116. Comparison of imputation methods for evaluating long-term clinical outcomes following lumbar total disc replacement

Abstract

BACKGROUND CONTEXT The problem of missing data is common in clinical trials, and it can have a significant impact on the conclusions that can be drawn from the data. Long-term results are particularly susceptible as the lost to follow-up (LTFU) rates increase over the course of a trial. Imputation methods are often used to account for missing data points, but some may either under or overestimate the true treatment effect. PURPOSE In this post-hoc analysis of a randomized clinical trial, we evaluated the clinical success of three motion preserving artificial discs up to 7 years following lumbar total disc replacement (TDR) using different imputation methods. STUDY DESIGN/SETTING Randomized, controlled, multicenter clinical IDE trial. PATIENT SAMPLE A total of 324 subjects with single level degenerative disc disease and discogenic pain. OUTCOME MEASURES Radigraphic range of motion on flexion-extension, Oswestry Disability Index (ODI), neurologic exam, adverse events, subsequent surgery. METHODS Subjects were randomized to receive either a semi-constrained mobile core disc (n=218) or a control device (n=106) which was either a constrained (n=65) or unconstrained (n=41) core disc. Several imputation methods were used to calculate clinical success, including: missing values=failure, missing values=success, last observation carried forward (LOCF), complete case, best case and worst case scenarios. Clinical success scores were compared between the treatment (semi-constrained) and control (constrained or unconstrained) groups.Clinical outcomes were collected from baseline through to 7 years following single level (L4-L5 or L5-S1) TDR. Clinical success was defined as a ≥15 point improvement in ODI from baseline, maintenance or improvement in ROM and neurological evaluation (motor and sensory), the absence of index-level subsequent surgical interventions (SSI) and serious device-related adverse events (SDAE). RESULTS By imputing missing values as failures, individual success scores decreased at 5 and 7 years compared to 2 years postop for both groups. Only ROM success at 2 years was significantly greater in the treatment compared to control group (58.7% vs 42.5%, p=0.0065). The overall success score, which is a composite of the individual success scores, also decreased over time, but it was significantly greater in the treatment group at 2 years (42.2% vs 28.3%, p=0.0020). Using complete case data, clinical success at 5 and 7 years was maintained close to 2-year values for overall and individual success scores, except for SDAE success which decreased at 7 years from 2 years for both the treatment (86.1% to 67.1%) and control groups (78.7% to 63.2%). Similarly, LOCF clinical outcomes were the same between 5 and 7 years postop for both groups. By imputing missing values as successes, the results were comparable to scores yielded by complete case and LOCF imputation methods. CONCLUSIONS The missing=failure imputation method is most susceptible to LFTU and may underestimate the treatment effect if there is a large LTFU rate, which is inherent in most long-term clinical studies. Complete case and LOCF imputation methods may be more accurate estimates of long-term clinical outcomes for clinical studies with a large patient enrollment. FDA DEVICE/DRUG STATUS This abstract does not discuss or include any applicable devices or drugs.