RawECGNet: Deep Learning Generalization for Atrial Fibrillation Detection From the Raw ECG.

INTRODUCTION: Deep learning models for detecting episodes of atrial fibrillation (AF) using rhythm information in long-term ambulatory ECG recordings have shown high performance. However, the rhythm-based approach does not take advantage of the morphological information conveyed by the different ECG waveforms, particularly the f-waves. As a result, the performance of such models may be inherently limited. METHODS: To address this limitation, we have developed a deep learning model, named RawECGNet, to detect episodes of AF and atrial flutter (AFl) using the raw, single-lead ECG. We compare the generalization performance of RawECGNet on two external data sets that account for distribution shifts in geography, ethnicity, and lead position. RawECGNet is further benchmarked against a state-of-the-art deep learning model, named ArNet2, which utilizes rhythm information as input. RESULTS: Using RawECGNet, the results for the different leads in the external test sets in terms of the F1 score were 0.91-0.94 in RBDB and 0.93 in SHDB, compared to 0.89-0.91 in RBDB and 0.91 in SHDB for ArNet2. The results highlight RawECGNet as a high-performance, generalizable algorithm for detection of AF and AFl episodes, exploiting information on both rhythm and morphology.

Land-use changes interact with geology to facilitate dispersal of the rock hyrax (Procavia capensis) and leishmaniasis across Israel and the West Bank.

Geology plays a fundamental role in establishing species' habitats, determining both physical (e.g., landscape morphology, soil texture) and chemical (e.g., mineral composition, water availability) properties. In the current Anthropocene epoch, human activity is transforming Earth's geology and ecosystems. Yet to date, there have been almost no studies incorporating geology when examining the effect of such land-use changes on species distribution. This study seeks to uncover how specific land-use changes interact with geology, in order to explain the recent and rapid expansion of the rock hyrax (Procavia capensis) across the mountains of central Israel and the West Bank. Hyraxes are dependent on rock mounds for their habitat, and their expansion seems to be correlated with increasing infrastructure construction. However, their expansion patterns differ among locations, even when the human land-use is similar. To explain the patterns of hyrax distribution observed over the past 46 years, we converted geological data into ecological data, which present the probability of the local bedrock breaking into boulders, whether due to either natural or anthropogenic weathering processes. We applied species distribution models (SDMs) and found that the expansion of rock hyrax populations was facilitated by means of the interaction of specific geological units with land-use practices (e.g., roads and construction), which resulted in the accumulation of large boulders, creating novel habitats and stepping stones in previously unsuitable areas for hyraxes. Since rock hyraxes are major hosts of the leishmaniasis pathogen, the findings from this study offer important insights into the progression and potential outbreaks of the disease in human populations. Understanding the role that geology plays in shaping a species' niche is expected to prove useful in studying the distribution of other wildlife species and is fundamental in studies seeking to predict the potential ecological impacts on local biodiversity associated with land-use change.

Exploring the risks and benefits of flexibility in biodiversity offset location in a case study of migratory shorebirds.

Biodiversity offsets aim to counterbalance the residual impacts of development on species and ecosystems. Guidance documents explicitly recommend that biodiversity offset actions be located close to the location of impact because of higher potential for similar ecological conditions, but allowing greater spatial flexibility has been proposed. We examined the circumstances under which offsets distant from the impact location could be more likely to achieve no net loss or provide better ecological outcomes than offsets close to the impact area. We applied a graphical model for migratory shorebirds in the East Asian-Australasian Flyway as a case study to explore the problems that arise when incorporating spatial flexibility into offset planning. Spatially flexible offsets may alleviate impacts more effectively than local offsets; however, the risks involved can be substantial. For our case study, there were inadequate data to make robust conclusions about the effectiveness and equivalence of distant habitat-based offsets for migratory shorebirds. Decisions around offset placement should be driven by the potential to achieve equivalent ecological outcomes; however, when considering more distant offsets, there is a need to evaluate the likely increased risks alongside the potential benefits. Although spatially flexible offsets have the potential to provide more cost-effective biodiversity outcomes and more cobenefits, our case study showed the difficulty of demonstrating these benefits in practice and the potential risks that need to be considered to ensure effective offset placement.

Estudio de los riesgos y beneficios de la flexibilidad en la ubicación de compensación de la biodiversidad en el estudio de caso de aves costeras migratorias Resumen Las compensaciones de la biodiversidad buscan contrabalancear el impacto residual que tiene el desarrollo sobre las especies y los ecosistemas. Los documentos guía recomiendan explícitamente que las acciones de estas compensaciones estén ubicadas cerca del lugar del impacto debido al potencial elevado de que haya condiciones ecológicas similares, aunque ya hay propuestas de una mayor flexibilidad espacial. Analizamos las circunstancias bajo las cuales las compensaciones alejadas del lugar de impacto tendrían mayor probabilidad de lograr pérdidas netas nulas o de proporcionar mejores resultados ecológicos que las compensaciones cercanas al área de impacto. Aplicamos un modelo gráfico para las aves costeras migratorias en el corredor aéreo asiático-australasiático del este como estudio de caso para estudiar los problemas que surgen cuando se incorpora la flexibilidad espacial a la planeación de las compensaciones. Las compensaciones espacialmente flexibles pueden mitigar los impactos más efectivamente que las compensaciones locales; sin embargo, los riesgos que esto involucra pueden ser considerables. En nuestro estudio de caso hubo datos insuficientes para concluir contundentemente sobre la efectividad y equivalencia de las compensaciones basadas en los hábitats distantes para las aves costeras migratorias. Las decisiones en torno a la ubicación de las compensaciones deberían estar impulsadas por el potencial para obtener resultados ecológicos equivalentes; sin embargo, al considerar compensaciones más alejadas, existe la necesidad de evaluar el incremento probable de riesgos junto a los beneficios potenciales. Aunque las compensaciones espacialmente flexibles tienen el potencial para proporcionar resultados más rentables y más beneficios colaterales, nuestro estudio de caso mostró la dificultad para demostrar estos beneficios en la práctica y los riesgos potenciales que necesitan considerarse para asegurar una ubicación efectiva de las compensaciones.

Shelter availability and human attitudes as drivers of rock hyrax (Procavia capensis) expansion along a rural-urban gradient.

While anthropogenic land-use changes threaten wildlife globally, some species take advantage of such changes and disperse into urban areas. The wildlife in urban areas often promotes conflicts with humans, notably when the animals are associated with the spread of zoonotic diseases. In Israel, current urban invasion of rock hyraxes (Procavia capensis) draws public attention, since the species is a reservoir host of cutaneous leishmaniasis, a serious skin disease. The rock hyrax, however, has seldom been studied in densely populated areas, and the drivers for its urban expansion, as well as its abilities to live and spread in core urban areas, are relatively unknown. Here, we explore the rock hyrax expansion to urban areas process by examining the availability, characteristics and use of shelter along an urban gradient. Our findings suggest that a series of factors determines shelter availability and quality for the rock hyrax, which facilitates its dispersion across the urban gradient. We found that rock hyraxes from the Judean Desert expand to the peri-urban region of Jerusalem by colonizing new rocky shelters formed as by-products of urban development. With their populations reaching extreme densities in this area and saturating the available shelters, there is some spill over to the adjacent core urban areas where they colonize littered sites, which are made available due to the local socio-economic conditions and cultural norms of waste disposal and illegal placement of temporary structures. Our work emphasizes the significance of the urban gradient approach for studying the mechanisms promoting wildlife expansion to cities. Our findings suggest that changes in shelter availability and quality due to urban development, and cultural norms promote shifts of the hyrax population by pushing from the already established areas and pulling into new environment across the urban gradient.