Patrick C Sanger1, Gabrielle H van Ramshorst2, Ezgi Mercan3, Shuai Huang4, Andrea L Hartzler5, Cheryl A L Armstrong6, Ross J Lordon7, William B Lober8, Heather L Evans6. 1. Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA. Electronic address: psanger@uw.edu. 2. Department of Surgery, VU University Medical Center, Amsterdam, Netherlands. 3. Department of Computer Science, University of Washington, Seattle, WA. 4. Department of Industrial and Systems Engineering, University of Washington, Seattle, WA. 5. Group Health Research Institute, Group Health Cooperative, Seattle, WA. 6. Department of Surgery, University of Washington, Seattle, WA. 7. Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA. 8. Department of Biobehavioral Nursing and Health Systems, and Biomedical Informatics and Medical Education, University of Washington, Seattle, WA.
Abstract
BACKGROUND: Surgical site infection (SSI) remains a common, costly, and morbid health care-associated infection. Early detection can improve outcomes, yet previous risk models consider only baseline risk factors (BF) not incorporating a proximate and timely data source-the wound itself. We hypothesize that incorporation of daily wound assessment improves the accuracy of SSI identification compared with traditional BF alone. STUDY DESIGN: A prospective cohort of 1,000 post open abdominal surgery patients at an academic teaching hospital were examined daily for serial features (SF), for example, wound characteristics and vital signs, in addition to standard BF, for example, wound class. Using supervised machine learning, we trained 3 Naïve Bayes classifiers (BF, SF, and BF+SF) using patient data from 1 to 5 days before diagnosis to classify SSI on the following day. For comparison, we also created a simplified SF model that used logistic regression. Control patients without SSI were matched on 5 similar consecutive postoperative days to avoid confounding by length of stay. Accuracy, sensitivity/specificity, and area under the receiver operating characteristic curve were calculated on a training and hold-out testing set. RESULTS: Of 851 patients, 19.4% had inpatient SSIs. Univariate analysis showed differences in C-reactive protein, surgery duration, and contamination, but no differences in American Society of Anesthesiologists scores, diabetes, or emergency surgery. The BF, SF, and BF+SF classifiers had area under the receiver operating characteristic curves of 0.67, 0.76, and 0.76, respectively. The best-performing classifier (SF) had optimal sensitivity of 0.80, specificity of 0.64, positive predictive value of 0.35, and negative predictive value of 0.93. Features most associated with subsequent SSI diagnosis were granulation degree, exudate amount, nasogastric tube presence, and heart rate. CONCLUSIONS: Serial features provided moderate positive predictive value and high negative predictive value for early identification of SSI. Addition of baseline risk factors did not improve identification. Features of evolving wound infection are discernable before the day of diagnosis, based primarily on visual inspection.
BACKGROUND: Surgical site infection (SSI) remains a common, costly, and morbid health care-associated infection. Early detection can improve outcomes, yet previous risk models consider only baseline risk factors (BF) not incorporating a proximate and timely data source-the wound itself. We hypothesize that incorporation of daily wound assessment improves the accuracy of SSI identification compared with traditional BF alone. STUDY DESIGN: A prospective cohort of 1,000 post open abdominal surgery patients at an academic teaching hospital were examined daily for serial features (SF), for example, wound characteristics and vital signs, in addition to standard BF, for example, wound class. Using supervised machine learning, we trained 3 Naïve Bayes classifiers (BF, SF, and BF+SF) using patient data from 1 to 5 days before diagnosis to classify SSI on the following day. For comparison, we also created a simplified SF model that used logistic regression. Control patients without SSI were matched on 5 similar consecutive postoperative days to avoid confounding by length of stay. Accuracy, sensitivity/specificity, and area under the receiver operating characteristic curve were calculated on a training and hold-out testing set. RESULTS: Of 851 patients, 19.4% had inpatient SSIs. Univariate analysis showed differences in C-reactive protein, surgery duration, and contamination, but no differences in American Society of Anesthesiologists scores, diabetes, or emergency surgery. The BF, SF, and BF+SF classifiers had area under the receiver operating characteristic curves of 0.67, 0.76, and 0.76, respectively. The best-performing classifier (SF) had optimal sensitivity of 0.80, specificity of 0.64, positive predictive value of 0.35, and negative predictive value of 0.93. Features most associated with subsequent SSI diagnosis were granulation degree, exudate amount, nasogastric tube presence, and heart rate. CONCLUSIONS: Serial features provided moderate positive predictive value and high negative predictive value for early identification of SSI. Addition of baseline risk factors did not improve identification. Features of evolving wound infection are discernable before the day of diagnosis, based primarily on visual inspection.
Authors: Eyal Zimlichman; Daniel Henderson; Orly Tamir; Calvin Franz; Peter Song; Cyrus K Yamin; Carol Keohane; Charles R Denham; David W Bates Journal: JAMA Intern Med Date: 2013 Dec 9-23 Impact factor: 21.873
Authors: Vanessa P Ho; Sharon L Stein; Koiana Trencheva; Philip S Barie; Jeffrey W Milsom; Sang W Lee; Toyooki Sonoda Journal: Dis Colon Rectum Date: 2011-07 Impact factor: 4.585
Authors: C Gibbons; J Bruce; J Carpenter; A P Wilson; J Wilson; A Pearson; D L Lamping; Z H Krukowski; B C Reeves Journal: Health Technol Assess Date: 2011-09 Impact factor: 4.014
Authors: Gabrielle H van Ramshorst; Margreet C Vos; Dennis den Hartog; Wim C J Hop; Johannes Jeekel; Steven E R Hovius; Johan F Lange Journal: Surg Infect (Larchmt) Date: 2013-03-13 Impact factor: 2.150
Authors: Thomas D Pinkney; Melanie Calvert; David C Bartlett; Adrian Gheorghe; Val Redman; George Dowswell; William Hawkins; Tony Mak; Haney Youssef; Caroline Richardson; Steven Hornby; Laura Magill; Richard Haslop; Sue Wilson; Dion Morton Journal: BMJ Date: 2013-07-31
Authors: Kristy Kummerow Broman; Cameron E Gaskill; Adil Faqih; Michael Feng; Sharon E Phillips; William B Lober; Richard A Pierce; Michael D Holzman; Heather L Evans; Benjamin K Poulose Journal: JAMA Surg Date: 2019-02-01 Impact factor: 14.766