A multi-modal wildfire prediction and early-warning system based on a novel machine learning framework.

Wildfires are increasingly impacting the environment and human health. Among the top 20 California wildfires, those in 2020-2021 burned more acres than the last century combined. Lack of an adequate early warning system impacts the health and safety of vulnerable populations disproportionately and widens the inequality gap. In this project, a multi-modal wildfire prediction and early warning system has been developed based on a novel spatio-temporal machine learning architecture. A comprehensive wildfire database with over 37 million data points was created, including the historical wildfires, environmental and meteorological sensor data from the Environmental Protection Agency, and geological data. The data was augmented into 2.53 km × 2.53 km square grids to overcome the sensor network coverage limitations. Leading and trailing indicators for the wildfires are proposed, classified, and tested. The leading indicators are correlated to the risks of wildfire conception, whereas the trailing indicators are correlated to the byproducts of the wildfires. Additionally, geological data was incorporated to provide additional information for better assessment on wildfire risks and propagation. Next, a novel U-Convolutional Long Short-Term Memory (ULSTM) neural network was developed to extract key spatial and temporal features of the dataset, specifically to address the spatial nature of the location of the wildfire and time-progression temporal nature of the wildfire evolution. Through iterative improvements and optimization, the final ULSTM network architecture, trained with data from 2012 to 2017, achieved >97% accuracy for predicting wildfires in 2018, as compared to ∼76% using traditional Convolutional Neural Network (CNN) techniques. The final model was applied to conduct a retrospective study for the 2018-2022 wildfire seasons, and successfully predicted 85.7% of wildfires >300 K acres in size. This technique could enable fire departments to anticipate and prevent wildfires before they strike and provide early warnings for at-risk individuals for better preparation, thereby saving lives, protecting the environment, and avoiding economic damages.

[HDL cholesterol and high-sensitive troponin T as predictive biomarkers of atrial fibrillation after heart surgery]. / Colesterol HDL y troponina T ultrasensible como biomarcadores predictivos de fibrilación auricular postoperatoria.

INTRODUCTION: Atrial fibrillation (AF) has an incidence rate of approximately 30% and is the most frequent arrhythmia following heart surgery. Factors such as inflammation, the presence of heart fibrosis, stress and cardiomyocyte apoptosis, have all been associated with AF. OBJECTIVES: We believe that atrial remodelling is a pre-existent process in patients with post-surgical AF. We have analyzed the factors related to the incidence of atrial fibrillation in the period after heart surgery. METHODS: We included consecutive, hemodynamically stable patients with a sinusal rhythm who were subjected to programmed heart surgery with extracorporeal circulation. An assessment was made of the fall in atrial fibrillation after surgery using prolonged electrocardiographic monitoring. RESULTS: A total of 100 patients were included in the study and were subjected to either coronary revascularisation surgery (59) or aortic valve substitution due to severe aortic stenosis (41). Postoperative AF occurred in 29 patients who received predominantly more valve surgery than coronary surgery. The following factors were predictive of postoperative AF in the multivariate analysis: Male sex; beta-blocker therapy for chronic disease; the use of intraoperative; fibrinogen perfusion; low HDL cholesterol values; and high sensitive troponin T values, in the preoperative period. CONCLUSIONS: HDL cholesterol and high sensitive troponin T can be useful biomarkers to predict the occurrence of AF after surgery. The early identification of these patients who develop of FA allows us to take preventive measures to minimize the negative effects.

Colesterol HDL y troponina T ultrasensible como biomarcadores predictivos de fibrilación auricular postoperatoria / HDL cholesterol and high-sensitive troponin T as predictives biomarkers of atrial fibrillation after heart surgery

Introducción: La fibrilación auricular (FA), con una incidencia aproximada del 30%, es la arritmia más frecuente tras cirugía cardiaca. Se han asociado a la FA factores como la inflamación, la presencia de fibrosis cardiaca, el estrés y la apoptosis de cardiomiocitos. Objetivos: Consideramos que el remodelado auricular es un proceso preexistente en los pacientes con FA posquirúrgica. Analizamos los factores relacionados con la incidencia de FA en el postoperatorio de cirugía cardiaca. Métodos: Incluimos a pacientes consecutivos, estables hemodinámicamente y en ritmo sinusal, sometidos a cirugía cardiaca programada con circulación extracorpórea. Se valora la caída en FA posquirúrgica. Resultados: Se incluyeron un total de 100 pacientes sometidos a cirugía de revascularización coronaria (59) o sustitución valvular aórtica (41) por estenosis aórtica grave. La FA postoperatoria se produjo en 29 pacientes con predominio de la cirugía valvular respecto a la cirugía coronaria. Los factores predictivos de la aparición de FA postoperatoria en el análisis multivariable fueron el sexo masculino, la ausencia de terapia crónica con betabloqueadores, la perfusión de fibrinógeno intraoperatorio, valores bajos de colesterol HDL y valores elevados de troponina T ultrasensible en el preoperatorio. Conclusiones: El colesterol HDL y la troponina T ultrasensible pueden ser biomarcadores útiles para predecir la aparición de FA postoperatoria. La identificación precoz de estos pacientes nos permite adoptar medidas preventivas para minimizar sus efectos negativos.

Introduction: Atrial fibrillation (AF) has an incidence rate of approximately 30% and is the most frequent arrhythmia following heart surgery. Factors such as inflammation, the presence of heart fibrosis, stress and cardiomyocyte apoptosis, have all been associated with AF. Objectives: We believe that atrial remodelling is a pre-existent process in patients with post-surgical AF. We have analyzed the factors related to the incidence of atrial fibrillation in the period after heart surgery. Methods: We included consecutive, hemodynamically stable patients with a sinusal rhythm who were subjected to programmed heart surgery with extracorporeal circulation. An assessment was made of the fall in atrial fibrillation after surgery using prolonged electrocardiographic monitoring. Results: A total of 100 patients were included in the study and were subjected to either coronary revascularisation surgery (59) or aortic valve substitution due to severe aortic stenosis (41). Postoperative AF occurred in 29 patients who received predominantly more valve surgery than coronary surgery. The following factors were predictive of postoperative AF in the multivariate analysis: Male sex; beta-blocker therapy for chronic disease; the use of intraoperative; fibrinogen perfusion; low HDL cholesterol values; and high sensitive troponin T values, in the preoperative period. Conclusions: HDL cholesterol and high sensitive troponin T can be useful biomarkers to predict the occurrence of AF after surgery. The early identification of these patients who develop of FA allows us to take preventive measures to minimize the negative effects.

Evaluación del índice de riesgo del primer trimestre en casos de embarazo múltiple con presencia de un feto perdido / Evaluation of the risk index of the first-trimester combined screening test in cases of multiple pregnancy with a «vanishing twin»

Fundamento y objetivo. Justificar una evaluación correcta del test combinado de cribado prenatal del primer trimestre, en casos especiales de embarazos gemelares con pérdida de uno de los embriones, debido al aumento de estos casos, sobre todo en gestantes sometidas a técnicas de reproducción in vitro. Paciente y métodos. Se documenta un caso clínico de gestación gemelar bicorial biamniótica con pérdida del primer feto en la semana 12. Se le solicita cribado prenatal en el que la estimación del índice de riesgo del primer trimestre no se pudo valorar como tal. Discusión y conclusiones. El índice de riesgo no es calculable debido a la pérdida de uno de los fetos. Los niveles de la fracción libre de la subunidad beta de la gonadotropina coriónica humana (Beta-hCG) en suero no se ven afectados pero sí se produce un aumento significativo de los niveles de la proteína plasmática A asociada al embarazo (PAPP-A), que depende del tiempo transcurrido desde la pérdida fetal, por lo que no puede considerarse ni como un feto aislado ni como 2. Por tanto, para evaluar el riesgo se recomienda una estimación de la translucencia nucal fetal (TN) y la Beta-hCG libre, o únicamente la TN, atendiendo también a unos múltiplos de la mediana (MoM) dentro de la normalidad(AU)

Background and purpose. To justify an accurate assessment of the first-trimester combined screening test, in special cases of twin pregnancies with a vanishing twin; because the increase in such cases specially is being seen in pregnant women undergoing in vitro fertilization techniques. Patients and methods. We report a case of biamniotic bichorionic twin pregnancy with loss of the first fetus at week 12. Prenatal screening was asked in wich it couldn’t been estimated the risk index for the first trimester screening test. Discussion and conclusions. The risk index is not calculable due to the loss of one fetus. The levels of the free fraction of the beta subunit of human chorionic gonadotropin (Beta-hCG) in serum are not affected but there is a significant increase in the levels of pregnancy associated plasma protein-A (PAPP-A), which depends on the time since fetal loss; so the serum levels cannot be regarded neither as an isolated fetus or as 2. Therefore to assess the risk of the first-trimester combined screening test, it is recommended to estimate the fetal nuchal translucency thickness (NT) and Beta-hCG, or just only NT, also considering the median multiples (MoM) within the normal limits(AU)