GSTDTAP

浏览/检索结果: 共2条,第1-2条 帮助

限定条件                            
已选(0)清除 条数/页:   排序方式:
Current European flood-rich period exceptional compared with past 500 years 期刊论文
NATURE, 2020, 583 (7817) : 560-+
作者:  ;  nter Blö;  schl;  Andrea Kiss;  Alberto Viglione;  Mariano Barriendos;  Oliver Bö;  hm;  Rudolf Brá;  zdil;  Denis Coeur;  Gaston Demaré;  e;  Maria Carmen Llasat;  Neil Macdonald;  Dag Retsö;  Lars Roald;  Petra Schmocker-Fackel;  Inê;  s Amorim;  Monika Bě;  ;  nová;  Gerardo Benito;  Chiara Bertolin;  Dario Camuffo;  Daniel Cornel;  Radosł;  aw Doktor;  ;  bor Elleder;  Silvia Enzi;  Joã;  o Carlos Garcia;  ;  diger Glaser;  Julia Hall;  Klaus Haslinger;  Michael Hofstä;  tter;  ;  rgen Komma;  Danuta Limanó;  wka;  David Lun;  Andrei Panin;  Juraj Parajka;  Hrvoje Petrić;  Fernando S. Rodrigo;  Christian Rohr;  Johannes Schö;  nbein;  Lothar Schulte;  Luí;  s Pedro Silva;  Willem H. J. Toonen;  Peter Valent;  ;  rgen Waser;  Oliver Wetter
收藏  |  浏览/下载:40/0  |  提交时间:2020/08/09

There are concerns that recent climate change is altering the frequency and magnitude of river floods in an unprecedented way(1). Historical studies have identified flood-rich periods in the past half millennium in various regions of Europe(2). However, because of the low temporal resolution of existing datasets and the relatively low number of series, it has remained unclear whether Europe is currently in a flood-rich period from a long-term perspective. Here we analyse how recent decades compare with the flood history of Europe, using a new database composed of more than 100 high-resolution (sub-annual) historical flood series based on documentary evidence covering all major regions of Europe. We show that the past three decades were among the most flood-rich periods in Europe in the past 500 years, and that this period differs from other flood-rich periods in terms of its extent, air temperatures and flood seasonality. We identified nine flood-rich periods and associated regions. Among the periods richest in floods are 1560-1580 (western and central Europe), 1760-1800 (most of Europe), 1840-1870 (western and southern Europe) and 1990-2016 (western and central Europe). In most parts of Europe, previous flood-rich periods occurred during cooler-than-usual phases, but the current flood-rich period has been much warmer. Flood seasonality is also more pronounced in the recent period. For example, during previous flood and interflood periods, 41 per cent and 42 per cent of central European floods occurred in summer, respectively, compared with 55 per cent of floods in the recent period. The exceptional nature of the present-day flood-rich period calls for process-based tools for flood-risk assessment that capture the physical mechanisms involved, and management strategies that can incorporate the recent changes in risk.


Analysis of thousands of historical documents recording floods in Europe shows that flooding characteristics in recent decades are unlike those of previous centuries.


  
Video-based AI for beat-to-beat assessment of cardiac function 期刊论文
NATURE, 2020, 580 (7802) : 252-+
作者:  Pleguezuelos-Manzano, Cayetano;  Puschhof, Jens;  Huber, Axel Rosendahl;  van Hoeck, Arne;  Wood, Henry M.;  Nomburg, Jason;  Gurjao, Carino;  Manders, Freek;  Dalmasso, Guillaume;  Stege, Paul B.;  Paganelli, Fernanda L.;  Geurts, Maarten H.;  Beumer, Joep;  Mizutani, Tomohiro;  Miao, Yi;  van der Linden, Reinier;  van der Elst, Stefan;  Garcia, K. Christopher;  Top, Janetta;  Willems, Rob J. L.;  Giannakis, Marios;  Bonnet, Richard;  Quirke, Phil;  Meyerson, Matthew;  Cuppen, Edwin;  van Boxtel, Ruben;  Clevers, Hans
收藏  |  浏览/下载:117/0  |  提交时间:2020/07/03

A video-based deep learning algorithm-EchoNet-Dynamic-accurately identifies subtle changes in ejection fraction and classifies heart failure with reduced ejection fraction using information from multiple cardiac cycles.


Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease(1), screening for cardiotoxicity(2) and decisions regarding the clinical management of patients with a critical illness(3). However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training(4,5). Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.