AI predicts who would benefit from high blood pressure treatment

High blood pressure(hypertension) is a common disease in which blood flows through blood vessels, or arteries, at higher than normal pressures. i.e. systolic blood pressure is consistently higher than 140 mmHg and diastolic blood pressure is consistently higher than 90 mmHg.  Hereditary, obesity, sedentary lifestyle, increased salt intake, etc are some of the known risk factors of high blood pressure.

Having high blood pressure puts you at risk for heart disease and stroke, which are leading causes of death worldwide. High blood pressure usually does not have any symptoms untill the complications occur. The complications of high blood pressure is usually fatal and disabling.

AI helps in high blood pressure treatment
Source: American Heart Association
For most people with high blood pressure, a doctor will develop a treatment plan that may include heart-healthy lifestyle changes alone or with medicines. Heart-healthy lifestyle changes, such as heart-healthy eating, can be highly effective in treating high blood pressure. The absolute risk reduction (ARR) in cardiovascular events from therapy is generally assumed to be proportional to baseline risk—such that high-risk patients benefit most. But now the AI researchers have shown that the Machine Learning methods can be used for better individualizing treatments regardless of their risk profiles. 

In an article published in American Heart Association journals, instead of giving every patient of the high blood pressure the same treatment, the practitioner can use Machine Learning(AI) to predict who would benefit from high blood pressure treatment and who wouldn't. This is surely going to reduce unnecessary medications for a lot of patients. Moreover, patients will get medications that are best suited for them. This is going to be a landmark in the future of patient-centered individualized treatment.

Few excerpts from their research paper,
Predictions for individual treatment effects from trial data reveal that patients may experience absolute risk reduction (ARRs) not simply proportional to baseline cardiovascular disease risk. Machine learning methods may improve discrimination and calibration of individualized treatment effect estimates from clinical trial data.

Read the full article here at  https://www.ahajournals.org/doi/full/10.1161/CIRCOUTCOMES.118.005010

Comments

Popular posts from this blog

Using torrent on iPad or iPhone without any extra apps or tools for free

How to download all your college and other textbook pdfs for free?

A simple explanation of Artificial Intelligence for people not belonging to the tech sector.