Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study
Abstract Background Population based surveillance of surgical site infections (SSIs) requires precise case-finding strategies. We sought to develop and validate machine learning models to automate the process of complex (deep incisional/organ space) SSIs case detection. Methods This retrospective co...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | Antimicrobial Resistance and Infection Control |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13756-023-01294-0 |
| _version_ | 1827708254841470976 |
|---|---|
| author | Guosong Wu Cheligeer Cheligeer Danielle A. Southern Elliot A. Martin Yuan Xu Jenine Leal Jennifer Ellison Kathryn Bush Tyler Williamson Hude Quan Cathy A. Eastwood |
| author_facet | Guosong Wu Cheligeer Cheligeer Danielle A. Southern Elliot A. Martin Yuan Xu Jenine Leal Jennifer Ellison Kathryn Bush Tyler Williamson Hude Quan Cathy A. Eastwood |
| author_sort | Guosong Wu |
| collection | DOAJ |
| description | Abstract Background Population based surveillance of surgical site infections (SSIs) requires precise case-finding strategies. We sought to develop and validate machine learning models to automate the process of complex (deep incisional/organ space) SSIs case detection. Methods This retrospective cohort study included adult patients (age ≥ 18 years) admitted to Calgary, Canada acute care hospitals who underwent primary total elective hip (THA) or knee (TKA) arthroplasty between Jan 1st, 2013 and Aug 31st, 2020. True SSI conditions were judged by the Alberta Health Services Infection Prevention and Control (IPC) program staff. Using the IPC cases as labels, we developed and validated nine XGBoost models to identify deep incisional SSIs, organ space SSIs and complex SSIs using administrative data, electronic medical records (EMR) free text data, and both. The performance of machine learning models was assessed by sensitivity, specificity, positive predictive value, negative predictive value, F1 score, the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision–recall curve (PR AUC). In addition, a bootstrap 95% confidence interval (95% CI) was calculated. Results There were 22,059 unique patients with 27,360 hospital admissions resulting in 88,351 days of hospital stay. This included 16,561 (60.5%) TKA and 10,799 (39.5%) THA procedures. There were 235 ascertained SSIs. Of them, 77 (32.8%) were superficial incisional SSIs, 57 (24.3%) were deep incisional SSIs, and 101 (42.9%) were organ space SSIs. The incidence rates were 0.37 for superficial incisional SSIs, 0.21 for deep incisional SSIs, 0.37 for organ space and 0.58 for complex SSIs per 100 surgical procedures, respectively. The optimal XGBoost models using administrative data and text data combined achieved a ROC AUC of 0.906 (95% CI 0.835–0.978), PR AUC of 0.637 (95% CI 0.528–0.746), and F1 score of 0.79 (0.67–0.90). Conclusions Our findings suggest machine learning models derived from administrative data and EMR text data achieved high performance and can be used to automate the detection of complex SSIs. |
| first_indexed | 2024-03-10T17:01:07Z |
| format | Article |
| id | doaj.art-a0c2fe694d044cdcb90af940fcda1fbf |
| institution | Directory Open Access Journal |
| issn | 2047-2994 |
| language | English |
| last_indexed | 2024-03-10T17:01:07Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | Antimicrobial Resistance and Infection Control |
| spelling | doaj.art-a0c2fe694d044cdcb90af940fcda1fbf2023-11-20T10:57:50ZengBMCAntimicrobial Resistance and Infection Control2047-29942023-09-0112111010.1186/s13756-023-01294-0Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort studyGuosong Wu0Cheligeer Cheligeer1Danielle A. Southern2Elliot A. Martin3Yuan Xu4Jenine Leal5Jennifer Ellison6Kathryn Bush7Tyler Williamson8Hude Quan9Cathy A. Eastwood10Department of Community Health Sciences, Cumming School of Medicine, University of CalgaryThe Centre for Health Informatics, Cumming School of Medicine, University of CalgaryDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryThe Centre for Health Informatics, Cumming School of Medicine, University of CalgaryDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryInfection Prevention and Control Surveillance and Standards, Alberta Health ServicesInfection Prevention and Control Surveillance and Standards, Alberta Health ServicesDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryDepartment of Community Health Sciences, Cumming School of Medicine, University of CalgaryAbstract Background Population based surveillance of surgical site infections (SSIs) requires precise case-finding strategies. We sought to develop and validate machine learning models to automate the process of complex (deep incisional/organ space) SSIs case detection. Methods This retrospective cohort study included adult patients (age ≥ 18 years) admitted to Calgary, Canada acute care hospitals who underwent primary total elective hip (THA) or knee (TKA) arthroplasty between Jan 1st, 2013 and Aug 31st, 2020. True SSI conditions were judged by the Alberta Health Services Infection Prevention and Control (IPC) program staff. Using the IPC cases as labels, we developed and validated nine XGBoost models to identify deep incisional SSIs, organ space SSIs and complex SSIs using administrative data, electronic medical records (EMR) free text data, and both. The performance of machine learning models was assessed by sensitivity, specificity, positive predictive value, negative predictive value, F1 score, the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision–recall curve (PR AUC). In addition, a bootstrap 95% confidence interval (95% CI) was calculated. Results There were 22,059 unique patients with 27,360 hospital admissions resulting in 88,351 days of hospital stay. This included 16,561 (60.5%) TKA and 10,799 (39.5%) THA procedures. There were 235 ascertained SSIs. Of them, 77 (32.8%) were superficial incisional SSIs, 57 (24.3%) were deep incisional SSIs, and 101 (42.9%) were organ space SSIs. The incidence rates were 0.37 for superficial incisional SSIs, 0.21 for deep incisional SSIs, 0.37 for organ space and 0.58 for complex SSIs per 100 surgical procedures, respectively. The optimal XGBoost models using administrative data and text data combined achieved a ROC AUC of 0.906 (95% CI 0.835–0.978), PR AUC of 0.637 (95% CI 0.528–0.746), and F1 score of 0.79 (0.67–0.90). Conclusions Our findings suggest machine learning models derived from administrative data and EMR text data achieved high performance and can be used to automate the detection of complex SSIs.https://doi.org/10.1186/s13756-023-01294-0Surgical site infectionsTotal hip arthroplastyTotal knee arthroplastyMachine learning |
| spellingShingle | Guosong Wu Cheligeer Cheligeer Danielle A. Southern Elliot A. Martin Yuan Xu Jenine Leal Jennifer Ellison Kathryn Bush Tyler Williamson Hude Quan Cathy A. Eastwood Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study Antimicrobial Resistance and Infection Control Surgical site infections Total hip arthroplasty Total knee arthroplasty Machine learning |
| title | Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study |
| title_full | Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study |
| title_fullStr | Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study |
| title_full_unstemmed | Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study |
| title_short | Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study |
| title_sort | development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty a multicenter cohort study |
| topic | Surgical site infections Total hip arthroplasty Total knee arthroplasty Machine learning |
| url | https://doi.org/10.1186/s13756-023-01294-0 |
| work_keys_str_mv | AT guosongwu developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT cheligeercheligeer developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT danielleasouthern developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT elliotamartin developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT yuanxu developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT jenineleal developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT jenniferellison developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT kathrynbush developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT tylerwilliamson developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT hudequan developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy AT cathyaeastwood developmentofmachinelearningmodelsforthedetectionofsurgicalsiteinfectionsfollowingtotalhipandkneearthroplastyamulticentercohortstudy |