Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset
Abstract Background The incidence of cardiac implantable electronic device infection (CIEDI) is low and usually belongs to the typical imbalanced dataset. We sought to describe our experience on the management of the imbalanced CIEDI dataset. Methods Database from two centers of patients undergoing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-09-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12911-019-0899-4 |
| _version_ | 1818049044582236160 |
|---|---|
| author | Xiang-Fei Feng Ling-Chao Yang Li-Zhuang Tan Yi-Gang Li |
| author_facet | Xiang-Fei Feng Ling-Chao Yang Li-Zhuang Tan Yi-Gang Li |
| author_sort | Xiang-Fei Feng |
| collection | DOAJ |
| description | Abstract Background The incidence of cardiac implantable electronic device infection (CIEDI) is low and usually belongs to the typical imbalanced dataset. We sought to describe our experience on the management of the imbalanced CIEDI dataset. Methods Database from two centers of patients undergoing device implantation from 2001 to 2016 were reviewed retrospectively. Re-sampling technique was used to improve the classifier accuracy. Results CIEDI was identified in 28 out of 4959 procedures (0.56%); a high imbalance existed in the sizes of the patient profiles. In univariate analyses, replacement procedure and male were significantly associated with an increase in CIEDI: (53.6% vs. 23.4, 0.8% vs. 0.3%, P < 0.01). Multivariate logistic regression analysis showed that gender (odds ratio, OR = 3.503), age (OR = 1.032), replacement procedure (OR = 3.503), and use of antibiotics (OR = 0.250) remained as independent predictors of CIEDI (all P < 0.05) after adjustment for diabetes, post-operation fever, and device style, device company. There were 616 under-sampled cases and 123 over-sampled cases in the analyzed cohort after re-sampling. The re-sampling and bootstrap results were robust and largely like the analysis results prior re-sampling method, while use of antibiotics lost the predicting capacity for CIEDI after re-sampling technique (P > 0.05). Conclusion The application of re-sampling techniques can generate useful synthetic samples for the classification of imbalanced data and improve the accuracy of predicting efficacy of CIEDI. The peri-operative assessment should be intensified in male and aged patients as well as patients receiving replacement procedures for the risk of CIEDI. |
| first_indexed | 2024-12-10T10:31:19Z |
| format | Article |
| id | doaj.art-9c758275a8a74d078198a13a1fd8b5bc |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-10T10:31:19Z |
| publishDate | 2019-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-9c758275a8a74d078198a13a1fd8b5bc2022-12-22T01:52:33ZengBMCBMC Medical Informatics and Decision Making1472-69472019-09-011911810.1186/s12911-019-0899-4Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced datasetXiang-Fei Feng0Ling-Chao Yang1Li-Zhuang Tan2Yi-Gang Li3Department of Cardiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Cardiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversitySchool of Electronics and Information Engineering, Beijing Jiaotong UniversityDepartment of Cardiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityAbstract Background The incidence of cardiac implantable electronic device infection (CIEDI) is low and usually belongs to the typical imbalanced dataset. We sought to describe our experience on the management of the imbalanced CIEDI dataset. Methods Database from two centers of patients undergoing device implantation from 2001 to 2016 were reviewed retrospectively. Re-sampling technique was used to improve the classifier accuracy. Results CIEDI was identified in 28 out of 4959 procedures (0.56%); a high imbalance existed in the sizes of the patient profiles. In univariate analyses, replacement procedure and male were significantly associated with an increase in CIEDI: (53.6% vs. 23.4, 0.8% vs. 0.3%, P < 0.01). Multivariate logistic regression analysis showed that gender (odds ratio, OR = 3.503), age (OR = 1.032), replacement procedure (OR = 3.503), and use of antibiotics (OR = 0.250) remained as independent predictors of CIEDI (all P < 0.05) after adjustment for diabetes, post-operation fever, and device style, device company. There were 616 under-sampled cases and 123 over-sampled cases in the analyzed cohort after re-sampling. The re-sampling and bootstrap results were robust and largely like the analysis results prior re-sampling method, while use of antibiotics lost the predicting capacity for CIEDI after re-sampling technique (P > 0.05). Conclusion The application of re-sampling techniques can generate useful synthetic samples for the classification of imbalanced data and improve the accuracy of predicting efficacy of CIEDI. The peri-operative assessment should be intensified in male and aged patients as well as patients receiving replacement procedures for the risk of CIEDI.http://link.springer.com/article/10.1186/s12911-019-0899-4DeviceInfectionRisk factorsImplantationRe-sampling technique |
| spellingShingle | Xiang-Fei Feng Ling-Chao Yang Li-Zhuang Tan Yi-Gang Li Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset BMC Medical Informatics and Decision Making Device Infection Risk factors Implantation Re-sampling technique |
| title | Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset |
| title_full | Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset |
| title_fullStr | Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset |
| title_full_unstemmed | Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset |
| title_short | Risk factor analysis of device-related infections: value of re-sampling method on the real-world imbalanced dataset |
| title_sort | risk factor analysis of device related infections value of re sampling method on the real world imbalanced dataset |
| topic | Device Infection Risk factors Implantation Re-sampling technique |
| url | http://link.springer.com/article/10.1186/s12911-019-0899-4 |
| work_keys_str_mv | AT xiangfeifeng riskfactoranalysisofdevicerelatedinfectionsvalueofresamplingmethodontherealworldimbalanceddataset AT lingchaoyang riskfactoranalysisofdevicerelatedinfectionsvalueofresamplingmethodontherealworldimbalanceddataset AT lizhuangtan riskfactoranalysisofdevicerelatedinfectionsvalueofresamplingmethodontherealworldimbalanceddataset AT yigangli riskfactoranalysisofdevicerelatedinfectionsvalueofresamplingmethodontherealworldimbalanceddataset |