Before long, parents will plan for their kids future by selecting which genes they end up with. And when people do get sick, there will be no more trial-and-error prescribing to isolate the drugs that are effective at combating the disease without bringing on debilitating or deadly side effects. Life expectancy will increase, and so will the overall quality of life.
Much of the work that will lay the foundation for this certain future is already taking place, playing out in clinical trails and laboratories throughout the country.
To help us make sense of the latest developments in medical science springing from the field of data science, we were fortunate enough to be able to sit down for a chat with Dr. Bhushan Kapoor, an early pioneer in the field and current chairman of the Department of Information Systems and Decision Sciences at Cal State-Fullerton. Dr. Kapoor offers his thoughts on what the new data revolution has done for personalized medicine and genomics, and where the field is heading.
Pre-Selecting a Cure Before The Disease Ever Happens
Your DNA contains six billion pairs of different combinations of four nucleotides, and these nucleotide combinations make up thousands of genes. The genes in a DNA chain code for certain traits like eye or hair color. Likewise, different genes at different locations in your DNA chain code for genetic disorders as well as how you respond to different drug treatments.
The problem is, for the most part we currently don’t know which genes code for which genetic disorders, and how those genes impact the types of responses a person will have to a certain medicine.
And to exponentially increase the difficulty of making sense of all that, there is no such thing as a one size fits all genetic solution, which is really the point. You need to account for the fact that every genetically unique individual has a different response.
The daunting task of making sense out of all these variables is something that just begs for some serious data mining, scrubbing and prescriptive analytics. Dr. Kapoor explains how this is possible:
“When you have all that information together and you have billions of records, you’re able to parse together and see which particular gene may or could have your certain disease, and then we see what kind of medicines have worked and not worked. So that’s where the big data comes in. When you have granular-level data on patients – on their DNA – and on the history of the disease they have, and the medicines they’ve taken, and their whole lifestyle, you can instantly put all that together and that’s where we can do wonders. Doctors may be able to tell you, you’re likely to get such-and-such a disease in the future with your particular DNA, and pre-select a cure for that.”
Doctors can already pre-screen patients for some genetic risks based on their DNA. By applying data science to medicine this capability will dramatically increase with huge implications for preventative procedures and screenings. And by pinpointing what treatments work best for people with certain configurations of DNA, doctors will also be able to identify effective treatments much faster, potentially even eliminating the need for individual trial-and-error drug calibration.
Mountains of Data from Genetic Testing Aids in Risk Evaluation
Heart disease kills some 600,000 – 700,000 American each year, and Harvard Medical School found that most of these cases of coronary artery disease have a genetic link.
Using a procedure that has identified 57 locations on the DNA chain as being indicators for an increased risk of heart disease, doctors and researchers at the Massachusetts General Hospital have recently developed a genetic-based evaluation that scores individuals on their chances for developing heart disease.
So far this probability score has been more accurate for predicting heart attacks than family history evaluations. It has identified variants in genes that were previously not associated with cardiovascular disease.
Those factors alone will have a significant impact on treating people with the highest genetic risk for developing heart disease. That’s because research has also shown that preemptively administering cholesterol-lowering statins to people in this category can reduce their risk of heart attack by 40 percent for every 40 milligrams-per-deciliter drop in cholesterol.
But here is the catch: unless you are one of the 9,500 people who took part in this recent research you’re not a candidate for this kind of genetic risk evaluation – it’s not ready for prime time. And there’s more. Most of the people who participated in this research were of European descent; whether or not there is a correlation with other genetic pools remains to be determined.
The kind of breakthroughs in genetic risk evaluation that will be achieved through the application of data science to genetic research will revolutionize medicine forever. And as we get closer to being capable of performing this kind of genetic analysis on millions of people, the revolution could be closer than you might think.