Due to long time to get failure data in a short-time testing or even an accelerated testing conditions, light emitting diodes (LEDs) are suffering from reliability prediction problems. In the past few years, data driven approaches based on degradation data have been found interesting for degradation modeling and remaining useful lifetime (RUL) prediction of highly reliable products such as LEDs. However, many of these approaches have been implemented based on deterministic regression approaches that couldn't handle diffusion properties and increase prediction uncertainties. In this paper, a Wiener process based method is used to model the lumen degradation and estimate the RULs of LEDs. Based on the maximum likelihood estimation, a model used to predict RUL from a degradation data has been developed. The effectiveness of proposed model for lifetime prediction is validated by using the simulation and demonstrated with the lumen flux degradation data for LEDs. The result shows that the Wiener process based method can help to estimate lifetime with better accuracy when compared to the IES-TM-21 standard with the nonlinear regression approach.