Browsing by Author "Ellison, Jennifer"

Now showing 1 - 4 of 4
  • 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
    Hospital ward design and prevention of hospital-acquired infections: A prospective clinical trial
    (2014-01-01) Ellison, Jennifer; Southern, Danielle; Holton, Donna; Henderson, Elizabeth; Wallace, Jean; Faris, Peter; Ghali, William A; Conly, John
    BACKGROUND: Renovation of a general medical ward provided an opportunity to study health care facility design as a factor for preventing hospital-acquired infections.OBJECTIVE: To determine whether a hospital ward designed with predominantly single rooms was associated with lower event rates of hospital-acquired infection and colonization.METHODS: A prospective controlled trial with patient allocation incorporating randomness was designed with outcomes on multiple ‘historic design’ wards (mainly four-bed rooms with shared bathrooms) compared with outcomes on a newly renovated ‘new design’ ward (predominantly single rooms with private bathrooms).RESULTS: Using Poisson regression analysis and adjusting for time at risk, there were no differences (P=0.18) in the primary outcome (2.96 versus 1.85 events/1000 patient-days, respectively). After adjustment for age, sex, Charlson score, admitted from care facility, previous hospitalization within six months, isolation requirement and the duration on antibiotics, the incidence rate ratio was 1.44 (95% CI 0.71 to 2.94) for the new design versus the historic design wards. A restricted analysis on the numbers of events occurring in single-bed versus multibed wings within the new design ward revealed an event incidence density of 1.89 versus 3.47 events/1000 patient-days, respectively (P=0.18), and an incidence rate ratio of 0.54 (95% CI 0.15 to 1.30).CONCLUSIONS: No difference in the incidence density of hospital-acquired infections or colonizations was observed for medical patients admitted to a new design ward versus historic design wards. A restricted analysis of events occurring in single-bed versus multibed wings suggests that ward design warrants further study.
  • Thumbnail Image
    ItemOpen Access
    Patient and ward related risk factors in a multi-ward nosocomial outbreak of COVID-19: Outbreak investigation and matched case–control study
    (2023-03-22) Leal, Jenine; O’Grady, Heidi M.; Armstrong, Logan; Dixit, Devika; Khawaja, Zoha; Snedeker, Kate; Ellison, Jennifer; Erebor, Joyce; Jamieson, Peter; Weiss, Amanda; Salcedo, Daniel; Roberts, Kimberley; Wiens, Karen; Croxen, Matthew A.; Berenger, Byron M.; Pabbaraju, Kanti; Lin, Yi-Chan; Evans, David; Conly, John M.
    Abstract Background Risk factors for nosocomial COVID-19 outbreaks continue to evolve. The aim of this study was to investigate a multi-ward nosocomial outbreak of COVID-19 between 1st September and 15th November 2020, occurring in a setting without vaccination for any healthcare workers or patients. Methods Outbreak report and retrospective, matched case–control study using incidence density sampling in three cardiac wards in an 1100-bed tertiary teaching hospital in Calgary, Alberta, Canada. Patients were confirmed/probable COVID-19 cases and contemporaneous control patients without COVID-19. COVID-19 outbreak definitions were based on Public Health guidelines. Clinical and environmental specimens were tested by RT-PCR and as applicable quantitative viral cultures and whole genome sequencing were conducted. Controls were inpatients on the cardiac wards during the study period confirmed to be without COVID-19, matched to outbreak cases by time of symptom onset dates, age within ± 15 years and were admitted in hospital for at least 2 days. Demographics, Braden Score, baseline medications, laboratory measures, co-morbidities, and hospitalization characteristics were collected on cases and controls. Univariate and multivariate conditional logistical regression was used to identify independent risk factors for nosocomial COVID-19. Results The outbreak involved 42 healthcare workers and 39 patients. The strongest independent risk factor for nosocomial COVID-19 (IRR 3.21, 95% CI 1.47–7.02) was exposure in a multi-bedded room. Of 45 strains successfully sequenced, 44 (97.8%) were B.1.128 and differed from the most common circulating community lineages. SARS-CoV-2 positive cultures were detected in 56.7% (34/60) of clinical and environmental specimens. The multidisciplinary outbreak team observed eleven contributing events to transmission during the outbreak. Conclusions Transmission routes of SARS-CoV-2 in hospital outbreaks are complex; however multi-bedded rooms play a significant role in the transmission of SARS-CoV-2.
  • Thumbnail Image
    ItemOpen Access