This paper discusses the usage of time series analysis for the early detection of Amyotrophic Lateral Sclerosis (ALS). A time series approach was used to expand a set of rules that may detect the early stages of ALS via analyzing symptomatic changes in signs and symptoms consisting of muscle energy, taking walks potential, speech, swallowing, and different bodily motion. This technique become examined on a retrospective dataset, and proven if you want to come across changes in the circumstance of ALS in a well-timed way. The outcomes suggest that this technique has ability as a tool for early detection in ALS sufferers. The proposed algorithm ought to potentially be used to improve the present day standard of care and help lead to in advance analysis and higher scientific effects.