Articolul precedent |
Articolul urmator |
341 4 |
Ultima descărcare din IBN: 2023-09-11 15:40 |
SM ISO690:2012 IAPĂSCURTĂ, Victor, BELÎI, Adrian. Sepsis: current challenges and new solutions based on modern technologies. A clinical management approach. In: Cercetarea în biomedicină și sănătate: calitate, excelență și performanță, Ed. 1, 20-22 octombrie 2021, Chişinău. Chișinău, Republica Moldova: 2021, p. 302. ISBN 978-9975-82-223-7 (PDF).. |
EXPORT metadate: Google Scholar Crossref CERIF DataCite Dublin Core |
Cercetarea în biomedicină și sănătate: calitate, excelență și performanță 2021 | ||||||
Conferința "Cercetarea în biomedicină și sănătate: calitate, excelență și performanță" 1, Chişinău, Moldova, 20-22 octombrie 2021 | ||||||
|
||||||
Pag. 302-302 | ||||||
|
||||||
Descarcă PDF | ||||||
Rezumat | ||||||
Background: Despite high associated mortality and high treatment costs, sepsis remains difficult to diagnose, particularly viral sepsis in COVID-19 infection with bacterial coinfection. A recent supplement to sepsis management are systems based on machine learning (ML). Objective of the study. Proof of concept and presentation of a ML-based clinical application for the early prediction of sepsis. Material and Methods. The data comes from the publicly accessible database Early Prediction of Sepsis from Clinical Data – the PhysioNet Computing in Cardiology Challenge 2019 and include 40366 intensive care clinical cases, of which 7.27% are patients with sepsis, and 92.73% – with other diagnoses. Exploratory data analysis and data processing are performed in RStudio, and ML - on H2O platform (www.h2o.ai). Results.Based on the processing of the large data set, an intelligent system is built, which allows the prediction of sepsis 4 hours before the onset and which can be delivered as an application for clinical use. The performance metrics are: accuracy – 0.91, specificity – 0.93 and sensitivity – 0.84. Conclusion. The ML-based clinical applications still currently have a little explored clinical potential, which once exploited could essentially change the management of critically ill patients. Benefits of such applications would be: early differential diagnosis, cost reduction, higher quality care, etc |
||||||
Cuvinte-cheie sepsis, early diagnosis, machine learning based systems, clinical app, sepsis, diagnostic precoce, sisteme de învățare automată, aplicație |
||||||
|