This article shows the use of machine learning to predict the occurrence of deaths in the areas most affected by covid-19 in Peru, where the records of deaths during the pandemic are found reflecting the damage caused by this pandemic, according to a MINSA report in a standard format for analysis that contains all the detailed information of each person. The machine learning procedure is a method of data analysis that automates the construction of analytical models in which we will apply the decision tree where we will use the Python programming language to make the predictions of the deaths caused by covid-19 in the departments, and it will also help us to train the model for greater accuracy in obtaining expected results. In such a way, it can elaborate scenario predictions or initiate operations that are the solution for a specific task. As a case study, it was carried out in the 25 departments of Peru to analyze the departments with the highest mortality rates in our country. As a result of the study were that the departments of Lima, Piura, Huánuco, Ica have the highest rate of deaths by covid-19; this may be due to the biosecurity measures and social distancing; it is worth mentioning that to date they are the departments that have had more policy interventions in recent years. The results of this study may help the authorities to create prevention and sanitary control strategies by implementing rigorous measures in Peru.