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

Keywords

• Medical data informatics
• Electronic health records
• Data science
• EDA
• Reproducible research

References

1. [1] Aggarwal, A. K. (2019). Opportunities and challenges of big data in public sector. In Web services: Concepts, methodologies, tools, and applications (pp. 1749-1761). IGI Global. doi: 10.4018/978-1-4666-9649-5.ch016
2. [2] Oussous, A., Benjelloun, F. Z., Lahcen, A. A., & Belfkih, S. (2018). Big Data technologies: A survey. Journal of King Saud University-Computer and Information Sciences, 30(4), 431-448. doi: 10.1016/j.jksuci.2017.06.001
3. [3] Shen, H. (2014). Interactive notebooks: Sharing the code. Nature, 515(7525), 151-152. doi: 10.1038/515151a
4. [4] Kluyver, T., Ragan-Kelley, B., Pérez, F., Granger, B. E., Bussonnier, M., Frederic, J., ... & Ivanov, P. (2016, May). Jupyter Notebooks-a publishing format for reproducible computational workflows. In ELPUB (pp. 87-90). doi:10.3233/978-1-61499-649-1-87
5. [5] McKinney, W. (2011). pandas: a foundational Python library for data analysis and statistics. Python for High Performance and Scientific Computing, 14(9).
6. [6] Hunter, J. D. (2007). Matplotlib: A 2D graphics environment. Computing In Science Engineering 9, 3. 90-95. doi: 10.1109/MCSE.2007.55
7. [7] Embarak, O. (2018). Data Visualization. In Data Analysis and Visualization Using Python (pp. 293-342). Apress, Berkeley, CA. 10.1007/978-1-4842-4109-7_7
8. [8] Cuttone, A., Lehmann, S., & Larsen, J. E. (2016). geoplotlib: a Python Toolbox for Visualizing Geographical Data. arXiv preprint arXiv:1608.01933.

9. [9] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Vanderplas, J. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
10. [10] Leung, C. K. S. (2019). Big data analysis and mining. In Advanced Methodologies and Technologies in Network Architecture, Mobile Computing, and Data Analytics (pp. 15-27). IGI Global. doi: 10.4018/978-1-5225-2255-3.CH030
11. [11] Loper, E., & Bird, S. (2002). NLTK: the natural language toolkit. arXiv preprint cs/0205028.
12. [12] Saleiro, P., Kuester, B., Hinkson, L., London, J., Stevens, A., Anisfeld, A., ... & Ghani, R. (2018). Aequitas: A bias and fairness audit toolkit. arXiv preprint arXiv:1811.05577.
13. [13] Detrano, R., Janosi, A., Steinbrunn, W., Pfisterer, M., Schmid, J. J., Sandhu, S., ... & Froelicher, V. (1989). International application of a new probability algorithm for the diagnosis of coronary artery disease. The American journal of cardiology, 64(5), 304-310. doi: 10.1016/0002-9149(89)90524-9
14. [14] Strzelecki, M., Szczypinski, P., Materka, A., & Klepaczko, A. (2013). A software tool for automatic classification and segmentation of 2D/3D medical images. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 702, 137-140. doi: 10.1016/j.nima.2012.09.006
15. [15] de Vos, B. D., Wolterink, J. M., de Jong, P. A., Viergever, M. A., & Išgum, I. (2016, March). 2D image classification for 3D anatomy localization: employing deep convolutional neural networks. In Medical imaging 2016: Image processing (Vol. 9784, p. 97841Y). International Society for Optics and Photonics. doi: 10.1117/12.2216971
16. [16] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
17. [17] Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., ... & Seekins, J. (2019, July). Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, pp. 590-597). 10.1609/aaai.v33i01.3301590