Explore the vast range of titles available.

Only 2–5% of patients who have a stroke receive thrombolytic treatment, mainly because of delay in reaching the hospital. We aimed to assess the efficacy of a new approach of diagnosis and treatment starting at the emergency site, rather than after hospital arrival, in reducing delay in stroke therapy. We did a randomised single-centre controlled trial to compare the time from alarm (emergency call) to therapy decision between mobile stroke unit (MSU) and hospital intervention. For inclusion in our study patients needed to be aged 18–80 years and have one or more stroke symptoms that started within the previous 2·5 h. In accordance with our week-wise randomisation plan, patients received either prehospital stroke treatment in a specialised ambulance (equipped with a CT scanner, point-of-care laboratory, and telemedicine connection) or optimised conventional hospital-based stroke treatment (control group) with a 7 day follow-up. Allocation was not masked from patients and investigators. Our primary endpoint was time from alarm to therapy decision, which was analysed with the Mann-Whitney U test. Our secondary endpoints included times from alarm to end of CT and to end of laboratory analysis, number of patients receiving intravenous thrombolysis, time from alarm to intravenous thrombolysis, and neurological outcome. We also assessed safety endpoints. This study is registered with ClinicalTrials.gov, number NCT00153036. We stopped the trial after our planned interim analysis at 100 of 200 planned patients (53 in the prehospital stroke treatment group, 47 in the control group), because we had met our prespecified criteria for study termination. Prehospital stroke treatment reduced the median time from alarm to therapy decision substantially: 35 min (IQR 31–39) versus 76 min (63–94), p<0·0001; median difference 41 min (95% CI 36–48 min). We also detected similar gains regarding times from alarm to end of CT, and alarm to end of laboratory analysis, and to intravenous thrombolysis for eligible ischaemic stroke patients, although there was no substantial difference in number of patients who received intravenous thrombolysis or in neurological outcome. Safety endpoints seemed similar across the groups. For patients with suspected stroke, treatment by the MSU substantially reduced median time from alarm to therapy decision. The MSU strategy offers a potential solution to the medical problem of the arrival of most stroke patients at the hospital too late for treatment. Ministry of Health of the Saarland, Germany, the Werner-Jackstädt Foundation, the Else-Kröner-Fresenius Foundation, and the Rettungsstiftung Saar.

Early treatment with rt-PA is critical for favorable outcome of acute stroke. However, only a very small proportion of stroke patients receive this treatment, as most arrive at hospital too late to be eligible for rt-PA therapy. We developed a \"Mobile Stroke Unit\", consisting of an ambulance equipped with computed tomography, a point-of-care laboratory system for complete stroke laboratory work-up, and telemedicine capabilities for contact with hospital experts, to achieve delivery of etiology-specific and guideline-adherent stroke treatment at the site of the emergency, well before arrival at the hospital. In a departure from current practice, stroke patients could be differentially treated according to their ischemic or hemorrhagic etiology even in the prehospital phase of stroke management. Immediate diagnosis of cerebral ischemia and exclusion of thrombolysis contraindications enabled us to perform prehospital rt-PA thrombolysis as bridging to later intra-arterial recanalization in one patient. In a complementary patient with cerebral hemorrhage, prehospital diagnosis allowed immediate initiation of hemorrhage-specific blood pressure management and telemedicine consultation regarding surgery. Call-to-therapy-decision times were 35 minutes. This preliminary study proves the feasibility of guideline-adherent, etiology-specific and causal treatment of acute stroke directly at the emergency site.

(2011) Correction: Bringing the Hospital to the Patient: First Treatment of Stroke Patients at the Emergency Site. No competing interests declared.

Early treatment with rt-PA is critical for favorable outcome of acute stroke. However, only a very small proportion of stroke patients receive this treatment, as most arrive at hospital too late to be eligible for rt-PA therapy. We developed a \"Mobile Stroke Unit\", consisting of an ambulance equipped with computed tomography, a point-of-care laboratory system for complete stroke laboratory work-up, and telemedicine capabilities for contact with hospital experts, to achieve delivery of etiology-specific and guideline-adherent stroke treatment at the site of the emergency, well before arrival at the hospital. In a departure from current practice, stroke patients could be differentially treated according to their ischemic or hemorrhagic etiology even in the prehospital phase of stroke management. Immediate diagnosis of cerebral ischemia and exclusion of thrombolysis contraindications enabled us to perform prehospital rt-PA thrombolysis as bridging to later intra-arterial recanalization in one patient. In a complementary patient with cerebral hemorrhage, prehospital diagnosis allowed immediate initiation of hemorrhage-specific blood pressure management and telemedicine consultation regarding surgery. Call-to-therapy-decision times were 35 minutes. This preliminary study proves the feasibility of guideline-adherent, etiology-specific and causal treatment of acute stroke directly at the emergency site.

Early treatment with rt-PA is critical for favorable outcome of acute stroke. However, only a very small proportion of stroke patients receive this treatment, as most arrive at hospital too late to be eligible for rt-PA therapy. We developed a \"Mobile Stroke Unit\", consisting of an ambulance equipped with computed tomography, a point-of-care laboratory system for complete stroke laboratory work-up, and telemedicine capabilities for contact with hospital experts, to achieve delivery of etiology-specific and guideline-adherent stroke treatment at the site of the emergency, well before arrival at the hospital. In a departure from current practice, stroke patients could be differentially treated according to their ischemic or hemorrhagic etiology even in the prehospital phase of stroke management. Immediate diagnosis of cerebral ischemia and exclusion of thrombolysis contraindications enabled us to perform prehospital rt-PA thrombolysis as bridging to later intra-arterial recanalization in one patient. In a complementary patient with cerebral hemorrhage, prehospital diagnosis allowed immediate initiation of hemorrhage-specific blood pressure management and telemedicine consultation regarding surgery. Call-to-therapy-decision times were 35 minutes. This preliminary study proves the feasibility of guideline-adherent, etiology-specific and causal treatment of acute stroke directly at the emergency site.

We consider using deep neural networks to solve time-dependent partial differential equations (PDEs), where multi-scale processing is crucial for modeling complex, time-evolving dynamics. While the U-Net architecture with skip connections is commonly used by prior studies to enable multi-scale processing, our analysis shows that the need for features to evolve across layers results in temporally misaligned features in skip connections, which limits the model's performance. To address this limitation, we propose SineNet, consisting of multiple sequentially connected U-shaped network blocks, referred to as waves. In SineNet, high-resolution features are evolved progressively through multiple stages, thereby reducing the amount of misalignment within each stage. We furthermore analyze the role of skip connections in enabling both parallel and sequential processing of multi-scale information. Our method is rigorously tested on multiple PDE datasets, including the Navier-Stokes equations and shallow water equations, showcasing the advantages of our proposed approach over conventional U-Nets with a comparable parameter budget. We further demonstrate that increasing the number of waves in SineNet while maintaining the same number of parameters leads to a monotonically improved performance. The results highlight the effectiveness of SineNet and the potential of our approach in advancing the state-of-the-art in neural PDE solver design. Our code is available as part of AIRS (https://github.com/divelab/AIRS).

We consider solving partial differential equations (PDEs) with Fourier neural operators (FNOs), which operate in the frequency domain. Since the laws of physics do not depend on the coordinate system used to describe them, it is desirable to encode such symmetries in the neural operator architecture for better performance and easier learning. While encoding symmetries in the physical domain using group theory has been studied extensively, how to capture symmetries in the frequency domain is under-explored. In this work, we extend group convolutions to the frequency domain and design Fourier layers that are equivariant to rotations, translations, and reflections by leveraging the equivariance property of the Fourier transform. The resulting \\(G\\)-FNO architecture generalizes well across input resolutions and performs well in settings with varying levels of symmetry. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS).

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.