Using Machine Learning to Predict Surgical Site Infection After Lumbar Spine Surgery

Tianyou Chen; Chong Liu; Zide Zhang; Tuo Liang; Jichong Zhu; Chenxing Zhou; Shaofeng Wu; Yuanlin Yao; Chengqian Huang; Bin Zhang; Sitan Feng; Zequn Wang; Shengsheng Huang; Xuhua Sun; Liyi Chen; Xinli Zhan

doi:10.2147/IDR.S417431

Using Machine Learning to Predict Surgical Site Infection After Lumbar Spine Surgery

Infect Drug Resist. 2023 Aug 9:16:5197-5207. doi: 10.2147/IDR.S417431. eCollection 2023.

Authors

Tianyou Chen^#¹, Chong Liu¹, Zide Zhang², Tuo Liang², Jichong Zhu¹, Chenxing Zhou¹, Shaofeng Wu¹, Yuanlin Yao^#¹, Chengqian Huang¹, Bin Zhang¹, Sitan Feng¹, Zequn Wang¹, Shengsheng Huang¹, Xuhua Sun¹, Liyi Chen¹, Xinli Zhan¹

Affiliations

¹ Department of Spine and Osteopathy Ward, the First Affiliated Hospital of Guangxi Medical University, Nanning, People's Republic of China.
² Spine Ward, Liuzhou People's Hospital, Liuzhou, People's Republic of China.

^# Contributed equally.

Abstract

Objective: The objective of this study was to utilize machine learning techniques to analyze perioperative factors and identify blood glucose levels that can predict the occurrence of surgical site infection following posterior lumbar spinal surgery.

Methods: A total of 4019 patients receiving lumbar internal fixation surgery from an institute were enrolled between June 2012 and February 2021. First, the filtered data were randomized into the test and verification groups. Second, in the test group, specific variables were screened using logistic regression analysis, Lasso regression analysis, support vector machine, and random forest. Specific variables obtained using the four methods were intersected, and a dynamic model was constructed. ROC and calibration curves were constructed to assess model performance. Finally, internal model performance was verified in the verification group using ROC and calibration curves.

Results: The data from 4019 patients were collected. In total, 1327 eligible cases were selected. By combining logistic regression analysis with three machine learning algorithms, this study identified four predictors associated with SSI, namely Modic changes, sebum thickness, hemoglobin, and glucose. Using this information, a prediction model was developed and visually represented. Then, we constructed ROC and calibration curves using the test group; the area under the ROC curve was 0.988. Further, calibration curve analysis revealed favorable consistency of nomogram-predicted values compared with real measurements. The C-index of our model was 0.986 (95% CI 0.981-0.994). Finally, we used the validation group to validate the model internally; the AUC was 0.987. Calibration curve analysis revealed favorable consistency of nomogram-predicted values compared with real measurements. The C-index was 0.982 (95% CI 0.974-0.999).

Conclusion: Logistic regression analysis and machine learning were employed to select four risk factors: Modic changes, sebum thickness, hemoglobin, and glucose. Then, a dynamic prediction model was constructed to help clinicians simplify the monitoring and prevention of SSI.

Keywords: blood glucose; dynamic prediction model; lumbar spine surgery; machine learning; surgical site infection.