Along with other single imputation methods (simple median/mean, regression mean, minimum or maximum), LOCF is often criticized for its statistical shortcomings to handle missing data in clinical trials (e.g., under-estimated variance and biased estimate). In this talk, I would like to present a case study involving an orthopedic implant, in which the strong assumption for LOCF may be reasonable for certain patients who missed the final primary evaluation at 2 years post-operation, and thus be served as an valuable approach along with other approaches (e.g., multiple imputation assuming missing at random). I will also emphasize that, within a single trial, patients with missing data due to different known reasons could be classified into several categories of most plausible missing mechanisms with clinical input and handled with different approaches accordingly (i.e., not necessary treat all missing data uniformly using either LOCF or multiple imputation).