Healthcare Big Data-When it comes to medicine there are constant discoveries and advancements in the field. Now with the help of machine learning algorithms, personalized medicine and predictive patient outcome has taken another step towards curing diseases.
With the data collected from patients, researchers are able to study different diseases and try to find better treatments and even cures. Scientists and pharmaceutical companies are able to use bioinformatics to develop new treatments and discover cures and treatments for diseases that currently do not have them. The benefit to using so much data is the ability to determine why some drugs worked for a population versus not for others.
A recent study found that the blood thinner clopidogrel, or Plavix, doesn’t work in the 75% of Pacific Islanders whose bodies don’t produce the enzyme is bringing a paradigm shift to healthcare, powered by increasing availability of healthcare data and rapid progress of analytics techniques required to activate the drug. By using algorithms, researchers can determine areas that certain drugs may work and where they may not.
A new computer program developed at the University of Arizona College of Medicine is able to personalize drug treatments for patients using genetic information. The program is licensed to INTelico Theraputics, LLC, a startup in Arizona and uses genetic information from millions of patients to predict the effects of drug therapy that is personalized to each individual using their specific genetic makeup.
The algorithm was created by Rui Chang, Associate Professor of Neurology, and Eric Shadt, Dean for Precision Medicine at the Icahn School of Medicine at Mount Sinai. It uses big data from large patient populations and a variety of sources such as DNA and RNA sequencing, proteomics, metabolomics and epigenetics. They use that data to then compare it to historic groups of those who have been diagnosed and treated for diseases and determine the course of treatments that will likely have the most effective outcome for the patient.