Academic Journal
A machine learning model for the early prediction of Gram-negative bloodstream infection in ICU patients.
| Τίτλος: | A machine learning model for the early prediction of Gram-negative bloodstream infection in ICU patients. |
|---|---|
| Συγγραφείς: | Zhou YL; Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui Province, China., Da HT; Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui Province, China., Wang TT; Department of Reproductive Medicine, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui Province, China., Wang ZX; Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui Province, China., Cheng ZL; Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui Province, China. ahczl@139.com. |
| Πηγή: | BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2026 Jan 31; Vol. 26 (1). Date of Electronic Publication: 2026 Jan 31. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2001- |
| Ιατρικοί όροι (MeSH): | Gram-Negative Bacterial Infections*/diagnosis , Bacteremia*/diagnosis , Intensive Care Units* , Machine Learning*, Humans ; Predictive Learning Models ; Retrospective Studies ; Female ; Middle Aged ; Aged ; Classification Algorithms ; Boosting Machine Learning Algorithms ; Prediction Algorithms |
| Περίληψη: | BACKGROUND: Gram-negative bloodstream infection (GN-BSI) can induce fatal septic shock. Moreover, the increasingly severe problem of antimicrobial resistance has led to high clinical mortality, particularly among intensive care unit (ICU) patients. The early identification of pathogens and timely antibiotic therapy are critical for patient outcomes. However, conventional diagnostic methods like blood culture are time-consuming and can delay treatment. Furthermore, the implementation of molecular detection techniques in routine laboratories is often hindered by high costs and technical complexity. Machine learning (ML) offers a promising alternative for the early prediction of GN-BSI. This study aims to develop an early prediction model for GN-BSI by integrating clinical and laboratory parameters from ICU patients using machine learning algorithms, thereby assisting in the early diagnosis and treatment of GN-BSI. METHODS: This retrospective study utilized data from ICU patients admitted to the West District of the First Affiliated Hospital of Anhui Medical University from January and July 2025. Following data preprocessing and multiple imputation of missing values, the dataset was randomly divided into training and validation sets in a 7:3 ratio. Feature selection was performed using Lasso regression and multivariate logistic regression. Seven ML models were developed and evaluated using metrics including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1 score, positive predictive value (PPV), and negative predictive value (NPV). Model interpretability was further assessed using Shapley Additive Explanations (SHAP) analysis. RESULTS: This study ultimately included 405 ICU patients. Following further feature selection, four variables were identified, including deep vein catheterization, continuous renal replacement therapy (CRRT), procalcitonin, and C-reactive protein (CRP). Early prediction models for GN-BSI in ICU patients were constructed using seven machine learning algorithms. Among these models, the XGBoost model demonstrated the best performance, with an AUC value of 0.898, accuracy of 88.43%, F1-score of 0.783, PPV of 85.00%, and NPV of 89.10%. SHAP bar and beeswarm plots illustrated the contribution of the four variables to the outcome. The SHAP dependency plot and force analysis provided model interpretability at the factor level and individual level, respectively. CONCLUSIONS: We developed, evaluated, and interpreted a machine learning model for predicting GN-BSI in ICU patients, which may facilitate timely intervention and treatment. The XGBoost model shows potential for clinical application following internal validation and further refinement. |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The study protocol received approval from the Clinical Medical Research Ethics Committee of the First Affiliated Hospital of Anhui Medical University (PJ2025-11-09) and was conducted in accordance with the principles of the Declaration of Helsinki. Due to the retrospective nature of the study, the requirement for written informed consent was waived. All patient data were de-identified prior to analysis to ensure confidentiality. Consent for the publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | PLoS One. 2022 Sep 22;17(9):e0273369. (PMID: 36137077) Nat Commun. 2021 Mar 31;12(1):2108. (PMID: 33790263) Antimicrob Resist Infect Control. 2022 Nov 9;11(1):137. (PMID: 36352414) Can J Infect Dis Med Microbiol. 2020 Oct 31;2020:8362109. (PMID: 33178372) JOR Spine. 2025 Jul 28;8(3):e70090. (PMID: 40727551) J Mater Chem B. 2017 Mar 21;5(11):2045-2067. (PMID: 32263678) Biomedicines. 2025 Jan 08;13(1):. (PMID: 39857720) IEEE Trans Neural Netw Learn Syst. 2017 Jun;28(6):1386-1396. (PMID: 28113826) Clin Microbiol Infect. 2020 Feb;26(2):151-157. (PMID: 31712069) IEEE Trans Comput Biol Bioinform. 2025 Nov-Dec;22(6):3463-3475. (PMID: 41191467) Infect Control Hosp Epidemiol. 2023 Feb;44(2):200-205. (PMID: 35938213) BMC Infect Dis. 2025 Sep 29;25(1):1196. (PMID: 41023926) Biomedicines. 2025 Feb 20;13(3):. (PMID: 40149513) BMC Med Inform Decis Mak. 2025 May 14;25(1):186. (PMID: 40369550) Crit Care. 2025 Jan 15;29(1):24. (PMID: 39815346) Antibiotics (Basel). 2020 Dec 18;9(12):. (PMID: 33352973) IEEE/ACM Trans Comput Biol Bioinform. 2023 Mar-Apr;20(2):1257-1268. (PMID: 35849666) Front Surg. 2022 Mar 07;9:857218. (PMID: 35345421) Nat Med. 2018 Sep;24(9):1304-1305. (PMID: 30177823) Infect Drug Resist. 2023 May 01;16:2589-2600. (PMID: 37152405) Front Microbiol. 2024 Jun 05;15:1405390. (PMID: 38903794) Chin Med J (Engl). 2023 Jun 20;136(12):1503-1505. (PMID: 37192008) Ann Clin Microbiol Antimicrob. 2023 Nov 20;22(1):103. (PMID: 37986183) Intensive Care Med. 2020 Feb;46(2):266-284. (PMID: 32047941) Sci Rep. 2025 Jul 18;15(1):26069. (PMID: 40681658) Radiother Oncol. 2018 Mar;126(3):437-442. (PMID: 29395287) Clin Microbiol Infect. 2023 Sep;29(9):1150-1158. (PMID: 36894053) Sci Rep. 2025 Jun 3;15(1):19423. (PMID: 40461566) BMC Infect Dis. 2023 Oct 10;23(1):675. (PMID: 37817106) Pharmaceuticals (Basel). 2022 Nov 30;15(12):. (PMID: 36558949) |
| Grant Information: | CXPJJH21002-2021SS the First Affiliated Hospital of Anhui Medical University Horizontal Research Project |
| Contributed Indexing: | Keywords: C-reactive protein; Clinical decision support; Gram-negative bloodstream infection; Intensive care unit; Machine learning; Procalcitonin; Risk prediction |
| Entry Date(s): | Date Created: 20260131 Date Completed: 20260627 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC12937544 |
| DOI: | 10.1186/s12911-026-03361-z |
| PMID: | 41620595 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1472-6947 |
|---|---|
| DOI: | 10.1186/s12911-026-03361-z |