Abstract
Introduction
Proximal Junction Failure (PJF) and Proximal Junction Kyphosis (PJK) are significant complications. It remains unclear what are the specific drivers behind the development of either. This study attempts to develop a preoperative predictive model to identify patients at risk to develop PJF or PJK.
Material and Methods
Inclusion criteria: age ≥18, adult spinal deformity (ASD), ≥4 levels fused. Variables included in the model were: demographics, primary/revision, use of 3-column osteotomy, UIV/LIV levels and anchor (screw, hooks), number of levels fused, and baseline sagittal radiographs (PT, PI, PI-LL, TK, and SVA). PJF was defined as requiring revision for PJK and PJK was defined as an increase from baseline of PJK > 20° and with deterioration by at least 1 SRS-Schwab sagittal modifier grade from 6wks postop. An ensemble of decision trees were constructed using the C5.0 algorithm with 5 different bootstrapped models, and internally validated via a 70:30 data split for training and testing. Accuracy and the area under a receiver operator characteristic curve (AUC) were calculated. Final model utilized 13 preoperative variables.
Results
510 patients were included, with 357 for model training and 153 as testing targets (PJF: 37, PJK: 102). The overall model accuracy was 86.3% with an AUC of 0.89 indicating a good model fit. The 6 strongest (importance ≥0.95) predictors were (% target): age (>64yrs, 41.4%), PI-LL (>48.7deg, 35.6%), UIV (T10-L3, 35.1%), SVA (>13.5cm, 32.5%), LIV (sacroiliac, 31.6%), and UIV Type (screws, 29.8%). If a patient met these criteria, they had a 66.7% chance of developing PJF or PJK with deterioration of sagittal alignment.
Conclusion
A successful model (86% accuracy, 0.89 AUC) was built predicting either PJF or clinically significant PJK. This model can set the groundwork for preoperative point of care decision making, risk stratification, and need for prophylactic strategies for patients undergoing ASD surgery.