Xinyu (David) Song, a doctoral student in Biomedical Engineering in the School of Engineering & Applied Science, took second place and won $100,000 in the CIMIT Student Healthcare Technology competition.
Xinyu (David) Song (left) working with Dennis Barbour, MD, PhD (right), in Barbour's lab
Earlier this year, he won $10,000 to continue developing his project as one of 10 finalists for the final prizes of $150,000, $100,000 and $50,000.
Song works in the lab of Dennis Barbour, MD, PhD, associate professor of biomedical engineering, studying how to streamline the diagnosis of auditory disorders.
Song's project involves providing an automated, user-friendly hearing test to primary-care physicians, who are likely the first to notice symptoms of hearing loss in their patients. By enabling hearing loss screening to be conducted in primary-care facilities, patients with hearing disorders can be more easily identified and can then be referred to audiologists for more detailed testing and treatment.
The competition is designed to help engineering students advance their promising clinically relevant, primary care innovations. Of particular interest are technologies that could improve access to medical care, leverage the skills of caregivers, automate routine tasks, increase workflow efficiency, support patients with chronic disease, increase compliance with care protocols, reduce medical error or supplement the physician-patient relationship.
In addition to Barbour, his collaborators are William W. Clark, PhD, professor of otolaryngology and of audiology & communication sciences and education in the Washington University School of Medicine, and Roman Garnett, PhD, assistant professor of computer science in the School of Engineering & Applied Science.
Original story: July 1, 2015
Doctoral student wins $10,000 for efficient hearing test
Hearing loss affects about 10 percent of American adults, and that prevalence greatly increases with age. But only about 20 percent of adults who could benefit from hearing-assist devices seek treatment for their hearing loss.
To make hearing loss diagnosis more accessible, Xinyu (David) Song, a doctoral student in biomedical engineering at Washington University in St. Louis, has proposed making an automated test available to primary-care physicians, who are most likely the first to notice symptoms of hearing loss in their patients. Instead of referring these patients to an audiologist, which adds to health-care costs and includes the risk that the patient will not follow through with treatment, the primary-care physician could use this automated, user-friendly system within the same office.
Song has received $10,000 for this idea as one of 10 finalists for the Student Technology Prize for Primary Healthcare, awarded by the Center for Integration of Medicine & Innovative Technology, a non-profit consortium of teaching hospitals and universities in Boston that promotes interdisciplinary collaboration to improve patient care. The competition awards $10,000 to each of 10 semifinalists to continue work on the project. In August, it will award $50,000, $100,000 and $150,000 to the top three projects.
The Student Technology Prize for Primary Healthcare competition seeks innovations, such as technologies, instruments, devices or systems with the potential to support improved delivery of patient care. In particular, the competition seeks technologies that could improve access to medical care, better use caregivers' skills, automate routine tasks, increase workflow efficiency, support patients with chronic disease, increase compliance with care protocols, reduce medical error in primary care, or augment the physician-patient or nurse-patient relationship.
Song said audiologists in the U.S. collectively spend about 238,000 work hours measuring pure-tone audiograms, a reliable measure of hearing loss, and that is expected to increase over the next 50 years.
"A more accessible form of hearing loss diagnosis could empower primary health-care providers as well as dramatically reduce the burden of labor for specialized health-care professions, ultimately lowering cost and barriers for this initial diagnostic activity," Song said.
Song will use a machine-learning technique called Bayesian active learning, which can be used to successively select the most informative pure tones to deliver to patients, expediting the testing, which proceeds automatically. In early trials, the algorithm he designed has measured audiograms with comparable accuracy and reliability to standard testing techniques while using less than half of the tones typically delivered by an audiologist.
Song works in the lab of Dennis Barbour, MD, PhD, associate professor of biomedical engineering, studying how to optimize the diagnosis and treatment of auditory processing disorders using distributed computing. In addition to Barbour, his collaborators are William W. Clark, PhD, professor of otolaryngology and of audiology & communication sciences and education in the Washington University School of Medicine, and Roman Garnett, PhD, assistant professor of computer science in the School of Engineering & Applied Science.
The School of Engineering & Applied Science at Washington University in St. Louis focuses intellectual efforts through a new convergence paradigm and builds on strengths, particularly as applied to medicine and health, energy and environment, entrepreneurship and security. With 87 tenured/tenure-track and 40 additional full-time faculty, 1,300 undergraduate students, more than 900 graduate students and more than 23,000 alumni, we are working to leverage our partnerships with academic and industry partners — across disciplines and across the world — to contribute to solving the greatest global challenges of the 21st century.