One of the most significant benefits offered by data mining projects is the potential to highlight patterns that would otherwise go unnoticed, thereby leading to improved insight and decision-making.
This potential is clearly on display in a new data mining project focused on improving the understanding of some of the world's most common diseases. The study, a joint effort by Danish scientists and researchers from the University of New Mexico, relied on data mining solutions to examine a vast trove of patient medical information.
Plenty of data
The project strives to apply advanced data mining technology and strategies to the health records of the entire Danish population. By doing so, the researchers hope to discover new strategies for predicting how diseases spread over time.
"This is a leap into a fairly large database," said Pope Mosley, chair of UNM's Department of Internal Medicine. "This method is able to recognize patterns in data that not only include diagnostic patterns, but includes the element of time and is able to build networks from that."
The database in question is the Danish National Patient Registry, as Popular Science reported. This registry includes information from every single interaction between a Danish resident and a Danish hospital. According to the researchers, this information concerns more than 6 million individuals and 65 million separate trips to the hospital between 1996 and 2010.
"You're able to take these mass of data and look at it over time and begin to draw associations," said Mosley.
Notably, this project aims to identify previously unseen connections between diseases. By doing so, physicians may be better able to diagnose serious conditions earlier based on a patient suffering from a more apparent disease.
"Instead of looking at each disease in isolation, you can talk about a complex system with many different interacting factors," said Anders Boeck Jensen, the lead author of the study and a postdoctoral fellow at the Novo Nordisk Center for Protein Research at the University of Copenhagen. "By looking at the order in which different diseases appear, you can start to draw patterns and see complex correlations outlining the direction for each individual person."
With this information in hand, physicians can identify warning signs for serious problems quicker, leading to earlier treatment.
Data mining technology was essential to this effort.
"The disease trajectories in this study follow causal relationships that were identified by a medically agnostic software," said Tudor Oprea, professor of internal medicine and chief of UNM's Translational Informatics Division. "This illustrates the power of data mining as a means to uncover novel disease relationships and its ability to inform the health care sector about new avenues in patient management."
As Popular Science pointed out, the data mining project delivered a number of noteworthy discoveries concerning the progression of common diseases. For example, the researchers found that many patients tend to be diagnosed with chronic obstructive pulmonary disease following a diagnosis of hardened arteries. Shortly thereafter, many of these received more serious diagnoses, many of which were fatal.
This led the study's authors to conclude that COPD is a more serious condition than previously realized, as it is often a precursor for deadly diseases, Popular Science reported. By viewing COPD as a warning sign, physicians may be better able treat these serious conditions before they would otherwise be discovered.
Ultimately, this project offered further support for a more personalized approach to medicine, one which factors in the individual's genetic profile and other unique information to predict further medical concerns.