Browsing by Author "Bush, Kathryn"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study
    (2023-09-02) Wu, Guosong; Cheligeer, Cheligeer; Southern, Danielle A.; Martin, Elliot A.; Xu, Yuan; Leal, Jenine; Ellison, Jennifer; Bush, Kathryn; Williamson, Tyler; Quan, Hude; Eastwood, Cathy A.
    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.
  • Thumbnail Image
    ItemOpen Access
    Risk of transmission of respiratory viruses during aerosol-generating medical procedures (AGMPs) revisited in the COVID-19 pandemic: a systematic review
    (2022-08-11) Leal, Jenine; Farkas, Brenlea; Mastikhina, Liza; Flanagan, Jordyn; Skidmore, Becky; Salmon, Charleen; Dixit, Devika; Smith, Stephanie; Tsekrekos, Stephen; Lee, Bonita; Vayalumkal, Joseph; Dunn, Jessica; Harrison, Robyn; Cordoviz, Melody; Dubois, Roberta; Chandran, Uma; Clement, Fiona; Bush, Kathryn; Conly, John; Larios, Oscar
    Abstract Background In many jurisdictions healthcare workers (HCWs) are using respirators for aerosol-generating medical procedures (AGMPs) performed on adult and pediatric populations with all suspect/confirmed viral respiratory infections (VRIs). This systematic review assessed the risk of VRIs to HCWs in the presence of AGMPs, the role respirators versus medical/surgical masks have on reducing that risk, and if the risk to HCWs during AGMPs differed when caring for adult or pediatric patient populations. Main text We searched MEDLINE, EMBASE, Cochrane Central, Cochrane SR, CINAHL, COVID-19 specific resources, and MedRxiv for English and French articles from database inception to September 9, 2021. Independent reviewers screened abstracts using pre-defined criteria, reviewed full-text articles, selected relevant studies, abstracted data, and conducted quality assessments of all studies using the ROBINS-I risk of bias tool. Disagreements were resolved by consensus. Thirty-eight studies were included; 23 studies on COVID-19, 10 on SARS, and 5 on MERS/ influenza/other respiratory viruses. Two of the 16 studies which assessed associations found that HCWs were 1.7 to 2.5 times more likely to contract COVID-19 after exposure to AGMPs vs. not exposed to AGMPs. Eight studies reported statistically significant associations for nine specific AGMPs and transmission of SARS to HCWS. Intubation was consistently associated with an increased risk of SARS. HCWs were more likely (OR 2.05, 95% CI 1.2–3.4) to contract human coronaviruses when exposed to an AGMP in one study. There were no reported associations between AGMP exposure and transmission of influenza or in a single study on MERS. There was limited evidence supporting the use of a respirator over a medical/surgical mask during an AGMP to reduce the risk of viral transmission. One study described outcomes of HCWs exposed to a pediatric patient during intubation. Conclusion Exposure to an AGMP may increase the risk of transmission of COVID-19, SARS, and human coronaviruses to HCWs, however the evidence base is heterogenous and prone to confounding, particularly related to COVID-19. There continues to be a significant research gap in the epidemiology of the risk of VRIs among HCWs during AGMPs, particularly for pediatric patients. Further evidence is needed regarding what constitutes an AGMP.
  • Thumbnail Image
    ItemOpen Access
    Validating administrative data to identify complex surgical site infections following cardiac implantable electronic device implantation: a comparison of traditional methods and machine learning
    (2022-11-10) Rennert-May, Elissa; Leal, Jenine; MacDonald, Matthew K.; Cannon, Kristine; Smith, Stephanie; Exner, Derek; Larios, Oscar E.; Bush, Kathryn; Chew, Derek
    Abstract Background Cardiac implantable electronic device (CIED) surgical site infections (SSIs) have been outpacing the increases in implantation of these devices. While traditional surveillance of these SSIs by infection prevention and control would likely be the most accurate, this is not practical in many centers where resources are constrained. Therefore, we explored the validity of administrative data at identifying these SSIs. Methods We used a cohort of all patients with CIED implantation in Calgary, Alberta where traditional surveillance was done for infections from Jan 1, 2013 to December 31, 2019. We used this infection subgroup as our “gold standard” and then utilized various combinations of administrative data to determine which best optimized the sensitivity and specificity at identifying infection. We evaluated six approaches to identifying CIED infection using administrative data, which included four algorithms using International Classification of Diseases codes and/or Canadian Classification of Health Intervention codes, and two machine learning models. A secondary objective of our study was to assess if machine learning techniques with training of logistic regression models would outperform our pre-selected codes. Results We determined that all of the pre-selected algorithms performed well at identifying CIED infections but the machine learning model was able to produce the optimal method of identification with an area under the receiver operating characteristic curve (AUC) of 96.8%. The best performing pre-selected algorithm yielded an AUC of 94.6%. Conclusions Our findings suggest that administrative data can be used to effectively identify CIED infections. While machine learning performed the most optimally, in centers with limited analytic capabilities a simpler algorithm of pre-selected codes also has excellent yield. This can be valuable for centers without traditional surveillance to follow trends in SSIs over time and identify when rates of infection are increasing. This can lead to enhanced interventions for prevention of SSIs.