Algorithm protects patients’ personal information while preserving the data’s utility in large-scale medical studies


MIT Technology Review, April 15, 2010, by Katharine Gammon  -      Researchers at Vanderbilt University have created an algorithm designed to protect the privacy of patients while maintaining researchers’ ability to analyze vast amounts of genetic and clinical data to find links between diseases and specific genes or to understand why patients can respond so differently to treatments.

Medical records hold all kinds of information about patients, from age and gender to family medical history and current diagnoses. The increasing availability of electronic medical records makes it easier to group patient files into huge databases where they can be accessed by researchers trying to find associations between genes and medical conditions–an important step on the road to personalized medicine. While the patient records in these databases are “anonymized,” or stripped of identifiers such as name and address, they still contain the numerical codes, known as diagnosis codes or ICD codes, that represent every condition a doctor has detected.

The problem is, it’s not all that difficult to follow a specific set of codes backward and identify a person, says Bradley Malin, an assistant professor of biomedical informatics at Vanderbilt University and one of the algorithm’s coauthors. In a paper published online today in the Proceedings of the National Academy of Sciences, Malin and his colleagues found that they could identify more than 96 percent of a group of patients based solely on their particular sets of diagnosis codes. “When people are asked about privacy priorities, their health data is always right up there with information about their finances,” says Malin–and for good reason. In 2000, computer science researcher Latanya Sweeney cross-referenced voter-registration records with a limited amount of public record information from the Group Insurance Commission (birth date, gender, and zip code) to identify the full medical records of former Massachusetts governor William Weld and his family. In the wrong hands, medical information could lead to blackmail or employment discrimination, or, less critical but still immensely annoying, increases in medical spam. In addition, the hospitals where data were compromised could be liable for negligence, says Malin.

To solve this problem, the Vanderbilt team designed an algorithm that searches a database for combinations of diagnosis codes that distinguish a patient. It then substitutes a more general version of the codes–for instance, postmenopausal osteoporosis could become osteoporosis–to ensure each patient’s altered record is indistinguishable from a certain number of other patients. Researchers could then access this parallel, de-identified database for gene-association studies.

To test their algorithm, the researchers applied it to 2,762 patients, then went back and tried to reconnect the study participants to their diagnostic codes. They were unable to do so. The algorithm also allows researchers to explicitly balance the level of anonymization according to the needs of their research. Ben Reis, an assistant professor at Harvard Medical School who studies personalized, predictive medical systems, says this is an important benefit of the Vanderbilt system.

An inherent tension lies between using medical records for legitimate clinical research and concerns about patient privacy. “The problem is, stuff that’s considered anonymous really isn’t,” says Michael Swiernik, director of medical informatics at the University of California, Los Angeles. “It’s going to take a lot of different creative approaches to protect people, and this algorithm is one tool in that box.”

The new approach has its limitations. The studies work best, say the researchers, when they start out with a specific hypothesis or goal–say, to study the prevalence of asthma in teenagers with allergies. However, if they wanted to use the same data to examine associations between two random health issues in the future, it would be more difficult.

The researchers want to combine their clinical-code-protecting algorithm with other security mechanisms already in place, like protections for demographic information, to keep patient data as safe as possible. They also want to reach out to use more data outside of Vanderbilt, according to Grigorios Loukides, the study’s lead author.

The future of science relies on more subtle ways of extracting useful information from existing data. Methods that allow researchers to be more nuanced in how they anonymize data “enable us to maximize the scientific benefit we get from population data while controlling the risks to privacy,” according to Isaac Kohane, director of the Boston Children’s Hospital Informatics Program. It’s all about sharing, says study author Malin. “Generating data is expensive, and it’s both good science and good etiquette to reuse data. The challenge is to do it while protecting people.” 

A new microfluidics device gives results in 15 minutes

MIT Technology Review, April 15, 2010, by Emily Singer  -  In an office park in Woburn, MA, a volunteer presents his fingertip for a quick finger stick. A phlebotomist wicks up the small drop of blood with a specially made square of plastic, then snaps the plastic into a credit-card sized microfluidics cartridge and feeds it into a special reader. Fifteen minutes later, the device spits out the volunteer’s prostate specific antigen (PSA) level, a protein used to monitor the return of prostate cancer after treatment.

The rapid results are possible because of a novel microfluidics technology developed by startup Claros Diagnostics, which hopes to make quick PSA monitoring in the doctor’s office a reality. If approved by the U.S. Food and Drug Administration, the device will be one of the first examples of long-awaited microfluidics-based diagnostics tests that can be performed in the hospital or doctor’s office. While microfluidics–which allows for the manipulation of fluids on a chip at microscopic scales–has been around for a decade, the complexity and expense has kept it largely limited to research applications.

Claros’s technology, which consists of a small blood-collector device, a disposable cartridge, and a toaster-sized reader, could, in theory at least, be adapted to detect any number of different proteins. But the company has initially chosen to focus on PSA, which is routinely monitored. With current testing, blood samples are typically sent to a centralized lab for PSA analysis. Results are returned in a day or two. Claros’s test, now in clinical trials, would allow PSA readings to be determined during the patient’s visit. While there is debate over how useful PSA testing is in diagnosing cancer, it is a well-accepted tool for monitoring those who have it. Within a month after prostate surgery, a man’s PSA levels drops–a subsequent increase suggests that PSA producing cancer cells have returned.

“Having a quick PSA test that is accurate would certainly be helpful to most urologists–simple and inexpensive being the two key words,” says Jerome Richie, chief of urology at Brigham and Women’s hospital in Boston. But he says that such a test must be able to accurately analyze the low levels of PSA that are present after prostate surgery.

Key to Claros’s device is its ability to perform the test on a small drop of blood. The surface of the cartridge is covered in narrow channels, which serve as both storage for the chemicals needed for the assay and as tiny test tubes in which to carry out the reaction. Each reagent is lined up sequentially in one long channel and separated by small air bubbles. Once the cartridge is inserted into the reader, a vacuum pulls the blood through one channel and delivers the appropriate sequence of reagents. This approach avoids the pumps used to move chemicals in other microfluidics chips, enabling a simple and robust design with no moving parts. The reader itself is simple, using an LED and photodiode to detect the buildup of silver–the output of the reaction–on the cartridge. The more silver, the less light passes through the chip and the higher the PSA level.

Scientists at Claros developed proprietary injection molding technologies that permit the hard-plastic cartridges to be made very quickly, in about 15 seconds, and for about 10 cents apiece. “Injection molding is used to make lots of consumer products, like pens, but we can manufacture them to micron-sized resolution,” says Samuel Sia, one of Claros’s cofounders and a bioengineer at Columbia University. “They cost just a few cents, and we can make hundreds of thousands per year–not many people can do that.”

Claros is currently running clinical trials to compare its device to standard PSA testing methods in order to garner regulatory approval. If approved, it could make a prostate-cancer patient’s visit to the doctor’s office much more productive. According to Stephen Zappala, a urologist at the Lahey Clinic in Andover, MA, who is working with Claros on the clinical trials, “the Claros technology will dramatically increase the efficiency of the urologist’s practice and alleviate patient anxiety associated with waiting for a laboratory result.”

Vincent Linder, a cofounder and chief technology officer, says Claros expect results from the trial in the next few months. The company hopes to launch the device in Europe later this year and in the United States in 2011. Similar technology could be used to create screening panels for women’s health or cardiac health, though Linder declined to discuss specific plans. He also declined to give an estimate of the system’s price.

In addition to the PSA monitoring device, which will be marketed in the U.S and Europe, Sia is developing a second version of the system to screen for infectious diseases in poor countries. While it uses the same core technology, this version has a battery-powered reader about the size of an iPhone and is designed to detect HIV, syphilis, and hepatitis. The device is currently being tested in health-care centers in Rwanda that treat pregnant women. “If you catch the diseases in mothers, you can prevent transmission to newborn, increasing clinical impact,” says Sia. After a series of successful field trials, Sia is now trying to find funding to move the device through the regulatory process in Africa.