Design and effectiveness of an AI⁃based early warning and clinical decision support system for multidrug⁃resistant organism infections
Abstract
ObjectiveTo explore the design and application effectiveness of an artificial intelligence(AI)⁃based early warning and clinical decision support system for multidrug⁃resistant organism(MDRO) infections.MethodsData of inpatients in a tertiary general hospital in Xuzhou from January 2022 to December 2024 were collected.According to the system implementation timeline,the study was divided into three phases:pre⁃implementation(2022),one year post⁃implementation(2023),and two years post⁃implementation(2024).Indicators including MDRO detection rate,immediate execution rate of early warnings,incidence of healthcare-associated infections, antimicrobial use rate,rate of pathogen detection before antimicrobial therapy,and compliance rate with core prevention and control measures were compared.ResultsAfter the AI system operation,the immediate response rate for MDRO early warning cases increased from 66.80% to 99.40%.The rate of isolation order issuance rose from 68.10% to 100.00%.The incidence of MDRO infections decreased from 0.197% to 0.073%(P<0.05).The therapeutic antimicrobial use rate,rate of pathogen detection before treatment, and compliance rate with core MDRO prevention and control measures all significantly improved(P<0.05).ConclusionsThe AI⁃based MDRO early warning and clinical decision support system enables more scientific,standardized, and efficient prevention and control of MDRO infections.It effectively reduced the incidence of MDRO healthcare⁃associated infections,and enhanced the rational use of antimicrobial agents.
Related
- High-Dose Tigecycline for Multidrug-Resistant Serratia Infections in Critically Ill Adults: A Systematic Review of Direct and Indirect Clinical Evidence.
- Detection of high-risk sequence type ST131 among multidrug-resistant Escherichia coli causing urinary tract infections in Cusco, Peru
- Risk of Donor‐Derived Infections From Organ Donors Colonized or Infected With Multidrug‐Resistant Gram‐Negative Bacteria: A Systematic Review and Meta‐Analysis
- Multiple Neurological Complications and Multidrug-Resistant Bacterial Infections During Prolonged Intensive Care for Undocumented Meningoencephalitis in Côte d'Ivoire: A Case Report
- Early best available antibiotic therapy for multidrug-resistant gram-negative bloodstream infections: a target trial emulation
BibTeX
@article{xiaoqin2026design,
title = {{Design and effectiveness of an AI⁃based early warning and clinical decision support system for multidrug⁃resistant organism infections}},
author = {WU Xiaoqin and LI Jin and XUE Jing and SHI Liran and GUO Feng and LI Aiying and WANG Shan},
journal = {Huli yanjiu},
year = {2026},
month = oct,
url = {http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.21.005},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Design and effectiveness of an AI⁃based early warning and clinical decision support system for multidrug⁃resistant organism infections
AU - WU Xiaoqin
AU - LI Jin
AU - XUE Jing
AU - SHI Liran
AU - GUO Feng
AU - LI Aiying
AU - WANG Shan
PY - 2026
DA - 2026/10/30
JO - Huli yanjiu
UR - http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.21.005
AB - ObjectiveTo explore the design and application effectiveness of an artificial intelligence(AI)⁃based early warning and clinical decision support system for multidrug⁃resistant organism(MDRO) infections.MethodsData of inpatients in a tertiary general hospital in Xuzhou from January 2022 to December 2024 were collected.According to the system implementation timeline,the study was divided into three phases:pre⁃implementation(2022),one year post⁃implementation(2023),and two years post⁃implementation(2024).Indicators including MDRO detection rate,immediate execution rate of early warnings,incidence of healthcare-associated infections, antimicrobial use rate,rate of pathogen detection before antimicrobial therapy,and compliance rate with core prevention and control measures were compared.ResultsAfter the AI system operation,the immediate response rate for MDRO early warning cases increased from 66.80% to 99.40%.The rate of isolation order issuance rose from 68.10% to 100.00%.The incidence of MDRO infections decreased from 0.197% to 0.073%(P<0.05).The therapeutic antimicrobial use rate,rate of pathogen detection before treatment, and compliance rate with core MDRO prevention and control measures all significantly improved(P<0.05).ConclusionsThe AI⁃based MDRO early warning and clinical decision support system enables more scientific,standardized, and efficient prevention and control of MDRO infections.It effectively reduced the incidence of MDRO healthcare⁃associated infections,and enhanced the rational use of antimicrobial agents.
SN - 1009-6493
ER -