Artificial intelligence (AI) has been one of the biggest stories in healthcare for years, but many clinicians still remain unsure about how, exactly, they should be using AI to help their patients. A new analysis in European Heart Journal explored that exact issue, providing cardiology professionals with a step-by-step breakdown of how to get the most out of this potentially game-changing technology.
The detailed assessment represents a collaboration between the cardAIc group, a team of data specialists from the University of Birmingham in the U.K, and the BigData@Heart Consortium, a five-year project focused on using advanced algorithms in personalized medicine.
“AI approaches have been developed in short order to deal with large or complex data sets, but a lack of transparency and understanding by health professionals has restricted their application and ability to impact patient management,” wrote corresponding author Dipak Kotecha, MBChB, PhD, a cardiologist with the University of Birmingham and Utrecht University in the Netherlands, and colleagues. “In this article, we summarize the what and why of applying AI techniques to health data … this framework for AI is designed to build a stronger foundation for collaboration between physicians and health data scientists, providing better understanding that can improve study design and clinical value.”
Kotecha et al. shared 4 key steps that healthcare researchers need to develop high-quality AI algorithms.
Step 1: Design your AI study and select your data
This first step involves making several decisions that will guide the rest of the development process. What questions are you hoping to answer? What kind of data do you want? Where will the data come from? What are some of the underlying biases that need to be addressed?
The choices made during this step, the authors noted, will impact every other step. If you decide to focus on unstructured data, for example, it may require pre-processing that would not be necessary if your team was only using structured data.
Step 2: Pre-processing your data to avoid AI Biases
“Underlying biases in the data need to be explored, and then the data transformed into usable formats for machine-learning algorithms,” the authors wrote. “The output of any AI model is only as good as its input; therefore, pre-processing is a critical step to plan a study and understand its findings.”
During this step, researchers should also check for any missing or incomplete data. If some data do appear to be missing, it is important to determine if it is at random or the sign of a significant trend.
Step 3: Select the right machine-learning approach for your study
Different AI algorithms can perform different tasks. Are you providing the AI with human-derived data and looking for an accurate prediction? Are you teaching the AI how different variables are related to one another? This will help determine which approach is the best fit for your analysis.
Decision trees, random forests, deep neural networks, convolutional neural networks and auto encoders are just some of the algorithm types researchers have at their fingertips. Of course, each one has its own advantages and disadvantages—and there will only be more and more options as time goes on.
Step 4: Validate and evaluate your method and your results
It all comes down to this crucial part of the process—grading the effectiveness of your team’s AI algorithm.
“Appropriate validation is needed in order to know how the study findings will apply to the real world,” the authors wrote. “The importance of evaluating machine-learning output is no different from any other prediction task, and there remain challenges in generalizing from one data set to another, and then again to actual clinical practice. External validation should be the default approach for all AI studies, and usually involves estimating performance on completely unseen data. A gold-standard method is to apply a learned model to one or more data sets originating from a different cohort or study, preferably from a different site or time interval.”
This is when researchers measure their algorithm’s accuracy, sensitivity, specificity and other performance metrics. In addition, it is another opportunity to consider any potential biases.
“The explainability of AI approaches is of substantial interest in healthcare,” the authors wrote. “Commonly, AI approaches outperform human experts in specialized tasks, yet they do not give a reason for a particular prediction. Underlying biases in the data might lead to misclassification, and so caution must be used when interpreting AI approaches if they influence the care of patients.”
Read the full analysis, including several examples of high-quality AI in action, in European Heart Journal here.
Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.