Artificial neural network approach to predict surgical site infection after free-flap reconstruction in patients receiving surgery for head and neck cancer

Background The aim of this study was to develop an effective surgical site infection (SSI) prediction model in patients receiving free-flap reconstruction after surgery for head and neck cancer using artificial neural network (ANN), and to compare its predictive power with that of conventional logistic regression (LR). Materials and methods There were 1,836 patients with 1,854 free-flap reconstructions and 438 postoperative SSIs in the dataset for analysis. They were randomly assigned tin ratio of 7:3 into a training set and a test set. Based on comprehensive characteristics of patients and diseases in the absence or presence of operative data, prediction of SSI was performed at two time points (pre-operatively and post-operatively) with a feed-forward ANN and the LR models. In addition to the calculated accuracy, sensitivity, and specificity, the predictive performance of ANN and LR were assessed based on area under the curve (AUC) measures of receiver operator characteristic curves and Brier score. Results ANN had a significantly higher AUC (0.892) of post-operative prediction and AUC (0.808) of pre-operative prediction than LR (both P<0.0001). In addition, there was significant higher AUC of post-operative prediction than pre-operative prediction by ANN (p<0.0001). With the highest AUC and the lowest Brier score (0.090), the post-operative prediction by ANN had the highest overall predictive performance. Conclusion The post-operative prediction by ANN had the highest overall performance in predicting SSI after free-flap reconstruction in patients receiving surgery for head and neck cancer.

[1]  T. Komori,et al.  Literature Review of Criteria for Defining Recipient-Site Infection after Oral Oncologic Surgery with Simultaneous Reconstruction. , 2017, Surgical infections.

[2]  Donald A Szlosek,et al.  Using Machine Learning and Natural Language Processing Algorithms to Automate the Evaluation of Clinical Decision Support in Electronic Medical Record Systems , 2016, EGEMS.

[3]  Zhongheng Zhang,et al.  A gentle introduction to artificial neural networks. , 2016, Annals of translational medicine.

[4]  M. Bulsara,et al.  Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods. , 2016, Medical physics.

[5]  D. Deschler,et al.  Head and neck free flap surgical site infections in the era of the Surgical Care Improvement Project , 2016, Head & neck.

[6]  Xilin Yang,et al.  Non-linear associations of risk factors with mild hypoglycemia among Chinese patients with type 2 diabetes. , 2016, Journal of diabetes and its complications.

[7]  David O. Meltzer,et al.  Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards , 2016, Critical care medicine.

[8]  R. Vogel,et al.  Antibiotic Use after Free Tissue Reconstruction of Head and Neck Defects: Short Course vs. Long Course. , 2016, Surgical infections.

[9]  M. Roudbari,et al.  Artificial neural networks versus bivariate logistic regression in prediction diagnosis of patients with hypertension and diabetes , 2016, Medical journal of the Islamic Republic of Iran.

[10]  D. Deschler,et al.  The time course and microbiology of surgical site infections after head and neck free flap surgery , 2015, The Laryngoscope.

[11]  P. Griffin,et al.  Use of random forest to estimate population attributable fractions from a case-control study of Salmonella enterica serotype Enteritidis infections , 2015, Epidemiology and Infection.

[12]  S. Miyamoto,et al.  Statistical Analysis of Surgical Site Infection After Head and Neck Reconstructive Surgery , 2014, Annals of Surgical Oncology.

[13]  Genevera I. Allen,et al.  Molecular pathway identification using biological network-regularized logistic models , 2013, BMC Genomics.

[14]  S. Jeng,et al.  Microsurgical Reconstruction for Head and Neck Cancer in Elderly Patients , 2013, Journal of Reconstructive Microsurgery.

[15]  King-Teh Lee,et al.  In-hospital mortality prediction in patients receiving mechanical ventilation in Taiwan. , 2013, American journal of critical care : an official publication, American Association of Critical-Care Nurses.

[16]  Juanmei Liu,et al.  Comparison of Prediction Model for Cardiovascular Autonomic Dysfunction Using Artificial Neural Network and Logistic Regression Analysis , 2013, PloS one.

[17]  Wen-Hsien Ho,et al.  Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network , 2013, TheScientificWorldJournal.

[18]  Y. Hasegawa,et al.  Surgical site infection in clean-contaminated head and neck cancer surgery: risk factors and prognosis , 2013, European Archives of Oto-Rhino-Laryngology.

[19]  Jian Sun,et al.  Surgical site infection in elderly oral cancer patients: is the evaluation of comorbid conditions helpful in the identification of high-risk ones? , 2012, Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons.

[20]  T. Mücke,et al.  Influence of irradiation and oncologic surgery on head and neck microsurgical reconstructions. , 2012, Oral oncology.

[21]  Z-Y Chen,et al.  The Diagnostic Value of a Multivariate Logistic Regression Analysis Model with Transvaginal Power Doppler Ultrasonography for the Prediction of Ectopic Pregnancy , 2012, The Journal of international medical research.

[22]  Woojae Kim,et al.  A Comparison of Intensive Care Unit Mortality Prediction Models through the Use of Data Mining Techniques , 2011, Healthcare informatics research.

[23]  J. Choi,et al.  Risk factors of surgical site infection in patients undergoing major oncological surgery for head and neck cancer. , 2011, Oral oncology.

[24]  T. Aoki,et al.  Analysis of risk factors for surgical-site infections in 276 oral cancer surgeries with microvascular free-flap reconstructions at a single university hospital , 2010, Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy.

[25]  D. Pittet,et al.  Preventing surgical site infections , 2010, Expert review of anti-infective therapy.

[26]  S. Jeng,et al.  Alternative reconstructive choices for anterolateral thigh flap dissection in cases in which no sizable skin perforator is available , 2009, Head & neck.

[27]  A. Sepehr,et al.  Antibiotics in head and neck surgery in the setting of malnutrition, tracheotomy, and diabetes , 2009, The Laryngoscope.

[28]  H. Devalia,et al.  Radiotherapy and wound healing , 2007, International wound journal.

[29]  Jigneshkumar L Patel,et al.  Applications of artificial neural networks in medical science. , 2007, Current clinical pharmacology.

[30]  Y. Wong,et al.  Risk Factors for Wound Infection After Surgery in Primary Oral Cavity Cancer Patients , 2007, The Laryngoscope.

[31]  A. Gabrielli,et al.  Power of breathing determined noninvasively with use of an artificial neural network in patients with respiratory failure* , 2006, Critical care medicine.

[32]  C. Fournier,et al.  Multivariate analysis of risk factors for wound infection in head and neck squamous cell carcinoma surgery with opening of mucosa. Study of 260 surgical procedures. , 2005, Oral oncology.

[33]  C. Maynard,et al.  Predictors of wound complications after laryngectomy: A study of over 2000 patients , 2004, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[34]  T. Calcaterra,et al.  Microvascular reconstruction after previous neck dissection. , 2002, Archives of otolaryngology--head & neck surgery.

[35]  J. Tracy,et al.  Surgical-Site Infections: Reanalysis of Risk Factors , 2002, Infection Control &#x0026; Hospital Epidemiology.

[36]  T. Coats,et al.  Comparison of artificial intelligence techniques with UKTRISS for estimating probability of survival after trauma. UK Trauma and Injury Severity Score. , 2001, The Journal of trauma.

[37]  L. Kowalski,et al.  Risk factors for postoperative complications in oral cancer and their prognostic implications. , 2001, Archives of otolaryngology--head & neck surgery.

[38]  C. Fournier,et al.  Risk factors for wound infection in head and neck cancer surgery: A prospective study , 2001, Head & neck.

[39]  S. Stoeckli,et al.  Salvage surgery after failure of nonsurgical therapy for carcinoma of the larynx and hypopharynx. , 2000, Archives of otolaryngology--head & neck surgery.

[40]  D. Osoba,et al.  Quality of life and oral function following radiotherapy for head and neck cancer , 1999, Head & neck.

[41]  J. Savino,et al.  An artificial neural network as a model for prediction of survival in trauma patients: validation for a regional trauma area. , 1998, The Journal of trauma.

[42]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[43]  F. Harrell,et al.  Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors , 2005 .

[44]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[45]  R. Coimbra,et al.  Isolated traumatic brain injury in patients with cirrhosis: do different treatment paradigms result in increased mortality? , 2017, American journal of surgery.

[46]  Yi Han,et al.  Overview of Artificial Neural Networks , 2009, Artificial Neural Networks.

[47]  M. Hanasono,et al.  Microvascular surgery in the previously operated and irradiated neck , 2009, Microsurgery.

[48]  V. Golubović,et al.  Risk factors for wound infection after oral cancer surgery. , 2007, Oral oncology.

[49]  N. Birkmeyer,et al.  Complications in head and neck surgery: a meta-analysis of postlaryngectomy pharyngocutaneous fistula. , 2006, Archives of otolaryngology--head & neck surgery.

[50]  S. le Cessie,et al.  Comorbidity as a major risk factor for mortality and complications in head and neck surgery. , 2005, Archives of otolaryngology--head & neck surgery.

[51]  W. Liljemark,et al.  Human oral microbial ecology and dental caries and periodontal diseases. , 1996, Critical reviews in oral biology and medicine : an official publication of the American Association of Oral Biologists.

[52]  G. Brier.  VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY , 1950 .

[53]  J. Vandenbroucke,et al.  Practice of Epidemiology What Do Case-Control Studies Estimate? Survey of Methods and Assumptions in Published Case-Control Research , 2008 .

[54]  L. Asadian,et al.  Hyperglycemia: a Predictor of Death in Severe Head Injury Patients , 2022 .