Using artificial intelligence (AI) to predict postoperative surgical site infection: A retrospective cohort of 4046 posterior spinal fusions

• Published in: Clinical neurology and neurosurgery 2020-05, Vol.192, p.105718-105718, Article 105718
• Main Authors: Hopkins, Benjamin S., Mazmudar, Aditya, Driscoll, Conor, Svet, Mark, Goergen, Jack, Kelsten, Max, Shlobin, Nathan A., Kesavabhotla, Kartik, Smith, Zachary A, Dahdaleh, Nader S
• Format: Article
• Language: English
• Subjects: Acquired immune deficiency syndrome; AIDS; Artificial intelligence; Back surgery; Big Data; Bone surgery; Cerebrovascular diseases; Comorbidity; Congestive heart failure; Decision making; Heart failure; Hemiplegia; HIV; Human immunodeficiency virus; Infections; Learning algorithms; Machine learning; Minimally invasive surgery; Neural networks; Neurology; Paralysis; Paraplegia; Patient satisfaction; Patients; Rheumatic diseases; Risk factors; Spine surgery; Surgeons; Surgery; Surgical site infection; Surgical site infections; Trends
• ISSN: 0303-8467; 1872-6968
• DOI: 10.1016/j.clineuro.2020.105718

•Postoperative surgical site infection after posterior spinal fusion was examined.•Machine learning and artificial intelligence were used to create a model.•The model had high predictive value.•Factors protective against infection were identified.•Machine learning and artificial intelligence should be employed in clinical decision making. Machine Learning and Artificial Intelligence (AI) are rapidly growing in capability and increasingly applied to model outcomes and complications within medicine. In spinal surgery, post-operative surgical site infections (SSIs) are a rare, yet morbid complication. This paper applied AI to predict SSIs after posterior spinal fusions. 4046 posterior spinal fusions were identified at a single academic center. A Deep Neural Network DNN classification model was trained using 35 unique input variables The model was trained and tested using cross-validation, in which the data were randomly partitioned into training n = 3034 and testing n = 1012 datasets. Stepwise multivariate regression was further used to identify actual model weights based on predictions from our trained model. The overall rate of infection was 1.5 %. The mean area under the curve (AUC), representing the accuracy of the model, across all 300 iterations was 0.775 (95 % CI [0.767,0.782]) with a median AUC of 0.787. The positive predictive value (PPV), representing how well the model predicted SSI when a patient had SSI, over all predictions was 92.56 % with a negative predictive value (NPV), representing how well the model predicted absence of SSI when a patient did not have SSI, of 98.45 %. In analyzing relative model weights, the five highest weighted variables were Congestive Heart Failure, Chronic Pulmonary Failure, Hemiplegia/Paraplegia, Multilevel Fusion and Cerebrovascular Disease respectively. Notable factors that were protective against infection were ICU Admission, Increasing Charlson Comorbidity Score, Race (White), and being male. Minimally invasive surgery (MIS) was also determined to be mildly protective. Machine learning and artificial intelligence are relevant and impressive tools that should be employed in the clinical decision making for patients. The variables with the largest model weights were primarily comorbidity related with the exception of multilevel fusion. Further study is needed, however, in order to draw any definitive conclusions.