Jingjie Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jingjie Song has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Kai Zhou
Guangdong Provincial Key Laboratory of Infection Immunity and Inflammation, Department of Pathogen Biology and Immunology, Medical School, Shenzhen University, Shenzhen 518060, China
2 shared publications - Lianghui Peng
Department of Clinical Laboratory, Fifth Affiliated Hospital Southern Medical University Guangzhou China
2 shared publications - Shihan Zeng
Department of Clinical Laboratory, Southern Medical University, Fifth Affiliated Hospital
2 shared publications - Xiaoyan Li
The Eighth Affiliated Hospital, Southern Medical University (The First People’s Hospital of Shunde), Foshan, China
2 shared publications Yang Liu
Shenzhen Institute of Respiratory Diseases, Second Clinical Medical College (Shenzhen People's Hospital), Jinan University, The First Affiliated Hospital (Shenzhen People's Hospital), Southern University of Science and Technology, Shenzhen, China
2 shared publicationsBo-Lin Li
Shunde Hospital, Southern Medical University (The First People's Hospital of Shunde), Foshan, China
1 shared publication
Latest Publications
- Open Access
A machine learning-based risk prediction model for Hospitalized patients with deep vein thrombosis
Background: Deep vein thrombosis (DVT) is a common thrombotic condition with substantial morbidity when not identified early. Machine learning (ML)–based predictive models may improve early identification of patients at high risk for DVT, but few clinically applicable early-risk models exist. Objectives: To develop and internally validate a ML model using routinely available clinical and laboratory indicators for early risk prediction of DVT, and to identify the most influential predictors using model explainability techniques. Methods: We retrospectively analyzed clinical data from 231 patients evaluated at the Fifth Affiliated Hospital of Southern Medical University between January 2017 and June 2024. Patients were labeled as DVT occurrence ( n = 159) or non-occurrence ( n = 72). Seven candidate predictors were selected by Least Absolute Shrinkage and Selection Operator (LASSO) regression. The dataset was split into training (70%, n = 162) and test (30%, n = 69) sets. Five ML algorithms were trained: XGBoost, CatBoost, Random Forest (RF), Logistic Regression, and Support Vector Machine, with hyperparameter tuning on the training set. Model performance was assessed by 5-fold cross-validation and on the held-out test set using Area Under the Receiver Operating Characteristic Curve (AUC), accuracy, recall, and F1 score. The best model was further interpreted via feature importance and Shapley Additive Explanations (SHAP). Results: LASSO selected seven predictors: hemoglobin, platelet count, leukocyte count, fibrinogen, prothrombin time, D-dimer (DD), and glucose. The Random Forest model showed the best discrimination (test-set AUC = 0.874), with favorable accuracy, recall, and F1 compared with other classifiers (detailed metrics reported in the manuscript). In the RF model, D-dimer had the highest feature-importance contribution; SHAP analysis confirmed DD as the dominant risk driver and characterized the directions and relative effects of other features. Conclusions: We developed an internally validated ML model for early DVT risk prediction using seven routine clinical variables; Random Forest achieved the best performance and identified D-dimer as the most influential predictor. This model may support earlier identification and intervention for patients at risk of DVT, pending external validation and prospective evaluation.
Open AccessA machine learning-based risk prediction model for Hospitalized patients with deep vein thrombosis
Background: Deep vein thrombosis (DVT) is a common thrombotic condition with substantial morbidity when not identified early. Machine learning (ML)–based predictive models may improve early identification of patients at high risk for DVT, but few clinically applicable early-risk models exist. Objectives: To develop and internally validate a ML model using routinely available clinical and laboratory indicators for early risk prediction of DVT, and to identify the most influential predictors using model explainability techniques. Methods: We retrospectively analyzed clinical data from 231 patients evaluated at the Fifth Affiliated Hospital of Southern Medical University between January 2017 and June 2024. Patients were labeled as DVT occurrence ( n = 159) or non-occurrence ( n = 72). Seven candidate predictors were selected by Least Absolute Shrinkage and Selection Operator (LASSO) regression. The dataset was split into training (70%, n = 162) and test (30%, n = 69) sets. Five ML algorithms were trained: XGBoost, CatBoost, Random Forest (RF), Logistic Regression, and Support Vector Machine, with hyperparameter tuning on the training set. Model performance was assessed by 5-fold cross-validation and on the held-out test set using Area Under the Receiver Operating Characteristic Curve (AUC), accuracy, recall, and F1 score. The best model was further interpreted via feature importance and Shapley Additive Explanations (SHAP). Results: LASSO selected seven predictors: hemoglobin, platelet count, leukocyte count, fibrinogen, prothrombin time, D-dimer (DD), and glucose. The Random Forest model showed the best discrimination (test-set AUC = 0.874), with favorable accuracy, recall, and F1 compared with other classifiers (detailed metrics reported in the manuscript). In the RF model, D-dimer had the highest feature-importance contribution; SHAP analysis confirmed DD as the dominant risk driver and characterized the directions and relative effects of other features. Conclusions: We developed an internally validated ML model for early DVT risk prediction using seven routine clinical variables; Random Forest achieved the best performance and identified D-dimer as the most influential predictor. This model may support earlier identification and intervention for patients at risk of DVT, pending external validation and prospective evaluation.
- Open Access
- 12 July 2026
- Published by Wiley in Microbial Biotechnology
- Vol. 19 (7) , e70413
Identification and Genomic Analysis of the First Salmonella typhimurium Monophasic Variant 1,4,[5],12:i:‐ Isolate Harbouring a Chromosomally Integrated bla NDM‐5
We report the first clinical strain of the monophasic variant of Salmonella typhimurium (serotype 1,4,[5],12:i:‐) belonging to ST34 with chromosomally integrated bla NDM‐5 . Although chromosomal integration of bla NDM‐5 has been described in other Enterobacterales and Salmonella serovars, this is the first such report in this high‐risk clone. This study characterises the genomic and epidemiological background of this strain. The isolate (1111‐90), obtained from a paediatric patient, was subjected to antimicrobial susceptibility testing, whole‐genome sequencing and comparative genomic analysis against 674 complete bla NDM‐5 ‐positive plasmids retrieved from the PlasmidScope database. The isolate exhibited a multidrug‐resistant phenotype, including carbapenem resistance, while retaining susceptibility to tigecycline and aztreonam. It harboured 13 resistance genes distributed across the chromosome and two plasmids. The ~11 kb chromosomally integrated bla NDM‐5 segment is flanked by directly oriented IS 26 elements, forming an IS 26 ‐bounded composite transposon with no canonical target‐site duplication at its boundaries. Phylogenetic analysis suggested that this chromosomal segment likely originated from IncX3 or IncI1 plasmid lineages prevalent in China. Comparative genetic analysis highlighted the significant role of mobile genetic elements (IS 26 , IS 5 and IS 3000 ) in the spread of bla NDM‐5 within S. typhimurium . The chromosomal integration of an IS 26 ‐bounded bla NDM‐5 module in S . 1,4,[5],12:i:‐ ST34 suggests the emergence of a stable, high‐risk carbapenem‐resistant clone, underscoring the need for genomic surveillance to track IS 26 ‐mediated chromosomal integration events.
- 12 July 2026
- Published by Wiley in Microbial Biotechnology
- Vol. 19 (7) , e70413
Open AccessIdentification and Genomic Analysis of the First Salmonella typhimurium Monophasic Variant 1,4,[5],12:i:‐ Isolate Harbouring a Chromosomally Integrated bla NDM‐5
We report the first clinical strain of the monophasic variant of Salmonella typhimurium (serotype 1,4,[5],12:i:‐) belonging to ST34 with chromosomally integrated bla NDM‐5 . Although chromosomal integration of bla NDM‐5 has been described in other Enterobacterales and Salmonella serovars, this is the first such report in this high‐risk clone. This study characterises the genomic and epidemiological background of this strain. The isolate (1111‐90), obtained from a paediatric patient, was subjected to antimicrobial susceptibility testing, whole‐genome sequencing and comparative genomic analysis against 674 complete bla NDM‐5 ‐positive plasmids retrieved from the PlasmidScope database. The isolate exhibited a multidrug‐resistant phenotype, including carbapenem resistance, while retaining susceptibility to tigecycline and aztreonam. It harboured 13 resistance genes distributed across the chromosome and two plasmids. The ~11 kb chromosomally integrated bla NDM‐5 segment is flanked by directly oriented IS 26 elements, forming an IS 26 ‐bounded composite transposon with no canonical target‐site duplication at its boundaries. Phylogenetic analysis suggested that this chromosomal segment likely originated from IncX3 or IncI1 plasmid lineages prevalent in China. Comparative genetic analysis highlighted the significant role of mobile genetic elements (IS 26 , IS 5 and IS 3000 ) in the spread of bla NDM‐5 within S. typhimurium . The chromosomal integration of an IS 26 ‐bounded bla NDM‐5 module in S . 1,4,[5],12:i:‐ ST34 suggests the emergence of a stable, high‐risk carbapenem‐resistant clone, underscoring the need for genomic surveillance to track IS 26 ‐mediated chromosomal integration events.
- Open Access
- 8 May 2025
- Published by Elsevier in International Journal of Antimicrobial Agents
- Vol. 66 (3) , 107533
Genetic framework and evolutionary dynamics of mcr-positive Klebsiella pneumoniae from 2000 to 2023
- 8 May 2025
- Published by Elsevier in International Journal of Antimicrobial Agents
- Vol. 66 (3) , 107533
Open AccessGenetic framework and evolutionary dynamics of mcr-positive Klebsiella pneumoniae from 2000 to 2023
- Open Access
- 20 December 2024
- Published by Elsevier in International Journal of Antimicrobial Agents
- Vol. 65 (3) , 107412
Molecular investigation of an epidemic dissemination of vancomycin-resistant Enterococcus faecium sequence type 80 in Guangdong province, China
- 20 December 2024
- Published by Elsevier in International Journal of Antimicrobial Agents
- Vol. 65 (3) , 107412
Open AccessMolecular investigation of an epidemic dissemination of vancomycin-resistant Enterococcus faecium sequence type 80 in Guangdong province, China
- 1 January 2021
- Published by Elsevier in Environmental Pollution
- Vol. 268 (Pt B) , 115706
Identification of mcr-10 carried by self-transmissible plasmids and chromosome in Enterobacter roggenkampii strains isolated from hospital sewage water
- 1 January 2021
- Published by Elsevier in Environmental Pollution
- Vol. 268 (Pt B) , 115706
Identification of mcr-10 carried by self-transmissible plasmids and chromosome in Enterobacter roggenkampii strains isolated from hospital sewage water
- Open Access
Silent dissemination of plasmid-borne tigecycline resistance gene tet (X6) in livestock-associated Acinetobacter towneri
A tigecycline-resistance gene, tet (X6), was detected on a 159-kb novel plasmid carried by a tigecycline-susceptible livestock-associated Acinetobacter towneri isolate. The genetic context of tet (X6) (ΔIS Vsa3 - tet (X6)- abh - guaA -IS Vsa3 ) is highly similar with that of the other plasmid-borne tet (X) variants. The 23-Ala residue of the first FAD binding site conferred higher activity to Tet(X6) than the 23-Gly reside conserved in the other plasmid-borne tet (X)s. To our knowledge, this is the first report of tet (X6) carried by the plasmid.
Open AccessSilent dissemination of plasmid-borne tigecycline resistance gene tet (X6) in livestock-associated Acinetobacter towneri
A tigecycline-resistance gene, tet (X6), was detected on a 159-kb novel plasmid carried by a tigecycline-susceptible livestock-associated Acinetobacter towneri isolate. The genetic context of tet (X6) (ΔIS Vsa3 - tet (X6)- abh - guaA -IS Vsa3 ) is highly similar with that of the other plasmid-borne tet (X) variants. The 23-Ala residue of the first FAD binding site conferred higher activity to Tet(X6) than the 23-Gly reside conserved in the other plasmid-borne tet (X)s. To our knowledge, this is the first report of tet (X6) carried by the plasmid.