The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae
ObjectiveTo develop a machine learning-based prediction model to assist clinicians in accurately determining whether the detection of Klebsiella pneumoniae (KP) in sputum samples indicates an infection, facilitating timely diagnosis and treatment.Research methodsA retrospective analysis was conducte...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2024.1508030/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590495102009344 |
|---|---|
| author | Xiaoyu Zhang Xifan Zhang Deng Zhang Jing Xu Jingping Zhang Xin Zhang |
| author_facet | Xiaoyu Zhang Xifan Zhang Deng Zhang Jing Xu Jingping Zhang Xin Zhang |
| author_sort | Xiaoyu Zhang |
| collection | DOAJ |
| description | ObjectiveTo develop a machine learning-based prediction model to assist clinicians in accurately determining whether the detection of Klebsiella pneumoniae (KP) in sputum samples indicates an infection, facilitating timely diagnosis and treatment.Research methodsA retrospective analysis was conducted on 8,318 patients with KP cultures admitted to a tertiary hospital in Northeast China from January 2019 to December 2023. After excluding duplicates, other specimen types, cases with substandard specimen quality, and mixed infections, 286 cases with sputum cultures yielding only KP were included, comprising 67 cases in the colonization group and 219 cases in the infection group. Antimicrobial susceptibility testing was performed on the included strains, and through univariate logistic regression analysis, 15 key influencing factors were identified, including: age > 62 years, ESBL, CRKP, number of positive sputum cultures for KP, history of tracheostomy, use of mechanical ventilation for >96 h, indwelling gastric tube, history of craniotomy, recent local glucocorticoid application, altered consciousness, bedridden state, diagnosed with respiratory infectious disease upon admission, electrolyte disorder, hypoalbuminemia, and admission to ICU (all p < 0.05). These factors were used to construct the model, which was evaluated using accuracy, precision, recall, F1 score, AUC value, and Brier score.ResultsAntimicrobial susceptibility testing indicated that the resistance rates for penicillins, cephalosporins, carbapenems, and quinolones were significantly higher in the infection group compared to the colonization group (all p < 0.05). Six predictive models were constructed using 15 key influencing factors, including Classification and Regression Trees (CART), C5.0, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), Random Forest (RF), and Nomogram. The Random Forest model performed best among all indicators (accuracy 0.93, precision 0.98, Brier Score 0.06, recall 0.72, F1 Score 0.83, AUC 0.99). The importance of each factor was demonstrated using mean decrease in Gini. “Admitted with a diagnosis of respiratory infectious disease” (8.39) was identified as the most important factor in the model, followed by “Hypoalbuminemia” (7.83), then “ESBL” (7.06), “Electrolyte Imbalance” (5.81), “Age > 62 years” (5.24), “The number of Positive Sputum Cultures for KP > 2” (4.77), and being bedridden (4.24). Additionally, invasive procedures (such as history of tracheostomy, use of ventilators for >96 h, and craniotomy) were also significant predictive factors. The Nomogram indicated that CRKP, presence of a nasogastric tube, admission to the ICU, and history of tracheostomy were important factors in determining KP colonization.ConclusionThe Random Forest model effectively distinguishes between infection and colonization status of KP, while the Nomogram visually presents the predictive value of various factors, providing clinicians with a reference for formulating treatment plans. In the future, the accuracy of infection diagnosis can be further enhanced through artificial intelligence technology to optimize treatment strategies, thereby improving patient prognosis and reducing healthcare burdens. |
| format | Article |
| id | doaj-art-c72850febbc44f568a5762035bf07e43 |
| institution | Kabale University |
| issn | 1664-302X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj-art-c72850febbc44f568a5762035bf07e432025-01-23T15:42:06ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2025-01-011510.3389/fmicb.2024.15080301508030The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniaeXiaoyu Zhang0Xifan Zhang1Deng Zhang2Jing Xu3Jingping Zhang4Xin Zhang5First Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, ChinaFirst Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Xiamen University, Xiamen, ChinaFirst Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, ChinaFirst Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, ChinaFirst Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, ChinaObjectiveTo develop a machine learning-based prediction model to assist clinicians in accurately determining whether the detection of Klebsiella pneumoniae (KP) in sputum samples indicates an infection, facilitating timely diagnosis and treatment.Research methodsA retrospective analysis was conducted on 8,318 patients with KP cultures admitted to a tertiary hospital in Northeast China from January 2019 to December 2023. After excluding duplicates, other specimen types, cases with substandard specimen quality, and mixed infections, 286 cases with sputum cultures yielding only KP were included, comprising 67 cases in the colonization group and 219 cases in the infection group. Antimicrobial susceptibility testing was performed on the included strains, and through univariate logistic regression analysis, 15 key influencing factors were identified, including: age > 62 years, ESBL, CRKP, number of positive sputum cultures for KP, history of tracheostomy, use of mechanical ventilation for >96 h, indwelling gastric tube, history of craniotomy, recent local glucocorticoid application, altered consciousness, bedridden state, diagnosed with respiratory infectious disease upon admission, electrolyte disorder, hypoalbuminemia, and admission to ICU (all p < 0.05). These factors were used to construct the model, which was evaluated using accuracy, precision, recall, F1 score, AUC value, and Brier score.ResultsAntimicrobial susceptibility testing indicated that the resistance rates for penicillins, cephalosporins, carbapenems, and quinolones were significantly higher in the infection group compared to the colonization group (all p < 0.05). Six predictive models were constructed using 15 key influencing factors, including Classification and Regression Trees (CART), C5.0, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), Random Forest (RF), and Nomogram. The Random Forest model performed best among all indicators (accuracy 0.93, precision 0.98, Brier Score 0.06, recall 0.72, F1 Score 0.83, AUC 0.99). The importance of each factor was demonstrated using mean decrease in Gini. “Admitted with a diagnosis of respiratory infectious disease” (8.39) was identified as the most important factor in the model, followed by “Hypoalbuminemia” (7.83), then “ESBL” (7.06), “Electrolyte Imbalance” (5.81), “Age > 62 years” (5.24), “The number of Positive Sputum Cultures for KP > 2” (4.77), and being bedridden (4.24). Additionally, invasive procedures (such as history of tracheostomy, use of ventilators for >96 h, and craniotomy) were also significant predictive factors. The Nomogram indicated that CRKP, presence of a nasogastric tube, admission to the ICU, and history of tracheostomy were important factors in determining KP colonization.ConclusionThe Random Forest model effectively distinguishes between infection and colonization status of KP, while the Nomogram visually presents the predictive value of various factors, providing clinicians with a reference for formulating treatment plans. In the future, the accuracy of infection diagnosis can be further enhanced through artificial intelligence technology to optimize treatment strategies, thereby improving patient prognosis and reducing healthcare burdens.https://www.frontiersin.org/articles/10.3389/fmicb.2024.1508030/fullKlebsiella pneumoniaecolonizationinfectionsputum culturerisk factorsmachine learning |
| spellingShingle | Xiaoyu Zhang Xifan Zhang Deng Zhang Jing Xu Jingping Zhang Xin Zhang The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae Frontiers in Microbiology Klebsiella pneumoniae colonization infection sputum culture risk factors machine learning |
| title | The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae |
| title_full | The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae |
| title_fullStr | The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae |
| title_full_unstemmed | The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae |
| title_short | The clinical prediction model to distinguish between colonization and infection by Klebsiella pneumoniae |
| title_sort | clinical prediction model to distinguish between colonization and infection by klebsiella pneumoniae |
| topic | Klebsiella pneumoniae colonization infection sputum culture risk factors machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2024.1508030/full |
| work_keys_str_mv | AT xiaoyuzhang theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT xifanzhang theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT dengzhang theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT jingxu theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT jingpingzhang theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT xinzhang theclinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT xiaoyuzhang clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT xifanzhang clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT dengzhang clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT jingxu clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT jingpingzhang clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae AT xinzhang clinicalpredictionmodeltodistinguishbetweencolonizationandinfectionbyklebsiellapneumoniae |