News

Clinical management and surveillance of the Enterobacter cloacae complex (ECC) face significant challenges due to inaccurate species identification and prolonged turnaround time for culture-based antimicrobial susceptibility testing (AST). To date, no studies have leveraged whole-genome sequencing (WGS) and metagenomic next-generation sequencing (mNGS) to develop a rapid AST prediction model for ECC. Here, a total of 1,054 ECC strain genomes with AST data were collected from a public database and a local hospital. The results of species identification between the average nucleotide identity (ANI)-based method on culture were compared, and machine learning was employed to identify resistance features for imipenem (IPM), meropenem (MEM), ciprofloxacin (CIP), levofloxacin (LEV), and trimethoprim-sulfamethoxazole (SXT). By referring to ANI-based species classification, culture-based methods showed a 74% misidentification rate for 1,054 ECC isolates. The antimicrobial resistance prediction model demonstrated good performance, with the area under the curve values of 91.25% (IPM), 89.69%, 88.17% (CIP), 91.01% (LEV), and 90.93% (SXT) respectively. Moreover, a combined WGS and mNGS approach was utilized and validated using 104 pediatric sputum specimens. Compared to culture-based AST, the overall accuracy of models exceeded 95%, especially achieving 100% for IPM and 98.80% for MEM, and the detection turnaround time was shortened by 69.64 h. Furthermore, it would enable early escalated therapy in 20.83% of cases, significantly improving patient management. This established WGS and mNGS-based AST prediction model addresses the limitations of traditional methods, offering a rapid, accurate, and clinically applicable tool for managing multidrug-resistant ECC infections.