In a subterranean lab at the far corner of Columbia University’s main New York City campus, a couple of men in lab coats and safety glasses discuss a problem in their research. Across the hall, a woman attired similarly is at work in the machine shop. Glassware, chemicals in jugs, tubing and various equipment cover what seems like every corner of bench space.
These people are part of Samuel Sia’s 30-member crack team of chemists, biologists and engineers. Sia, a biomedical engineer, has gathered them together to help foment a medical revolution.
Their idea: to outsource to individuals and family doctors the tests that are now the exclusive domain of centralized labs and hospitals. Their weapons are a new crop of coming diagnostic technologies that are smaller, cheaper and smarter than anything on the market today. Inherent to this change in the business model is the jailbreak of patients’ medical data from healthcare facilities and insurance companies back to the patient and doctor from where it came.
“Whenever we want to know about our own body, we have to go through the healthcare system,” Sia tells Txchnologist. “You shouldn’t have to do that. Are you vitamin deficient? Do you have the flu? Are you trying to get pregnant? What is that new Mediterranean diet doing to your body? You should be able to monitor your own body, but right now it’s out of your hands.”
Researchers have studied the medical histories of the entire population of Denmark to chart how medical conditions are linked and forecast disease before it begins.
In a major advance for the field of biomedical Big Data analytics, scientists followed the medical history of some 6.2 million Danes over the course of almost 15 years. Since the dataset includes those who died in those years, that’s a sample size 600,000 people larger than the current living population of the small Scandinavian country. Using the Danish National Patient Registry, which healthcare providers are required to report to, the data scientists were given access to 65 million inpatient, outpatient and emergency room events from 1996 to 2010.
Over that long study period and with so many data points that included every demographic in the country, they were able to start seeing hidden patterns in how disease progresses from its earliest stages. They found more than 1,100 “sequential diagnostic correlations” that occurred the most frequently in the Danish population, from an early seemingly unrelated medical issue through later diagnosis of maladies like diabetes, chronic obstructive pulmonary disease, cancer, arthritis and cardiovascular disease.
See below for an example of a disease network.
The number of children under the age of 5 who died around the world in 2013 fell by almost two-thirds compared to mortality rates in 1970, a major international study reports. That proportion represents 11.3 million fewer young children dying of injury, disease and malnourishment every year from then to now.
“Child mortality worldwide is decreasing and has been in many countries for many decades,” the authors wrote in their study published in The Lancet earlier this month. “The decreases achieved in high-income, middle-income and low-income countries surely count among the more important achievements for humanity in the past 60 years.”
We’ve all been hearing for years about how a number of technologies are poised to change the nature of medicine. One of those with the biggest promise is centered on the study of genetics, which is revealing the blueprints behind some of our most intractable diseases. Another, which proponents argue will be a disruptive force to advance preventative medicine, is Big Data—the analysis of massive amounts of information being collected on patients to find clues to detecting and treating disease.
This is not the first article to show that those years of dedication and work by scientists in a number of fields are starting to bear fruits. An article published late last month in the journal Science Translational Medicine reveals some of the latest findings. In it, a team used both genetics and Big Data to link patients’ seemingly unrelated traits with the onset of disease. Their work will one day point doctors to a developing disease before it could have been diagnosed in the past.
“Over the last 10 to 15 years, researchers have been doing lots of genetic studies,” says Dr. Atul Butte, a biomedical informatics researcher and Stanford professor. “These studies are indicating that certain diseases come from certain genes, but also that certain traits can predict a coming disease. Electronic medical records are feeding this, offering more data on patients along with their genome to see what spelling differences in DNA mean.”
Butte and scientists from Mount Sinai School of Medicine, Stanford and Columbia used previous gene research that linked a specific gene variant to a trait, like elevated levels of cholesterol or a certain enzyme, and a disease. They then analyzed electronic medical records to link the early appearance of that trait to a later disease diagnosis. Their effort uncovered five previously unknown associations after combing through as many as 610,000 anonymized patient records per linkage.