Data Science for Medical Professionals

In the last few years, Big Data, Data Science, Machine Learning, and Artificial Intelligence have become increasingly more popular in the healthcare sector. Predicting acute kidney injury after intravenous contrast injection two days before it occurs (Koyner et al.) and predicting cardiovascular risk factors solely from retinal exams (Poplin et al.) are some of the exciting uses of machine learning and deep learning algorithms in medicine. Its applications also extend to emergency department operations including flow management, quality control, and identification of at-risk patients. While software engineers, data scientists, and technologists are driving the majority of the innovations, the majority of physicians are unaware of its most basic concepts. Given that clinicians are the core of healthcare, there is a tremendous need for well-versed and technically savvy clinicians to be forefront leaders for healthcare innovation. This workshop aims to educate physicians, regardless of their technical background, and to develop a general understanding of data science and its implementation in medicine via live coding demonstration. At the end of the workshop, learners will understand how the principles of data science and machine learning can be used to solve common problems encountered by Emergency Departments.

 

Upon completion of this session, participants should be able to:

1. Discuss the most common concepts of data science and machine learning in medicine.

 2. Program in the basics of Python, a popular programming language in data science, and implement its most common visualization, statistical, and machine learning packages.

 3. Demonstrate familiarity with the current industry trends in data science and healthcare.

 4. Identify problems and projects that are suitable for the application of data science and machine learning.

 References

 1. Koyner JL, Carey KA, Edelson DP, Churpek MM. The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model*. Critical Care Medicine. 2018;46(7):1070-1077. doi:10.1097/ccm.0000000000003123.

Course Instructor: Dr. Joel Park


 

2. Poplin R, Varadarajan AV, Blumer K, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomedical Engineering. 2018;2(3):158-164.

doi:10.1038/s41551-18-0195-0.