Pragmatic Prediction of Excessive Length of Stay After Cervical Spine Surgery With Machine Learning and Validation on a National Scale

Abstract

BACKGROUND: Extended postoperative hospital stays are associated with numerous clinical risks and increased economic cost. Accurate preoperative prediction of extended length of stay (LOS) can facilitate targeted interventions to mitigate clinical harm and resource utilization. OBJECTIVE: To develop a machine learning algorithm aimed at predicting extended LOS after cervical spine surgery on a national level and elucidate drivers of prediction. METHODS: Electronic medical records from a large, urban academic medical center were retrospectively examined to identify patients who underwent cervical spine fusion surgeries between 2008 and 2019 for machine learning algorithm development and insample validation. The National Inpatient Sample database was queried to identify cervical spine fusion surgeries between 2009 and 2017 for out-of-sample validation of algorithm performance. Gradient-boosted trees predicted LOS and efficacy was assessed using the area under the receiver operating characteristic curve (AUROC). Shapley values were calculated to characterize preoperative risk factors for extended LOS and explain algorithm predictions. RESULTS: Gradient-boosted trees accurately predicted extended LOS across cohorts, achieving an AUROC of 0.87 (SD = 0.01) on the single-center validation set and an AUROC of 0.84 (SD = 0.00) on the nationwide National Inpatient Sample data set. Anterior approach only, elective admission status, age, and total number of Elixhauser comorbidities were important predictors that affected the likelihood of prolonged LOS. CONCLUSION: Machine learning algorithms accurately predict extended LOS across single-center and national patient cohorts and characterize key preoperative drivers of increased LOS after cervical spine surgery.

Using Machine Learning and Deep Learning Algorithms to Predict Postoperative Outcomes Following Anterior Cervical Discectomy and Fusion

“…In our analysis of extended LOS, RF had a higher average AUC of 0.74, which could be attributed to our more robust set of patient features, including medical and surgical history, along with several lab values. In another study looking at extended LOS, Valliani et al 13 studied cervical fusion patients from a single institution to develop a predictive ML model. Subsequently, they attempted to externally validate the model using a national data set and found good applicability with their gradient boosted trees model with an AUC of 0.87 on the test set from the single center and an AUC of 0.84 on the external data set.…”

Machine Learning in Spine Surgery: A Narrative Review

“…Predicting LOS, hospital discharge time, and medical costs is crucial for proper management of patient and hospital resources. 93 ML can utilize intraoperative surgical details and a patient's socioeconomic factors to predict inpatient LOS. [94][95][96][97][98] This was performed in a 63 533-patient cohort after anterior lumbar and posterior lumbar interbody fusion, transforaminal lumbar interbody fusion, and posterior spine fusion.…”