This research proposes a multi-level predictive algorithm based on the k-means algorithm with multiple adaptations. The research highlights the main limitations of k-means and proposes a set of adaptations that enhance the clustering task results in accuracy with minimal centroid distance error. The study proposes three enhancements in selecting the number of clusters, identifying the initial point, and exploring the contributing features set. Moreover, prediction is performed through a multi-level paradigm targeting performance enhancement by following the partitioning approach. The research experimental study focused on applying the proposed algorithm to the healthcare supply chain as it is one of the most influential factors for health services delivery. The proposed algorithm is applied to a dataset that is offered by USAID which includes 31622 records with 104 attributes. The proposed algorithm aims to predict the valued information in the supply chain progress such as predicted delivery time, predicted delay time, and other vital attributes. The data source is the USAID dataset; however, the research utilized the dataset for multiple objectives in vital aspects prediction of the healthcare supply chain with an average accuracy of 97.45%.