Health care is one of the prominent industries that generate voluminous data, thereby finding the need for machine learning techniques with big data solutions. The goal of this paper is to (i) compare the performance of the six different machine learning techniques in spark platform specifically for health big data and (ii) discuss the results from the experiments conducted on datasets of different characteristics, thereby drawing inferences and conclusion. Five benchmark health datasets are considered for experimentation. The metric chosen for comparison is the accuracy, and the computational time of the algorithms and the experiments are conducted with different proportions of training data. The experimental results show that the logistic regression and random forests perform well in terms of accuracy and naive Bayes outperforms other techniques in terms of computational time for health big datasets. © Springer Nature Singapore Pte Ltd. 2019.