Enhanced neonatal surgical site infection prediction model utilizing statistically and clinically significant variables in combination with a machine learning algorithm

American Journal of Surgery

Volumn 216, Issue 4, 2018, Pages 764-777

  Bartz Kurycki, Marisa A ^a   Green, Charles ^a   Anderson, Kathryn T ^a   Alder, Adam C ^b   Bucher, Brian T ^c   Cina, Robert A ^d   Jamshidi, Ramin ^e   Russell, Robert T ^f   Williams, Regan F ^g   Tsao, KuoJen ^a  

^a UNIVERSITY OF TEXAS   (United States)

^b CHILDREN S MEDICAL CENTER   (United States)

^c UNIVERSITY OF UTAH SCHOOL OF MEDICINE   (United States)

^d MEDICAL UNIVERSITY OF SOUTH CAROLINA   (United States)

^e PHOENIX CHILDREN'S HOSPITAL   (United States)

^f UNIVERSITY OF ALABAMA AT BIRMINGHAM   (United States)

^g UNIVERSITY OF TENNESSEE HEALTH SCIENCE CENTER   (United States)

Author keywords

Infants; Machine learning algorithm; Prediction model; Risk factors; Surgical wound infection

Indexed keywords

ALGORITHM; ARTICLE; CLINICAL FEATURE; CONTROLLED STUDY; DIAGNOSTIC ACCURACY; FEMALE; HUMAN; INFANT; MACHINE LEARNING; MAJOR CLINICAL STUDY; MALE; NEWBORN; NEWBORN DISEASE; PREDICTION; PRIORITY JOURNAL; STATISTICAL MODEL; SURGICAL INFECTION; VALIDATION PROCESS; AREA UNDER THE CURVE; DECISION SUPPORT SYSTEM; RECEIVER OPERATING CHARACTERISTIC; RETROSPECTIVE STUDY; RISK ASSESSMENT; RISK FACTOR;

ALGORITHMS; AREA UNDER CURVE; DECISION SUPPORT TECHNIQUES; FEMALE; HUMANS; INFANT; INFANT, NEWBORN; LOGISTIC MODELS; MACHINE LEARNING; MALE; RETROSPECTIVE STUDIES; RISK ASSESSMENT; RISK FACTORS; ROC CURVE; SURGICAL WOUND INFECTION;

EID: 85050874585     PISSN: 00029610     EISSN: 18791883     Source Type: Journal    
DOI: 10.1016/j.amjsurg.2018.07.041     Document Type: Article

References (27)

1. Khoshbin, A., So, J.P., Aleem, I.S., Stephens, D., Matlow, A.G., Wright, J.G., Antibiotic prophylaxis to prevent surgical site infections in children: a prospective cohort study. Ann Surg 262:2 (2014), 397–402, 10.1097/SLA.0000000000000938.
2. Maizlin II, Redden, D.T., Beierle, E.A., Chen, M.K., Russell, R.T., Utilization of the NSQIP-pediatric database in development and validation of a new predictive model of pediatric postoperative wound complications. J Am Coll Surg, 2017, 10.1016/j.jamcollsurg.2016.12.022.
3. Weber, C.D., Applying adult ventilator-associated pneumonia bundle evidence to the ventilated neonate. Adv Neonatal Care 16:3 (2016), 178–190, 10.1097/ANC.0000000000000276.
4. Vu, L.T., Vittinghoff, E., Nobuhara, K.K., Farmer, D.L., Lee, H., Surgical site infections in neonates and infants: is antibiotic prophylaxis needed for longer than 24 h?. Pediatr Surg Int 30:6 (2014), 587–592, 10.1007/s00383-014-3506-x.
5. Fawley, J., Chelius, T.H., Anderson, Y., Cassidy, L.D., Arca, M.J., Relationship between perioperative blood transfusion and surgical site infections in the newborn population: an ACS-NSQIP-Pediatrics analysis. J Pediatr Surg 51:9 (2016), 1397–1404, 10.1016/j.jpedsurg.2016.05.010.
6. Segal, I., Kang, C., Albersheim, S.G., Skarsgard, E.D., Lavoie, P.M., Surgical site infections in infants admitted to the neonatal intensive care unit. J Pediatr Surg 49:3 (2014), 381–384, 10.1016/j.jpedsurg.2013.08.001.
7. Zens, T.J., Rusy, D.A., Gosain, A., Pediatric surgeon-directed wound classification improves accuracy. J Surg Res 201:2 (2016), 432–439, 10.1016/j.jss.2015.11.051.
8. Putnam, L.R., Levy, S.M., Holzmann-Pazgal, G., Lally, K.P., Lillian, S.K., Tsao, K., Surgical wound classification for pediatric appendicitis remains poorly documented despite targeted interventions. J Pediatr Surg 50:6 (2015), 915–918, 10.1016/j.jpedsurg.2015.03.008.
9. Levy, S.M., Holzmann-Pazgal, G., Lally, K.P., Davis, K., Kao, L.S., Tsao, K., Quality check of a quality measure: surgical wound classification discrepancies impact risk-stratified surgical site infection rates in pediatric appendicitis. J Am Coll Surg 217:6 (2013), 969–973, 10.1016/j.jamcollsurg.2013.07.398.
10. Snyder, R.A., Johnson, L., Tice, J., et al. Wound classification in pediatric general surgery: significant variation exists among providers. J Am Coll Surg 217:5 (2013), 819–826, 10.1016/j.jamcollsurg.2013.05.027.
11. Ortega, G., Rhee, D.S., Papandria, D.J., et al. An evaluation of surgical site infections by wound classification system using the ACS-NSQIP. J Surg Res 174:1 (2012), 33–38, 10.1016/j.jss.2011.05.056.
12. Vu, L.T., Nobuhara, K.K., Lee, H., Farmer, D.L., Conflicts in wound classification of neonatal operations. J Pediatr Surg 44:6 (2009), 1206–1211, 10.1016/j.jpedsurg.2009.02.026.
13. Kraemer, K., Cohen, M.E., Liu, Y., et al. Development and evaluation of the american College of surgeons NSQIP pediatric surgical risk calculator. J Am Coll Surg 223:5 (2016), 685–693, 10.1016/j.jamcollsurg.2016.08.542.
14. Stey, A.M., Kenney, B.D., Moss, R.L., et al. A risk calculator predicting postoperative adverse events in neonates undergoing major abdominal or thoracic surgery. J Pediatr Surg 50:6 (2015), 987–991, 10.1016/j.jpedsurg.2015.03.023.
15. Bilimoria, K.Y., Liu, Y., Paruch, J.L., et al. Development and evaluation of the universal ACS NSQIP surgical risk calculator: a decision aid and informed consent tool for patients and surgeons. J Am Coll Surg 217:5 (2013), 833–842, 10.1016/j.jamcollsurg.2013.07.385 e3.
16. Azar, A.T., Elshazly, H.I., Hassanien, A.E., Elkorany, A.M., A random forest classifier for lymph diseases. Comput Meth Progr Biomed 113:2 (2014), 465–473, 10.1016/j.cmpb.2013.11.004.
17. Ross, E.G., Shah, N.H., Dalman, R.L., Nead, K.T., Cooke, J.P., Leeper, N.J., The use of machine learning for the identification of peripheral artery disease and future mortality risk. J Vasc Surg 64:5 (2016), 1515–1522, 10.1016/j.jvs.2016.04.026 e3.
18. Breiman, L., Random forests. Mach Learn 45:1 (2001), 5–32, 10.1023/A:1010933404324.
19. Saito, J.M., Chen, L.E., Hall, B.L., et al. Risk-adjusted hospital outcomes for children ’ s surgery. Pediatrics 132:3 (2013), e677–e688, 10.1542/peds.2013-0867.
20. Stone, M., Cross-validatory choice and assessment of statistical predictions. J Roy Stat Soc 36:2 (1974), 111–147.
21. Zweig, M.H., Campbell, G., Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 39:4 (1993), 561–577 (ROC; Receiver-Operating Characteristic; SDT; Signal Detection Theory).
22. Clements, K.E., Fisher, M., Quaye, K., O'Donnell, R., Whyte, C., Horgan, M.J., Surgical site infections in the NICU. J Pediatr Surg 51:9 (2016), 1405–1408, 10.1016/j.jpedsurg.2016.04.002.
23. Stey, A.M., Kenney, B.D., Moss, R.L., et al. A risk calculator predicting postoperative adverse events in neonates undergoing major abdominal or thoracic surgery. J Pediatr Surg 50:6 (2015), 987–991, 10.1016/j.jpedsurg.2015.03.023.
24. Gilje, E.A., Hossain, M.J., Vinocur, C.D., Berman, L., Surgical site infections in neonates are independently associated with longer hospitalizations. J Perinatol 37:10 (2017), 1130–1134, 10.1038/jp.2017.107.
25. Lin, W.J., Chen, J.J., Class-imbalanced classifiers for high-dimensional data. Briefings Bioinf 14:1 (2013), 13–26, 10.1093/bib/bbs006.
26. Gross, E.R., Christensen, M., Schultz, J.A., Cassidy, L.D., Anderson, Y., Arca, M.J., Does the American College of Surgeons NSQIP-pediatric accurately represent overall patient outcomes?. J Am Coll Surg 221:4 (2015), 828–836, 10.1016/j.jamcollsurg.2015.07.014.
27. Ju, M.H., Ko, C.Y., Hall, B.L., Bosk, C.L., Bilimoria, K.Y., Wick, E.C., A comparison of 2 surgical site infection monitoring systems. JAMA Surg, 150(1), 2015, 51, 10.1001/jamasurg.2014.2891.