AI as an intervention: improving clinical outcomes relies on a causal approach to AI development and validation.

The primary practice of healthcare artificial intelligence (AI) starts with model development, often using state-of-the-art AI, retrospectively evaluated using metrics lifted from the AI literature like AUROC and DICE score. However, good performance on these metrics may not translate to improved clinical outcomes. Instead, we argue for a better development pipeline constructed by working backward from the end goal of positively impacting clinically relevant outcomes using AI, leading to considerations of causality in model development and validation, and subsequently a better development pipeline.

A time-calibrated salamander phylogeny including 765 species and 503 genes.

Recent time-calibrated amphibian phylogenies agree on the family-level relationships among extant salamanders but had disparate sampling regimes and inferred very different divergence times. For example, a recent phylogenomic study based on 220 nuclear loci had limited taxon sampling (41 species) and estimated relatively young divergence dates, whereas a more extensive supermatrix study based on 15 genes and 481 species estimated dates that were 22-45 million years older for major clades. Here, we combined phylogenomic and supermatrix approaches to estimate the largest salamander phylogeny to date based on molecular markers.

What Predicts Gene Flow During Speciation? The Relative Roles of Time, Space, Morphology and Climate.

The processes that restrict gene flow between populations are fundamental to speciation. Here, we develop a simple framework for studying whether divergence in morphology, climatic niche, time and space contribute to reduced gene flow among populations and species. We apply this framework to a model system involving a clade of spiny lizards (Sceloporus) occurring mostly in northeastern Mexico, which show striking variation in morphology and habitat among closely related species and populations.

Racial differences in laboratory testing as a potential mechanism for bias in AI: A matched cohort analysis in emergency department visits.

AI models are often trained using available laboratory test results. Racial differences in laboratory testing may bias AI models for clinical decision support, amplifying existing inequities. This study aims to measure the extent of racial differences in laboratory testing in adult emergency department (ED) visits.

How life became colourful: colour vision, aposematism, sexual selection, flowers, and fruits.

Plants and animals are often adorned with potentially conspicuous colours (e.g. red, yellow, orange, blue, purple).

Learning control-ready forecasters for Blood Glucose Management.

Type 1 diabetes (T1D) presents a significant health challenge, requiring patients to actively manage their blood glucose (BG) levels through regular bolus insulin administration. Automated control solutions based on machine learning (ML) models could reduce the need for manual patient intervention. However, the accuracy of current models falls short of what is needed.

Shortcomings in the Evaluation of Blood Glucose Forecasting.

Objective: Recent years have seen an increase in machine learning (ML)-based blood glucose (BG) forecasting models, with a growing emphasis on potential application to hybrid or closed-loop predictive glucose controllers. However, current approaches focus on evaluating the accuracy of these models using benchmark data generated under the behavior policy, which may differ significantly from the data the model may encounter in a control setting. This study challenges the efficacy of such evaluation approaches, demonstrating that they can fail to accurately capture an ML-based model's true performance in closed-loop control settings.

Toward Realizing the Promise of AI in Precision Health Across the Spectrum of Care.

Significant progress has been made in augmenting clinical decision-making using artificial intelligence (AI) in the context of secondary and tertiary care at large academic medical centers. For such innovations to have an impact across the spectrum of care, additional challenges must be addressed, including inconsistent use of preventative care and gaps in chronic care management. The integration of additional data, including genomics and data from wearables, could prove critical in addressing these gaps, but technical, legal, and ethical challenges arise.

Hidden hotspots of amphibian biodiversity in China.

Identifying and protecting hotspots of endemism and species richness is crucial for mitigating the global biodiversity crisis. However, our understanding of spatial diversity patterns is far from complete, which severely limits our ability to conserve biodiversity hotspots. Here, we report a comprehensive analysis of amphibian species diversity in China, one of the most species-rich countries on Earth.

Predicting 5-year dementia conversion in veterans with mild cognitive impairment.

Introduction: Identifying mild cognitive impairment (MCI) patients at risk for dementia could facilitate early interventions. Using electronic health records (EHRs), we developed a model to predict MCI to all-cause dementia (ACD) conversion at 5 years.

Methods: Cox proportional hazards model was used to identify predictors of ACD conversion from EHR data in veterans with MCI.

How many species will Earth lose to climate change?

Climate change may be an important threat to global biodiversity, potentially leading to the extinction of numerous species. But how many? There have been various attempts to answer this question, sometimes yielding strikingly different estimates. Here, we review these estimates, assess their disagreements and methodology, and explore how we might reach better estimates.

The causes of species richness patterns among clades.

Two major types of species richness patterns are spatial (e.g. the latitudinal diversity gradient) and clade-based (e.

Learning Concept Credible Models for Mitigating Shortcuts.

During training, models can exploit spurious correlations as shortcuts, resulting in poor generalization performance when shortcuts do not persist. In this work, assuming access to a representation based on domain knowledge () that is invariant to shortcuts, we aim to learn robust and accurate models from biased training data. In contrast to previous work, we do not rely solely on known concepts, but allow the model to also learn unknown concepts.

How many species are there on Earth? Progress and problems.

How many species exist on Earth? Projections range from millions to trillions. A 2011 paper in PLOS Biology provided a comprehensive estimate of 9 million.

The radiation continuum and the evolution of frog diversity.

Most of life's vast diversity of species and phenotypes is often attributed to adaptive radiation. Yet its contribution to species and phenotypic diversity of a major group has not been examined. Two key questions remain unresolved.

Sexual Health Assessment in Women with Lung Cancer study: Sexual health assessment in women with lung cancer.

Background: Sexual health is understudied and underreported in patients with lung cancer, and most data precede the approval of widely used targeted therapies and immune checkpoint inhibitors. The authors sought to evaluate the prevalence of sexual dysfunction in women with lung cancer in our current clinical environment.

Methods: This cross-sectional survey study was administered online to 249 women via the GO2 for Lung Cancer (GO2) Registry, using the Patient-Reported Outcomes Measurement Information System Sexual Function and Satisfaction Measures questionnaire.

Accelerating local extinction associated with very recent climate change.

Climate change has already caused local extinction in many plants and animals, based on surveys spanning many decades. As climate change accelerates, the pace of these extinctions may also accelerate, potentially leading to large-scale, species-level extinctions. We tested this hypothesis in a montane lizard.

Machine Learning Analysis of Raman Spectra To Quantify the Organic Constituents in Complex Organic-Mineral Mixtures.

Important decisions in local agricultural policy and practice often hinge on the soil's chemical composition. Raman spectroscopy offers a rapid noninvasive means to quantify the constituents of complex organic systems. But the application of Raman spectroscopy to soils presents a multifaceted challenge due to organic/mineral compositional complexity and spectral interference arising from overwhelming fluorescence.