Medical Data Analysis for Different Data Types

Abstract

Many discoveries and decisions in science are now being made on the basis of analyzing datasets. To gain useful information from raw medical data, data analytic uses insights to benefit the entire lifecycle of medical data. In this paper, medical data analysis notebooks are presented for collaborative and reproducible research. They provide a broad and practical introduction to medical data analysis with different data types such as images and texts. We aim to provide Jupyter notebooks to help those new to the medical data analysis field. Three exploratory coding activities including different data types are introduced: (i) Building, evaluating and interpreting deep learning models with EHR data, (ii) 2D mammogram medical imaging data analysis using CNNs for dense breasts classification, and (iii) Label recognition in radiology reports. Jupyter notebooks are useful for learning how to analyze different medical datasets and identify patterns that will improve any hospitals’ and clinicians' computer-aided medical decision-making process. Leveraging advances in exploratory data analysis in healthcare requires collaboration between clinicians and data scientists