Home > News and Events > News Releases > News Releases Archive

E-mail this page

News Releases: July - September 2008

Contents

• July
• August
• September

July

A Sensible Censor for Sharing Medical Records
MIT-developed Software Helps Protect Patient Privacy

Elizabeth A. Thomson, MIT News Office
July 23, 2008

Newly developed MIT software will help to allay patients' fears about who has access to their confidential records, facilitating the use of that data for medical research.

In the July 24 issue of the journal BMC Medical Informatics and Decision Making, a team of MIT researchers describes a computer program capable of automatically deleting details from medical records that may identify patients, while leaving important medical information intact.

Patient records that are to be shared within the research community must have any identifying information removed, according to the U.S. Health Insurance Portability and Accountability Act (HIPAA). However, manual removal of identifying information is prohibitively expensive, time consuming and prone to error-constraints that have prompted considerable research toward developing automated techniques for "de-identifying" medical records.

The MIT team aimed to solve this problem. "We've developed a free and open-source software package to allow researchers to accurately de-identify text in medical records in a HIPAA-compliant manner," said Gari D. Clifford, a principal research scientist in the Harvard-MIT Division of Health Sciences and Technology (HST) who led the work with Principal Investigator Roger G. Mark, a professor in HST and MIT's Department of Electrical Engineering and Computer Science.

According to Dr. Zohara Cohen, program director at the National Institute of Biomedical Imaging and Bioengineering, sponsor of the work, the information in patients' medical records is a "largely untapped treasure trove" that the biomedical research community could use to better understand diseases and their treatments.

"The automated de-identification software developed under the guidance of Dr. Mark is a big step forward in permitting the widespread sharing of patient information without the risk of compromised privacy and confidentiality," Cohen said.

Clifford, Mark and colleagues tested their censoring software on 1,836 nursing notes (a total of 296,400 words). Using multiple experts and additional algorithms, they replaced all personal information with "fake" data. In their BMC paper, they report that "the software successfully deleted more than 94 percent of the confidential information, while wrongly deleting only 0.2 percent of the useful content. This is significantly better than one expert working alone, at least as good as two trained medical professionals checking each other's work and many, many times faster than either."

The team is providing researchers access to the evaluation dataset together with the software to allow others to improve their systems, and to allow the software to be adapted to other data types that may exhibit different qualities.

Clifford and Mark's co-authors are Ishna Neamatullah; Margaret M. Douglass; Li-wei H. Lehman, an HST research engineer; Andrew Reisner, an HST visiting scientist; Mauricio Villarroel, an HST visiting engineer; William J. Long, a principal research associate in MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL); Professor Peter Szolovits of the Department of Electrical Engineering and Computer Science and HST; and George B. Moody, HST sponsored research staff.

Back to Top

August

In Memoriam: Dr. Robert F. Wagner (1938-2008)

Dr. Robert F. Wagner was a distinguished research physicist and member of the Senior Biomedical Research Service in the Center for Devices and Radiological Health (CDRH), U.S. Food and Drug Administration (FDA). His career was dedicated to the development of consensus measurement methods for the assessment of medical imaging systems, quantitative medical imaging and tissue characterization, and computer-aided diagnosis. He earned an international reputation in these areas and applied his expertise to a wide range of regulatory issues central to FDA’s mission. He enlightened the scientific community within the Agency as well as the international scientific community through many invited presentations and tutorials, his numerous publications, his many professional society activities, and his assistance in regulatory decision making. His greatest legacy may be the many young scientists he nurtured, either by direct tutelage at the FDA or by his many teaching engagements and research collaborations.

Dr. Robert F. Wagner (1938-2008)

Robert F. Wagner was born in Philadelphia on January 10, 1938. After graduate and post-graduate work on the physics of nuclear interactions with radiation, he was hired by the Bureau of Radiological Health (a precursor to CDRH) to assess the dose reduction potential of radiographic intensifying screens. Within months he published a review of the relevant imaging literature together with a charter for a laboratory program. Soon thereafter, Bob introduced digital noise analysis to radiography, and showed that the new technology offered a 1.6 to 2.5-fold exposure reduction without compromising imaging performance. He then launched a program of inter-laboratory comparison of measurements on radiographic film samples that were circulated among fifteen commercial, government, and academic laboratories world wide. In the process he became the prime mover for work toward consensus methodology for quantitative imaging performance measurements.

In the mid-1970s most investigators were concerned by the high exposures and doses required by the newly introduced CT technology. Wagner and his colleagues showed that CT was intrinsically a high-dose technique and his analyses and clarifications were used by the BRH laboratory staff in the writing of the CT amendments to the X-ray Performance Standards. Bob Wagner subsequently led the development of a “unified signal-to-noise” ratio approach to the assessment of all conventional modes of medical imaging. This work led to the wide use of detection quantum efficiency as a performance metric for radiographic imaging systems that continues to this day.

Dr. Wagner’s valuable ability to unify performance measures among different imaging was next applied to ultrasound. Adopting key results from radar and laser literature, he was able to develop the first satisfactory theoretical and experimental approach to quantitative understanding of ultrasound speckle, its dependence on ultrasonic hardware parameters, and its effect on the detectability of lesions by medical ultrasound. Two award winning papers in 1983 and a stream of related publications on ultrasound that followed made possible many advances in the development of standards for ultrasonic imaging system performance assessment. In another prize winning 1989 Investigative Radiology publication, he showed that the incoherent backscattered signal could be separated from two classes of coherent ultrasound signals returned from the body and demonstrated how the resulting algorithm discriminated several diffuse liver diseases from each other and from normal liver.

In the field of decision analysis, Dr. Wagner and his collaborators published key investigations on the ability of human observers to extract information from images obtained by a medical imaging system. In a 1981 article in Science, Dr. Wagner extended his investigations of human performance to explore statistical methods for analyzing the performance of imaging systems within the context of reader variability. Thereafter, he extended his image assessment methodology to the many new and increasingly sophisticated computer techniques being developed to aid the human reader in the interpretation of high-dimensional image data sets for medical diagnosis. In recent years, he was working on study designs, objective measurements, and analytical methods for the assessment of stand-alone diagnostic modalities such as high-dimensional DNA micro-arrays.

Dr. Wagner’s research resulted in a stream of highly cited and extremely creative scientific publications, as well as recognition in the form of honors and awards by FDA and his professional community. He was elected to the rank of Fellow by five societies: IEEE, AIMBE, OSA, SPIE, and SPSE. Within the FDA he was awarded the FDA Commendable Service Award and the Award of Merit, the Commissioner’s Special Citation, and the Public Health Service Superior Service award, in addition to having been a member of numerous groups receiving unit awards. In recognition of his contributions, Dr. Wagner was chosen as a principal author of an International Commission for Radiation Units and Measurements (ICRU) report on image quality in medical imaging. This 1995 document laid the foundation for a series of ICRU reports with more detailed recipes, one medical imaging modality at a time, that have been developed since. He served on numerous academic advisory boards, search committees, conference program committees, and editorial boards, and carried on an extremely active service function as a reviewer of grants and scientific papers.

Dr. Wagner revolutionized the way in which medical imaging technologies are evaluated. He spent more than 35 years in seminal work on understanding and developing paradigms for the description and evaluation of medical imaging and computer-assisted diagnostic modalities. His contributions to the science enterprise will live on in the work of his students and colleagues for decades to come.

Back to Top

September

NIBIB Welcomes Two New Members to Advisory Council

Two new members were recently appointed to the Advisory Council of the National Institute of Biomedical Imaging and Bioengineering (NIBIB). The Council serves as the principal advisory body to the NIBIB, a component of the National Institutes of Health. The Council, which meets three times a year, provides recommendations on research priority and opportunities in biomedical imaging and bioengineering and research training.

At the meeting on September 16, 2008, NIBIB Director Roderic I. Pettigrew, Ph.D., M.D., introduced the following new members:

PHILIP O. ALDERSON, M.D., is the Dean of the Saint Louis University School of Medicine, a position he assumed in April 2008. He is a renowned nuclear medicine physician and diagnostic radiologist who helped develop standard procedures for noninvasive diagnosis of pulmonary emboli. Dr. Alderson is a Past President of the Academy for Radiology Research. Prior to joining Saint Louis University, he was the chairman of the department of radiology at Columbia-Presbyterian Medical Center and the James Picker Professor of Radiology at the College of Physicians and Surgeons at Columbia University. While at Columbia, he championed the integration of bioengineering and radiology, and promoted the rapidly developing area of molecular imaging. Dr. Alderson received his medical degree from Washington University in St. Louis.

CHERRI M. PANCAKE, PH.D., is a professor of electrical engineering and computer science and Intel faculty fellow at Oregon State University. She is a pioneer in applying ethnographic techniques to identify software usability problems of science and business communities. The methods she developed are used in software products from Hewlett Packard, Convex, Intel, IBM, and Tektronix. Recently, she has focused on how virtual collaborations differ from proximal collaborations. Dr. Pancake received her degree in computer engineering from Auburn University. Her research interests are in usability engineering, more specifically, addressing the problem of how complex software can better support the conceptual models and computing strategies of practicing scientists and engineers. Dr. Pancake has been instrumental in the creation of the Parallel Tools Consortium and the Network for Earthquake Engineering Simulation (NEESH).

Members of the Advisory Council are drawn from the scientific communities, appointed for 4-year terms, and represent all areas within the Institute's research mission.

Back to Top