Fuzzy Logic in neurosurgery: predicting poor outcomes after lumbar disk surgery in 501 consecutive patients

Abstract

Background: Despite a lot of research into patient selection, a significant number of patients fail to benefit from surgery for symptomatic lumbar disk herniation. We have used Fuzzy Logic-based fuzzy inference system (FIS) for identifying patients unlikely to improve after disk surgery and explored FIS as a tool for surgical outcome prediction.

Methods: Data of 501 patients were retrospectively reviewed for 54 independent variables. Sixteen variables were short-listed based on heuristics and were further classified into memberships with degrees of membership within each. A set of 11 rules was formed, and the rule base used individual membership degrees and their values mapped from the membership functions to perform Boolean Logical inference for a particular set of inputs. For each rule, a decision bar was generated that, when combined with the other rules in a similar way, constituted a decision surface. The FIS decisions were then based on calculating the centroid for the resulting decision surfaces and thresholding of actual centroid values. The results of FIS were then compared with eventual postoperative patient outcomes based on clinical follow-ups at 6 months to evaluate FIS as a predictor of poor outcome.

Results: Fuzzy inference system has a sensitivity of 88% and specificity of 86% in the prediction of patients most likely to have poor outcome after lumbosacral miscrodiskectomy. The test thus has a positive predictive value of 0.36 and a negative predictive value of 0.98.

Conclusion: Fuzzy inference system is a sensitive method of predicting patients who will fail to improve with surgical intervention.