Pitfalls to Avoid with Machine Learning in Healthcare

Abstract

In this chapter I am going to share my experience and knowledge that I have gathered over the years in building both machine learning and non-machine learning applications. The main objective of this chapter is to make you aware of the common miss that people make when implementing machine learning in their business environment. I will be highlighting some of the pitfalls that the machine learning teams and organizations who are implementing machine learning need to avoid. You may have come across these in your work environment, or some of them may be new to you; however, this scenario that I give from my experience is something that you will cherish and we’ll know an expert opinion on how to avoid these issues. From that perspective I would like you to read all of the six pitfalls that I talked about in this chapter. I will be using and giving various examples from my experience without naming the clients to maintain anonymity as to how, when the teams did not focus on these principles, it led to the project either being delayed or terminated. In my capacity of having worked as a program and project manager for more than 17 years, I cannot stress enough on the fact that if you do not follow these principles, your machine learning project is also bound to fail.