Data science in medicine

In recent years, there has been an increase in the use of applications, tools and solutions that use machine learning in the field of medicine. The solutions cover disease prediction, imaging analysis to filter or select relevant conditions and even provide additional information for clinicians to make better decisions.

In this text, I will share a data science solution that has a component of machine learning carried out in Spain. The purpose of this mechanism is to filter out relevant cases so that cardiologists can make better use of their time and expertise.

An echocardiogram is similar to an ultrasound: it is a non-invasive study that measures the strength, size, and shape of the heart to identify or rule out different conditions in a particular patient. To determine the ejection force of the heart, it is necessary to determine its four chambers, calculate their volume, divide and / or define.

The cardiologist is the only person responsible for performing and analyzing the echocardiogram, through a two-stage process: taking the echocardiogram in the presence of the patient and analyzing it. The first stage takes about 30 minutes or more, depending on the age of the patient; The second takes 20 minutes per study. However, it may take up to two days for the results to be delivered due to the workload of cardiologists.

Additionally, it is common for a cardiologist to spend about three hours a day sitting in front of a computer identifying objects in the image for segmentation. A segmentation error refers to an error in calculating the volume, in the force of the ejection and possibly in determining whether or not there is a problem with the core.

See also  It's not water: Scientists explain the truth about Martian subterranean lakes | technology

Solution machine learning The proposal focuses on the ability to identify and map the four chambers of the heart, as well as calculate the volume and ejection force to generate a recommendation as to whether it is necessary for a cardiologist to review the case, either because the model has doubts about it. Whether there is a problem – because of the value of the ejection force produced – or because the model is certain that the study should be reviewed by a cardiologist.

This model facilitates the automated process of cavity determination and segmentation, so that we can later generate a volume and ejection force calculation. So this simple solution allows cardiologists to free up hours so they can care for more patients, make better use of their expertise and invest that time doing what they’re passionate about. This example shows that using AI with proper planning can have a positive impact on certain areas, such as medicine.

Aileen Morales

"Beer nerd. Food fanatic. Alcohol scholar. Tv practitioner. Writer. Troublemaker. Falls down a lot."

Leave a Reply

Your email address will not be published.

Back to top