Advertisement

Machine-learning models for predicting surgical site infections using patient pre-operative risk and surgical procedure factors

  • Rabia Emhamed Al Mamlook
    Correspondence
    Address correspondence to Rabia Emhamed Al Mamlook, PhD, Department of Industrial and Entrepreneurial Engineering & Engineering Management, Western Michigan University, 3635 kenbrooke ct, Kalamazoo, MI, 49008, USA.
    Affiliations
    Department of Industrial and Entrepreneurial Engineering & Engineering Management, Western Michigan University, Kalamazoo, MI

    Department of Industrial, Engineering University of Zawiya, Al Zawiya City, Libya
    Search for articles by this author
  • Lee J. Wells
    Affiliations
    Department of Industrial and Entrepreneurial Engineering & Engineering Management, Western Michigan University, Kalamazoo, MI
    Search for articles by this author
  • Robert Sawyer
    Affiliations
    Department of Surgery, Western Michigan University Homer Stryker School of Medicine, Kalamazoo, MI
    Search for articles by this author
Published:August 21, 2022DOI:https://doi.org/10.1016/j.ajic.2022.08.013

      Highlights

      • This study aimed to develop and validate classification models for the occurrence of SSI to improve upon previous models.
      • Multiple risk factors for Pre-operative surgical site infection (SSI)were identified.
      • Various Machine learning and Deep Neural networks approach were compared to identify preoperative risk factors associated with SSI.
      • Deep Neural Network (DNN) model performed best on most model fit measures

      Abstract

      Background

      Surgical site infections (SSIs) are a significant health care problem as they can cause increased medical costs and increased morbidity and mortality. Assessing a patient's preoperative risk factors can improve risk stratification and help guide the surgical decision-making process. Previous efforts to use preoperative risk factors to predict the occurrence of SSIs have relied upon traditional statistical modeling approaches. The aim of this paper is to develop and validate, using state-of-the-art machine learning (ML) approaches, classification models for the occurrence of SSI to improve upon previous models.

      Methods

      In this work, using the American College of Surgeons’ National Surgical Quality Improvement Program (ACS NSQIP) database, the performances (eg prediction accuracy) of 7 different ML approaches (Logistic Regression (LR), Naïve Bayesian (NB), Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Deep Neural Network (DNN)) were compared. The performance of these models was evaluated using the area under the curve, accuracy, precision, sensitivity, and F1-score metrics.

      Results

      Overall, 2,882,526 surgical procedures were identified in the study for the SSI predictive models’ development. The results indicate that the DNN model offers the best predictive performance with 10-fold compared to the other 6 approaches considered (area under the curve = 0.8518, accuracy = 0.8518, precision = 0.8517, sensitivity = 0.8527, F1-score = 0.8518). Emergency case surgeries, American Society of Anesthesiologists (ASA) Index of 4 (ASA_4), BMI, Vascular surgeries, and general surgeries were most significant influencing features towards developing an SSI.

      Conclusions

      Equally important is that the commonly used LR approach for SSI prediction displayed mediocre performance. The results are encouraging as they suggest that the prediction performance for SSIs can be improved using modern ML approaches.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to American Journal of Infection Control
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Najjar YW
        • Al-Wahsh ZM
        • Hamdan M
        • Saleh MY
        Risk factors of orthopedic surgical site infection in Jordan: a prospective cohort study.
        Int J Surg Open. 2018; 15: 1-6
        • Tschelaut L
        • Assadian O
        • Strauss R
        • et al.
        A survey on current knowledge, practice and beliefs related to pre-operative antimicrobial decolonization regimens for prevention of surgical site infections among Austrian surgeons.
        J Hosp Infect. 2018; 100: 386-392
        • Ahmad HF
        • Kallies KJ
        • Shapiro SB
        The effect of mupirocin dressings on Post-operative surgical site infections in elective colorectal surgery: A prospective, randomized controlled triet al.
        Am J Surg. 2019; 217: 1083-1088
        • Schiavone MB
        • Moukarzel L
        • Leong K
        • et al.
        Surgical site infection reduction bundle in patients with gynecologic cancer undergoing colon surgery.
        Gynecol Oncol. 2017; 147: 115-119
        • Takahashi Y
        • Takesue Y
        • Fujiwara M
        • et al.
        Risk factors for surgical site infection after major hepatobiliary and pancreatic surgery.
        J Infect Chemother. 2018; 24: 739-743
        • Lubega A
        • Joel B
        • Lucy NJ
        Incidence and etiology of surgical site infections among emergency post-operative patients in Mbarara Regional Referral Hospital, South Western Uganda.
        Surg Res Pract. 2017; 2017: 1-6
        • Kang SI
        • Oh H
        • Kim MH
        • et al.
        Systematic review and meta-analysis of randomized controlled trials of the clinical effectiveness of impervious plastic wound protectors in reducing surgical site infections in patients undergoing abdominal surgery.
        Surgery. 2018; 164: 939-945
        • Segreti J
        • Parvizi J
        • Berbari E
        • Ricks P
        • Berríos-Torres SI
        Introduction to the centers for disease control and prevention and health care infection control practices advisory committee guideline for prevention of surgical site infection: prosthetic joint arthroplasty section.
        Surg Infect (Larchmt). 2017; 18: 394-400
        • Korol E
        • Johnston K
        • Waser N
        • et al.
        A systematic review of risk factors associated with surgical site infections among surgical patients.
        PLoS One. 2013; 8: e83743
        • Hoang SC
        • Klipfel AA
        • Roth LA
        • Vrees M
        • Schechter S
        • Shah N
        Colon and rectal surgery surgical site infection reduction bundle: to improve is to change.
        Am J Surg. 2019; 217: 40-45
        • Rudder NJ
        • Borgert AJ
        • Kallies KJ
        • Smith TJ
        • Shapiro SB
        Reduction of surgical site infections in colorectal surgery: a 10-year experience from an independent academic medical center.
        Am J Surg. 2019; 217: 1089-1093
        • Ban KA
        • Minei JP
        • Laronga C
        • et al.
        American college of surgeons and surgical infection society: surgical site infection guidelines, 2016 update.
        J Am Coll Surg. 2017; 224: 59-74
        • Lachiewicz MP
        • Moulton LJ
        • Jaiyeoba O
        Pelvic surgical site infections in gynecologic surgery.
        Infect Dis Obstet Gynecol. 2015; 2015: 1-8
        • Bartz-Kurycki MA
        • Green C
        • Anderson KT
        • et al.
        Enhanced neonatal surgical site infection prediction model utilizing statistically and clinically significant variables in combination with a machine learning algorithm.
        Am J Surg. 2018; 216: 764-777
        • Walraven CV
        • Musselman R
        The Surgical site infection risk score (SSIRS): a model to predict the risk of surgical site infection.
        PLoS One. 2013;
        • Li X
        • Nylander W
        • Smith T
        • Han S
        • Gunnar W
        Risk factors and predictive model development of thirty-day post-operative surgical site infection in the veterans administration surgical population.
        Surg Infect (Larchmt). 2018; 19: 278-285
        • Mu Yi
        • et al.
        Improving risk-adjusted measures of surgical site infection for the national health care safely network.
        Infect Control Hosp Epidemiol. 2011; 32: 970-986
        • Sampalis JS
        Development of risk scoring tool to predict surgical site infections.
        SOJ Surgery. 2015; 2: 1-10
        • Leekha S
        • Lahr BD
        • Thompson RL
        • Sampathkumar P
        • Duncan AA
        • Orenstein R
        Pre-operative risk prediction of surgical site infection requiring hospitalization or reoperation in patients undergoing vascular surgery.
        J Vasc Surg. 2016; 64: 177-184
        • Ejaz A
        • Schmidt C
        • Johnston FM
        • Frank SM
        • Pawlik TM
        Risk factors and prediction model for inpatient surgical site infection after major abdominal surgery.
        J Surg Res. 2017; 217: 153-159
        • Gbegnon A
        • Monestina J
        • Cromwell J
        Machine learning algorithm for accurate, automated, and real-time prediction of surgical site infections using EHR Data.
        J Surg Res. 2014; 186: 527
        • Reese SM
        • Knepper B
        • Young HL
        • Mauffrey C
        Development of a surgical site infection prediction model in orthopaedic trauma: the denver health model.
        Injury. 2017; 48: 2699-2704
        • Janssen DM
        • van Kuijk SM
        • d'Aumerie B
        • Willems P
        A prediction model of surgical site infection after instrumented thoracolumbar spine surgery in adults.
        Eur Spine J. 2019; 28: 775-782
        • Kuo P
        • Wu S
        • Chien P
        • et al.
        Artificial neural network approach to predict surgical site infection after free-flap reconstruction in patients receiving surgery for head and neck cancer.
        Oncotarget. 2018; 9
        • Haridas M
        • Malangoni MA
        Predictive factors for surgical site infection in general surgery.
        Surgery. 2008; 144: 496-503
        • Petrosyan Y
        • Thavorn K
        • Smith G
        • et al.
        Predicting postoperative surgical site infection with administrative data: a random forests algorithm.
        BMC Med Res Method. 2021; 21: 1-11
        • Shi S
        • Lei G
        • Yang L
        • et al.
        Using machine learning to predict postoperative liver dysfunction after aortic arch surgery.
        J Cardiothorac Vasc Anesth. 2021;
        • Zhu Y
        • Simon GJ
        • Wick EC
        • et al.
        Applying machine learning across sites: external validation of a surgical site infection detection algorithm.
        J Am Coll Surg. 2021; 232: 963-971
        • Hopkins BS
        • Mazmudar A
        • Driscoll C
        • et al.
        Using artificial intelligence (AI) to predict postoperative surgical site infection: a retrospective cohort of 4046 posterior spinal fusions.
        Clin Neurol Neurosurg. 2020; 192105718
        • Cooper JN
        • Wei L
        • Fernandez SA
        • Minneci PC
        • Deans KJ
        Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.
        Comput Biol Med. 2015; 57: 54-65
        • Fkirin A
        • Attiya G
        • El-Sayed A
        • Shouman MA
        Copyright protection of deep neural network models using digital watermarking: a comparative study.
        Multimedia Tools Appl. 2022; 81: 15961-15975
        • Kotsiantis SB
        • Zaharakis I
        • Pintelas P
        Supervised machine learning: a review of classification techniques.
        Emerg Artif Intell Appl Comput Eng. 2007; 160: 3-24https://doi.org/10.1007/s10462-007-9052-3
        • Chawla NV
        • Bowyer KW
        • Hall LO
        • Kegelmeyer WP
        SMOTE: synthetic minority over-sampling technique.
        J Artificial Intelligence Res. 2002; 16: 321-357
        • Chen CW
        • Tsai YH
        • Chang FR
        • Lin WC
        Ensemble feature selection in medical datasets: combining filter, wrapper, and embedded feature selection results.
        Expert Systems. 2020; 37: e12553
        • Al Mamlook Rabia Emhamed
        Advanced risk models to predict surgical site infections using machine learning approaches and risk-adjusted control charts.
        Dissertations. 2021; 3779
        • Vapnik V
        An overview of statistical learning theory.
        IEEE Trans Neural Networks. 1999; 10 (Sep.): 988-999
        • Ott E
        • BANGE FC
        • Sohr D
        • Teebken O
        • Mattner F
        Risk factors associated with surgical site infections following vascular surgery at a German university hospitet al.
        Epidemiol Infect. 2013; 141: 1207-1213