Skip to content
DraconiticResearch
Search Sources API
203,952 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BY 4.0Microbiology Spectrum

Utilizing machine learning and MALDI-TOF MS platform for rapid detection of ceftriaxone-resistant nontyphoidal Salmonella

  • Jintao Xia1
  • Jun Ren2
  • Shifu Wang3
  • Mengyu Zhang4
  • Xiaochen Sun5
  • Chao Fang1
  • Shixing Liu1
  • Xiucai Zhang1
  • Yining Zhao1
  • Lijia Wang6,7
  • Shiqiang Shang1
  • Shengjie Li2
2 more authors
  • Wenjun Cao2
  • Mingming Zhou1
7 affiliations
  1. 1Department of Laboratory Medicine, Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents' Health and Diseases, Hangzhou, China
  2. 2Department of Clinical Laboratory, Eye & ENT Hospital, Fudan University, Shanghai, China
  3. 3Department of Clinical Microbiology, Children’s Hospital Affiliated to Shandong University (Jinan Children’s Hospital), Jinan, China
  4. 4Department of Clinical Laboratory, Wanbei Coal Electric Group General Hospital, Suzhou, Anhui Province, China
  5. 5Department of Anesthesiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
  6. 6Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents' Health and Diseases, Hangzhou, Zhejiang, China
  7. 7Zhejiang Key Laboratory of Neonatal Diseases, Hangzhou, China
Read full textDOICite

Abstract

Ceftriaxone (CRO) is a first-line antibiotic for pediatric nontyphoidal Salmonella (NTS) infections, but rising resistance threatens public health. Conventional antimicrobial susceptibility testing remains time-consuming, delaying treatment. Although MALDI-TOF MS enables rapid microbial identification, it lacks inherent resistance detection. This study integrates MALDI-TOF MS with machine learning to predict CRO resistance in NTS. Using 472 isolates (1,414 spectra) from three medical centers, we developed and validated a model based on the Light Gradient Boosting Machine (LGB) algorithm. With only seven features, LGB achieved AUCs of 0.94 (training), 0.88 (internal validation), 0.79 (external validation 1), and 0.80 (external validation 2). We further deployed the model as an interactive Streamlit web interface to demonstrate its potential usability and facilitate future laboratory evaluation. This approach provides a proof-of-concept framework for rapid preliminary prediction of ceftriaxone resistance in NTS using routinely generated MALDI-TOF MS spectra. However, further large-scale, prospective, multicenter validation is required before this model can be implemented as a routine clinical susceptibility testing tool.

IMPORTANCE: The increasing prevalence of ceftriaxone-resistant nontyphoidal Salmonella in pediatric patients, particularly in cases requiring antimicrobial therapy, highlights the need for faster antimicrobial susceptibility testing. In this study, we developed a machine learning model integrated with MALDI-TOF MS to predict ceftriaxone resistance in NTS and deployed it as a web-based research-use interface. This proof-of-concept approach may support the future development of rapid adjunctive tools for antimicrobial resistance prediction.

Related

  1. Secondary hemophagocytic lymphohistiocytosis complicating culture-confirmed ceftriaxone-resistant Salmonella typhi infection: A rare case report.
    Hafsa Akter, Samila Tabassum Shithil, Iftekhar Ahmed Sakib +3
    IDCasesPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  2. An Exploratory Study on the Antibiotic Potentiation Activity of Riboflavin Against Biofilm‐Forming Multidrug‐Resistant Salmonella and Shigella Clinical Isolates
    Abiola Isawumi, Gloria Kutorkor Addo, Elizabeth W. Bugase +2
    International Journal of MicrobiologyPeer-reviewedCC BY 4.0Full textGeneral medicinePMC
  3. Antimicrobial-resistant Salmonella and Escherichia coli in fresh vegetables from Ouagadougou, Burkina Faso: Prevalence, β-lactamase genes, and food safety implications
    Adama Pamba Séré, Nabèrè Ouattara, Abdoudramane Sanou +5
    PLOS OnePeer-reviewedCC BY 4.0MicrobiologyEpidemiology & public healthPLOS
  4. Retail fish markets in Bangladesh are hidden hotspots of multidrug resistant Salmonella providing critical One Health insights
    Md. Niamul Shahadat, Abu Bakkar Siddique, Md. Nazmussakib Shuvo +3
    Scientific ReportsPeer-reviewedCC BYFull textGeneral medicineDOAJ
  5. Detection of Nitazenes in the Illicit Drug Supply Utilizing Precursor Ion Scan Methods With Paper Spray Mass Spectrometry
    Allie Miskulin, Irene Shkolnikov, Jindar Sboto +4
    Drug Testing and AnalysisPeer-reviewedCC BY-NC-ND 4.0Full textPharmacology & toxicologyPMC

Cite

BibTeXRIS
BibTeX
@article{xia2026utilizing,
  title = {{Utilizing machine learning and MALDI-TOF MS platform for rapid detection of ceftriaxone-resistant nontyphoidal Salmonella}},
  author = {Jintao Xia and Jun Ren and Shifu Wang and Mengyu Zhang and Xiaochen Sun and Chao Fang and Shixing Liu and Xiucai Zhang and Yining Zhao and Lijia Wang and Shiqiang Shang and Shengjie Li and Wenjun Cao and Mingming Zhou},
  journal = {Microbiology Spectrum},
  year = {2026},
  month = sep,
  doi = {10.1128/spectrum.00984-26},
  url = {https://doi.org/10.1128/spectrum.00984-26},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Utilizing machine learning and MALDI-TOF MS platform for rapid detection of ceftriaxone-resistant nontyphoidal Salmonella
AU  - Jintao Xia
AU  - Jun Ren
AU  - Shifu Wang
AU  - Mengyu Zhang
AU  - Xiaochen Sun
AU  - Chao Fang
AU  - Shixing Liu
AU  - Xiucai Zhang
AU  - Yining Zhao
AU  - Lijia Wang
AU  - Shiqiang Shang
AU  - Shengjie Li
AU  - Wenjun Cao
AU  - Mingming Zhou
PY  - 2026
DA  - 2026/09/28
JO  - Microbiology Spectrum
DO  - 10.1128/spectrum.00984-26
UR  - https://doi.org/10.1128/spectrum.00984-26
AB  - Ceftriaxone (CRO) is a first-line antibiotic for pediatric nontyphoidal Salmonella (NTS) infections, but rising resistance threatens public health. Conventional antimicrobial susceptibility testing remains time-consuming, delaying treatment. Although MALDI-TOF MS enables rapid microbial identification, it lacks inherent resistance detection. This study integrates MALDI-TOF MS with machine learning to predict CRO resistance in NTS. Using 472 isolates (1,414 spectra) from three medical centers, we developed and validated a model based on the Light Gradient Boosting Machine (LGB) algorithm. With only seven features, LGB achieved AUCs of 0.94 (training), 0.88 (internal validation), 0.79 (external validation 1), and 0.80 (external validation 2). We further deployed the model as an interactive Streamlit web interface to demonstrate its potential usability and facilitate future laboratory evaluation. This approach provides a proof-of-concept framework for rapid preliminary prediction of ceftriaxone resistance in NTS using routinely generated MALDI-TOF MS spectra. However, further large-scale, prospective, multicenter validation is required before this model can be implemented as a routine clinical susceptibility testing tool.  IMPORTANCE: The increasing prevalence of ceftriaxone-resistant nontyphoidal Salmonella in pediatric patients, particularly in cases requiring antimicrobial therapy, highlights the need for faster antimicrobial susceptibility testing. In this study, we developed a machine learning model integrated with MALDI-TOF MS to predict ceftriaxone resistance in NTS and deployed it as a web-based research-use interface. This proof-of-concept approach may support the future development of rapid adjunctive tools for antimicrobial resistance prediction.
SN  - 2165-0497
ER  -