Can Machine Learning Step up to Predict Heart Diseases?
Is it possible to detect the factors that can trigger heart diseases in the future?
Machine learning is a subset of Artificial Intelligence that primarily focuses on analyzing data to interpret patterns. And the healthcare industry is one of the sectors that generate an enormous amount of data every year, from patient records to medicine stock supplies, and more. Now researchers are hoping to use this healthcare data to predict diseases and in timely prevention of the same. Hence currently, many research projects are experimenting on ways to mine data that shall allow physicians to prevent life-threatening diseases.
Earlier, they used to predict a disease by using risk calculators and mathematical equations and studying information such as medical conditions and life routines. Though such methods resulted in low accuracy, now machine learning can help improve such predictions by a higher margin. Out of all the diseases man can face in his lifetime, heart diseases are too difficult to predict. And by heart disease, we mean a range of different conditions that could affect one’s heart. Hence, identifying the factors that may aggravate it, and predicting those beforehand poses plenty of challenges for researchers and physicians. This why machine learning has been proposed for cardiac imaging applications like automated computation of scores, differentiation of prognostic phenotypes, quantification of heart function, and segmentation of the heart. These tools have also demonstrated the capability of performing early and accurate detection of anomalies in electrocardiographic exams. AI can also help in the genomic assessment of cardiovascular diseases and contribute to cardiovascular risk assessment in different settings. A research study has discovered that neural network classifiers could facilitate the detection of patterns of congestive heart failure on chest radiographs.
Last year, a team of researchers from Brigham and Women’s Hospital and UT Southwestern Medical Center developed a machine learning model that can accurately predict heart failure among patients with diabetes. Named WATCH-DM, the model evaluated clinical information, laboratory data, and demographics and found 147 variables that would accurately predict heart failure risk from a data set pooled from 8,756 patients with diabetes. The team observed that patients with the highest WATCH-DM risk scores faced a five-year risk of heart failure approaching 20 percent. This year, AstraZeneca teamed up with eko.ai to develop AI software to help cardiologists better diagnose heart failure patients through echocardiography.
All these initiatives can help to reduce the statistics of annual deaths due to cardiovascular or similar heart-related diseases. According to a recent update from the CDC, one person dies every 36 seconds in the United States from cardiovascular disease. Also, heart disease costs the United States about US$219 billion each year from 2014 to 2015.