Abstract This paper presents the Modified Grey Wolf Optimization (MGWO) algorithm which helps with the identification of the symptoms of Parkinson’s disease at a premature stage. Parkinson disease is kind of a movement malady, which if not cured timely can prove to be fatal. Thus it becomes significant to identify Parkinson’s disease at its premature phase so proper medications can provide longevity to patient by controlling the symptoms. In this work, a new model named Modified Grey Wolf Optimization (MGWO) has been proposed grounded on the traditional Grey Wolf Optimizer (GWO), which acts as a search strategy for feature selection. GWO is a meta-heuristic algorithm which is enthused by hunt down behavior of wolves. Random forest, k-nearest neighbor classifier and decision tree espy on selected features. The proposed model is evaluated using various types of datasets of voice, handwriting (spiral and meander) and speech. The put forward algorithm helps in the prediction of Parkinson disease with an estimated accuracy of 94.83%, detection rate of 98.28%, false alarm rate of 16.03% and further aid the individuals to receive a functional treatment at an early stage. The proposed bio-inspired algorithm is stable enough to find out the optimal subset of features. At last the results derived from the evaluation of proposed algorithm on datasets are compared with the results of Optimized Cuttlefish Algorithm (OCFA). The experimental results depict that the proposed algorithm helps in maximizing the accurateness and minimizing the number of features selected.