Explainable Random Forest Predicts Adjacent Segment Degeneration After Lumbar Fusion

An externally validated random forest model predicted radiographic adjacent segment degeneration after short-segment lumbar fusion (AUROC 0.782 internal test, 0.749 external). Five perioperative variables were integrated; preoperative intervertebral space height was the stronges…

• Model integrates preoperative intervertebral space height, postoperative PI-LL mismatch, frailty, Coflex implantation, and WOMAC lower-extremity dysfunction.
• Among logistic regression, random forest, XGBoost, LightGBM, and multilayer perceptron, random forest achieved the highest discrimination.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.