, and low dilution of waste-water effluents.
The presence of non-steroidal anti-inflammatory drugs (NSAIDs) in the aquatic environment has raised concern that chronic exposure to these compounds may cause adverse effects in wild fish populations. This potential scenario has led some stakeholders to advocate a stricter regulation of NSAIDs, especially diclofenac. Considering their global clinical importance for the management of pain and inflammation, any regulation that may affect patient access to NSAIDs will have considerable implications for public health. The current environmental risk assessment of NSAIDs is driven by the results of a limited number of standard toxicity tests and does not take into account mechanistic and pharmacological considerations. Here we present a pharmacology-informed framework that enables the prediction of the risk posed to fish by 25 different NSAIDs and their dynamic mixtures. Using network pharmacology approaches, we demonstrated that these 25 NSAIDs display a significant mechanistic promiscuity that could enhance the risk of target-mediated mixture effects near environmentally relevant concentrations. Integrating NSAIDs pharmacokinetic and pharmacodynamic features, we provide highly specific predictions of the adverse phenotypes associated with exposure to NSAIDs, and we developed a visual multi-scale model to guide the interpretation of the toxicological relevance of any given set of NSAIDs exposure data. Our analysis demonstrated a non-negligible risk posed to fish by NSAID mixtures in situations of high drug use and low dilution of waste-water treatment plant effluents. We anticipate that this predictive framework will support the future regulatory environmental risk assessment of NSAIDs and increase the effectiveness of ecopharmacovigilance strategies. Moreover, it can facilitate the prediction of the toxicological risk posed by mixtures via the implementation of mechanistic considerations and could be readily extended to other classes of chemicals.
We report a comprehensive study of Mars dayglow observations focusing on upper atmospheric structure and seasonal variability. We analyzed 744 vertical brightness profiles comprised of ∼109,300 ...spectra obtained with the Imaging Ultraviolet Spectrograph (IUVS) aboard the Mars Atmosphere and Volatile EvolutioN (MAVEN) satellite. The dayglow emission spectra show features similar to previous UV measurements at Mars. We find a significant drop in thermospheric scale height and temperature between LS = 218° and LS = 337–352°, attributed primarily to the decrease in solar activity and increase in heliocentric distance. We report the detection of a second, low‐altitude peak in the emission profile of OI 297.2 nm, confirmation of the prediction that the absorption of solar Lyman alpha emission is an important energy source there. The
CO2+ UV doublet peak intensity is well correlated with simultaneous observations of solar 17–22 nm irradiance at Mars.
Key Points
Significant drop in thermospheric temperature between two Martian seasons
Detection of second layer of OI 297.2 nm emission below 100 km
Strong correlation between observed mid‐UV dayglow and simultaneously measured EUV flux at Mars