The growth of computing techniques has reduced the complications in handling medical and healthcare data for optimal processing. We modeled the infectious disease cryptosporidiosis, which is a parasitic disease, to inform the management of its spread. We used a cohesive prediction model (CPM) for analyzing the nature of the cryptosporidiosis disease through a series of observed data. In this prediction model, the disease's characteristics and its attributes were used to predict its nature over a specific period. The prediction model relies on the attributes of cryptosporidiosis diseases and its adverse effects from its time of emergence. The attributes and recurrent cryptosporidiosis disease data are analyzed using Naive Bayes classification learning. The time recurrence data of cryptosporidiosis disease is predictively handled using prior classifications and validations of the analysis's new attributes. Using this information, the predictive model maps all possible attributes of the cryptosporidiosis disease in time recurrence. The experimental results showed that the suggested system was validated by datasets from the European Centre for Disease Prevention and Control, with an accuracy ratio of 95.55%, the sensitivity of 94.10%, and specificity of 94.89% in predicting and modeling the attributes of cryptosporidiosis disease.