Joint embedding-classifier learning for interpretable collaborative filtering.

Background: Interpretability is a topical question in recommender systems, especially in healthcare applications. An interpretable classifier quantifies the importance of each input feature for the predicted item-user association in a non-ambiguous fashion.

Results: We introduce the novel Joint Embedding Learning-classifier for improved Interpretability (JELI).

Comprehensive evaluation of pure and hybrid collaborative filtering in drug repurposing.

Drug development is known to be a costly and time-consuming process, which is prone to high failure rates. Drug repurposing allows drug discovery by reusing already approved compounds. The outcomes of past clinical trials can be used to predict novel drug-disease associations by leveraging drug- and disease-related similarities.

One-quarter of freshwater fauna threatened with extinction.

Freshwater ecosystems are highly biodiverse and important for livelihoods and economic development, but are under substantial stress. To date, comprehensive global assessments of extinction risk have not included any speciose groups primarily living in freshwaters. Consequently, data from predominantly terrestrial tetrapods are used to guide environmental policy and conservation prioritization, whereas recent proposals for target setting in freshwaters use abiotic factors.

A multi-taxon analysis of European Red Lists reveals major threats to biodiversity.

Biodiversity loss is a major global challenge and minimizing extinction rates is the goal of several multilateral environmental agreements. Policy decisions require comprehensive, spatially explicit information on species' distributions and threats. We present an analysis of the conservation status of 14,669 European terrestrial, freshwater and marine species (ca.

End-of life medical spending and care pathways in the last 12 months of life: A comprehensive analysis of the national claims database in France.

Background: To inform policy makers on efficient provision of end-of-life care, we estimated the 12-month medical expenditures of French decedents in 2015.

Methods: We estimated total medical expenditures by service type and diagnosis category, and analyzed care pathways for breast cancer, dementia, chronic obstructive lung disease.

Results: 501,121 individuals died in 2015, 59% of whom were in a hospital at the time of death.

Body-weight variability and risk of cardiovascular outcomes in patients with type 1 diabetes: a retrospective observational analysis of data from the DCCT/EDIC population.

Background: Cardiovascular risk and body-weight management are both emerging challenges of type 1 diabetes care. We evaluated the association between intraindividual variability of body-weight and risk of cardiovascular events in people with type 1 diabetes.

Methods: We analyzed 1,398 participants from the DCCT/EDIC studies.

Multidimensional Item Response Theory in the Style of Collaborative Filtering.

This paper presents a machine learning approach to multidimensional item response theory (MIRT), a class of latent factor models that can be used to model and predict student performance from observed assessment data. Inspired by collaborative filtering, we define a general class of models that includes many MIRT models. We discuss the use of penalized joint maximum likelihood to estimate individual models and cross-validation to select the best performing model.

Interdisciplinary Research in Artificial Intelligence: Challenges and Opportunities.

The use of artificial intelligence (AI) in a variety of research fields is speeding up multiple digital revolutions, from shifting paradigms in healthcare, precision medicine and wearable sensing, to public services and education offered to the masses around the world, to future cities made optimally efficient by autonomous driving. When a revolution happens, the consequences are not obvious straight away, and to date, there is no uniformly adapted framework to guide AI research to ensure a sustainable societal transition. To answer this need, here we analyze three key challenges to interdisciplinary AI research, and deliver three broad conclusions: 1) future development of AI should not only impact other scientific domains but should also take inspiration and benefit from other fields of science, 2) AI research must be accompanied by decision explainability, dataset bias transparency as well as development of evaluation methodologies and creation of regulatory agencies to ensure responsibility, and 3) AI education should receive more attention, efforts and innovation from the educational and scientific communities.

Conservation resource allocation, small population resiliency, and the fallacy of conservation triage.

Some conservation prioritization methods are based on the assumption that conservation needs overwhelm current resources and not all species can be conserved; therefore, a conservation triage scheme (i.e., when the system is overwhelmed, species should be divided into three groups based on likelihood of survival, and efforts should be focused on those species in the group with the best survival prospects and reduced or denied to those in the group with no survival prospects and to those in the group not needing special efforts for their conservation) is necessary to guide resource allocation.

International electronic health record-derived COVID-19 clinical course profiles: the 4CE consortium.

We leveraged the largely untapped resource of electronic health record data to address critical clinical and epidemiological questions about Coronavirus Disease 2019 (COVID-19). To do this, we formed an international consortium (4CE) of 96 hospitals across five countries (www.covidclinical.

The importance and benefits of species.

Humans depend on biodiversity in myriad ways, yet species are being rapidly lost due to human activities. The ecosystem services approach to conservation tries to establish the value that society derives from the natural world such that the true cost of proposed development actions becomes apparent to decision makers. Species are an integral component of ecosystems, and the value they provide in terms of services should be a standard part of ecosystem assessments.

Identifying the world's most climate change vulnerable species: a systematic trait-based assessment of all birds, amphibians and corals.

Climate change will have far-reaching impacts on biodiversity, including increasing extinction rates. Current approaches to quantifying such impacts focus on measuring exposure to climatic change and largely ignore the biological differences between species that may significantly increase or reduce their vulnerability. To address this, we present a framework for assessing three dimensions of climate change vulnerability, namely sensitivity, exposure and adaptive capacity; this draws on species' biological traits and their modeled exposure to projected climatic changes.

The impact of conservation on the status of the world's vertebrates.

Using data for 25,780 species categorized on the International Union for Conservation of Nature Red List, we present an assessment of the status of the world's vertebrates. One-fifth of species are classified as Threatened, and we show that this figure is increasing: On average, 52 species of mammals, birds, and amphibians move one category closer to extinction each year. However, this overall pattern conceals the impact of conservation successes, and we show that the rate of deterioration would have been at least one-fifth again as much in the absence of these.

Global biodiversity: indicators of recent declines.

In 2002, world leaders committed, through the Convention on Biological Diversity, to achieve a significant reduction in the rate of biodiversity loss by 2010. We compiled 31 indicators to report on progress toward this target. Most indicators of the state of biodiversity (covering species' population trends, extinction risk, habitat extent and condition, and community composition) showed declines, with no significant recent reductions in rate, whereas indicators of pressures on biodiversity (including resource consumption, invasive alien species, nitrogen pollution, overexploitation, and climate change impacts) showed increases.

The status of the world's land and marine mammals: diversity, threat, and knowledge.

Knowledge of mammalian diversity is still surprisingly disparate, both regionally and taxonomically. Here, we present a comprehensive assessment of the conservation status and distribution of the world's mammals. Data, compiled by 1700+ experts, cover all 5487 species, including marine mammals.

Hematologic and serum biochemistry values in two species of free-ranging porcupines (Coendou prehensilis, Coendou melanurus) in French Guiana.

Individuals of two porcupine species (Coendou prehensilis and Coendou melanurus) were translocated during the flooding of a forest at a hydroelectric dam site in French Guiana. Blood samples were collected for 11 mo to determine hematologic and serum chemistry reference mean values and ranges and to look for blood parasites. Male C.

Abundance, use of space, and activity patterns of white-faced sakis (Pithecia pithecia) in French Guiana.

White-faced sakis (Pithecia pithecia) are among the least studied neotropical primates. The combination of shy and quiet behavior, their ability to move silently, and the extreme difficulty of capturing them may explain why very few field studies have been undertaken in undisturbed habitats. During the course of a wildlife rescue in French Guiana, six individuals were captured and translocated to a safe area of primary rainforest.

Health evaluation of translocated free-ranging primates in French Guiana.

Among over 40 mammal species threatened by the filling of a hydroelectric dam reservoir in French Guiana, three species of primates have been translocated, comprising 124 red howler monkeys, six white-faced sakis, and 95 golden-handed tamarins. Health status of the animals was evaluated by direct physical examination and by hematological, biochemical, virological, and parasitological surveys of collected blood. The physical condition of the howlers was slightly worse toward the end of the capture period, but that of sakis and tamarins remained satisfactory.

Trypanosomatidae from wild mammals in the neotropical rainforest of French Guiana.

The initial filling of the reservoir behind the Petit Saut hydro-electric dam, on the Sinnamary River in French Guiana, threatened the terrestrial and arboreal animals living in the neotropical rainforest being flooded. During a rescue programme between 24 October and 12 November in 1994, many of these animals were checked for infection with trypanosomatids. Overall, 45 blood samples and 54 skin biopsies were collected from 53 mammals (of 13 species representing five orders) and blood samples were also taken from each of nine reptiles (six species from four families).

A survey of hemoparasite infections in free-ranging mammals and reptiles in French Guiana.

Blood smears of 1,353 free-ranging mammals (35 species) and 112 reptiles (31 species) from French Guiana were examined for hemoparasites. Parasites from 3 major groups were recorded: Apicomplexa (including hemogregarines, piroplasms, and Plasmodium spp.), Trypanosomatidae, and Filaroidea.