<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper, a prototype network model is used for event extraction of antibiotic resistance and new anti-infection information, and also limited or small amount of labeled data is used to obtain a prediction model with excellent generalization performance. The Bi-LSTM framework for antibiotic resistance element detection is a mainstream sequence annotation framework that combines bidirectional long- and short-term memory networks, and its main idea is to obtain contextual information through bidirectional long- and short-term memory networks, and to fuse antibiotic as well as bacterial entity information, and trigger word information for the assignment of element roles. In the keyword co-occurrence analysis, combination therapy and phage had the highest frequency with a centrality of 0.57 and 0.59, respectively, indicating that phage-antibiotic therapy effectively treated patients with drug-resistant bacterial infections. There was a high correlation (r=0.57) between the number of days of ICU stay and the number of days of phage-antibiotic combination therapy, which was further analyzed to show that the number of days of fever, the number of days of indwelling urinary catheter, and the number of days of mechanical ventilation, phage-antibiotic combination days are more important influencing factors.</p>
</abstract>

In this paper, a prototype network model is used for event extraction of antibiotic resistance and new anti-infection information, and also limited or small amount of labeled data is used to obtain a prediction model with excellent generalization performance. The Bi-LSTM framework for antibiotic resistance element detection is a mainstream sequence annotation framework that combines bidirectional long- and short-term memory networks, and its main idea is to obtain contextual information through bidirectional long- and short-term memory networks, and to fuse antibiotic as well as bacterial entity information, and trigger word information for the assignment of element roles. In the keyword co-occurrence analysis, combination therapy and phage had the highest frequency with a centrality of 0.57 and 0.59, respectively, indicating that phage-antibiotic therapy effectively treated patients with drug-resistant bacterial infections. There was a high correlation (r=0.57) between the number of days of ICU stay and the number of days of phage-antibiotic combination therapy, which was further analyzed to show that the number of days of fever, the number of days of indwelling urinary catheter, and the number of days of mechanical ventilation, phage-antibiotic combination days are more important influencing factors.

Detection of antibiotic resistance mechanism and research on new anti-infection measures based on big data analysis

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In this paper, a prototype network model is used for event extraction of antibiotic resistance and new anti-infection information, and also limited or small...

Detection of antibiotic resistance mechanism and research on new anti-infection measures based on big data analysis

Pubblicato online: 03 mag 2024

Pagine: -

Ricevuto: 19 apr 2024

Accettato: 27 apr 2024

DOI: https://doi.org/10.2478/amns-2024-0960

Parole chiave
Prototype network, Event extraction, Predictive modeling, Phage-antibiotic, Bi-LSTM

© 2024 Yan Ji et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Detection of antibiotic resistance mechanism and research on new anti-infection measures based on big data analysis

Pubblicato online: 03 mag 2024

Pagine: -

Ricevuto: 19 apr 2024

Accettato: 27 apr 2024

DOI: https://doi.org/10.2478/amns-2024-0960

Parole chiavePrototype network, Event extraction, Predictive modeling, Phage-antibiotic, Bi-LSTM

© 2024 Yan Ji et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Prototype network, Event extraction, Predictive modeling, Phage-antibiotic, Bi-LSTM