Background and Objective: Code assignment is of paramount importance in many levels in modern hospitals, from ensuring accurate billing process to creating a valid record of patient care history. However, the coding process is tedious and subjective, and it requires medical coders with extensive training. This study aims to evaluate the performance of deep-learning-based systems to automatically map clinical notes to ICD-9 medical codes. Methods: The evaluations of this research are focused on end-to-end learning methods without manually defined rules. Traditional machine learning algorithms, as well as state-of-the-art deep learning methods such as Recurrent Neural Networks and Convolution Neural Networks, were applied to the Medical Information Mart for Intensive Care (MIMIC-III) dataset. An extensive number of experiments was applied to different settings of the tested algorithm. Results: Findings showed that the deep learning-based methods outperformed other conventional machine learning methods. From our assessment, the best models could predict the top 10 ICD-9 codes with 0.6957 F 1 and 0.8967 accuracy and could estimate the top 10 ICD-9 categories with 0.7233 F 1 and 0.8588 accuracy. Our implementation also outperformed existing work under certain evaluation metrics. Conclusion: A set of standard metrics was utilized in assessing the performance of ICD-9 code assignment on MIMIC-III dataset. All the developed evaluation tools and resources are available online, which can be used as a baseline for further research.
The objective of the study was to determine the enteric methane emissions from lactating and dry cows fed on rotational grazing on ryegrass/clover with supplementation of oat and vetch forage in the Andes of Peru. Sulfur hexafluoride (SF6) tracer gas methodology was used to determine enteric methane emission; the external marker Titanium dioxide (TiO2) to determine the production of feces and the protein in feces was used to estimate the digestibility of the feed. The enteric methane emissions of 5 lactating cows (LC) and 6 dry cows (DC) Brown Swiss breed were 358.5 and 337.4 g CH4/cow/day for LC and DC, respectively (P> 0.05). The conversion factor from gross energy to methane (Ym;%) was 9.7 for LC and 9.6 for DC. The enteric methane yield per kilogram of organic matter consumption was 32.5 g CH4/lactating cow /day and 32.2 g CH4/dry cow/day (p> 0.05) and the emission per kilogram of metabolic live weight for lactating cows was 3.1 g CH4/kg PV0.75 and for dry cows 2.9 g CH4/kg PV0.75 (P> 0.05). It was concluded that enteric methane emissions are similar for lactating cows and dry cows measured with the SF6 tracer gas technique.
Esta investigación se centra en el análisis de nuevas aplicaciones de equipos centrífugos en minería, basándose en las múltiples fallas geotécnicas de componentes mineros que se han visto en los últimos años, las cuales están provocando contaminación del medio ambiente y descarga de efluentes mineros no adecuados para su disposición en los ríos. Por estas razones, la sociedad y las comunidades exigen mayor regulación y control de la industria minera. Sin embargo, esta investigación propone caracterizar dichas tecnologías y escoger la más eficiente y de menos costo para su puesta en marcha. Así mismo, las operaciones mineras se han enfocado en incrementar su producción, pero han descuidado el adecuado control de construcción y operación de componentes mineros, como el ambiental, el social, entre otros. El artículo evalúa los separadores no solo porque remueven sólidos, sino porque también concentran los sólidos separados y los transfieren (con poca o ninguna pérdida de líquido) hasta el dispositivo que se haya elegido para el manejo de los sólidos separados, reduciendo la pérdida de líquido y reduciendo el manejo de los sólidos deshechos y sus costos.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.