Skip to content Skip to navigation

Study: Statistical Model Could Forecast Future Ailments

June 4, 2012
by Gabriel Perna
| Reprints

According to a study from the University of Washington (UW), through thorough analysis of medical records from patients, statisticians have created a statistical model for predicting what other medical problems a patient might encounter. This, according to UW, would be similar to how Netflix recommends movies and TV shows for viewers. The algorithm makes predictions based on what a patient has already experienced as well as the experiences of other patients showing a similar medical history.

"This provides physicians with insights on what might be coming next for a patient, based on experiences of other patients. It also gives a predication that is interpretable by patients," Tyler McCormick, lead author of the paper and an assistant professor of statistics and sociology at UW, said in a statement.

According to McCormick, this type of predictive algorithm has rarely been used in a medical setting. He says the difference between his model and others is it shares information across patients who have similar health problems. This, he says, allows for better predictions when details of a patient's medical history are sparse, such as when a patient doesn’t have a lengthy file listing ailments and drug prescriptions.

"We're looking at each sequence of symptoms to try to predict the rest of the sequence for a different patient," McCormick said.     

In addition, the algorithm can also accommodate situations where it's statistically difficult to predict a less common condition. An example, McCormick cites, is most patients do not experience strokes, and accordingly most models could not predict one because they only factor in an individual patient's medical history with a stroke. His model uses medical histories of patients who went on to have a stroke and uses that analysis to make a stroke prediction.

The authors used medical records obtained from a multiyear clinical drug trial involving tens of thousands of patients aged 40 and older. They included other demographic details, such as gender and ethnicity, as well as patients' histories of medical complaints and prescription medications.

Of the 1,800 medical conditions in the dataset, most of them – 1,400 – occurred fewer than 10 times. They came up with a statistical modeling technique to account for these rarer conditions. "We hope that this model will provide a more patient-centered approach to medical care and to improve patient experiences," McCormick said.

The algorithm will be published in an upcoming issue of the journal Annals of Applied Statistics.



OSU Wexner Medical Center Receives AHIMA Grace Award

The Ohio State University Wexner Medical Center (OSUWMC) received the American Health Information Management Association (AHIMA) annual Grace Award in recognition of its leadership in health information management.

Kansas Health Information Network Expands its Network across State Lines

The Kansas Health Information Network (KHIN) has announced that it is expanding its horizons, and is now connected to Health Information Exchange Texas (HIETexas).

CMS Selects Vendor to Modernize Critical Identity Infrastructure

The Centers for Medicare & Medicaid Services (CMS) last week announced it had selected San Francisco-based vendor Okta to enhance the security of its information systems.

Mayo Clinic, ASU Partner for Medical Education, Healthcare Innovation

The Mayo Clinic and Arizona State University have announced a partnership centered on transforming medical education and healthcare in the U.S. through a variety of innovation efforts.

CMS Hospital Compare Website Updated with VA Data

The Centers for Medicare & Medicaid Services (CMS) has announced the inclusion of Veterans Administration (VA) hospital performance data as part of the federal agency’s Hospital Compare website.

CMS Awards Funding to Special Innovation Projects

The Centers for Medicare & Medicaid Services (CMS) has awarded 20, two-year Special Innovation Projects (SIPs) aimed at local efforts to deliver better care at lower cost.