dummyML: Automated tabular data analysis pipelines for non-experts (Preprint)

UNSTRUCTURED Health researchers and healthcare professionals are interested in exploring predictive analytics and machine learning applications of health data but were challenged by accessing software programming expertise and dealing with the complexity of carrying out machine learning based predictive analysis (e.g., prediction of a future outcome at the individual level). We present an automated machine learning analytical pipeline dummyML, a free and open-source tool designed to reduce the burden of conducting exploratory machine-learning data analysis on tabular data (e.g., data organized into a table, in which information is arranged in rows and columns), for non-experts, and to facilitate meaningful variable explanation.