Biomedical Information Processing
Gathering data is crucial to providing health care, advancing our understanding of basic biological processes, and identifying novel therapeutic targets and diagnostic biomarkers. The ability to effectively analyze, interpret, and manage that data is just as vital. With the technological advances that make data gathering faster than ever comes the need to efficiently process all this data. Opportunities abound to use patient data to personalize health care, automate the analysis of complex medical images, and mine biological databases to gather new insights into basic biological processes. Ongoing research projects in biomedical information processing by our faculty in this field are streamlining the effort to turn raw data into biomedical advances.
Genomic and Proteomic Analysis
Over the past decade, several organisms’ genomes have been sequenced, including the human genome. These genomic databases are now routinely used in drug discovery and development. While the genomic databases are clearly an advance, this is not the complete picture since the genes that are expressed by an organism vary from cell type to cell type. Even within a given cell, the protein expression will change in response to a variety of factors (e.g., the environment). The study of protein expression, structure, and function is termed proteomics. Integral to both proteomics and genomics is the management and utilization of large data sets. Lonnie Welch, Stuckey Professor of Electrical Engineering and Computer Science, and his team are developing custom integrated software to expedite proteomics and genomics research. Welch works with John Kopchick, Goll Ohio Eminent Scholar and Professor of Molecular Biology, and his group to identify new therapeutic targets for endocrine diseases, especially those involved with growth disorders and diabetes. In a separate project, Welch and his team are working with Sarah Wyatt, Professor of Environmental and Plant Biology, and her group, who use genomics to study plant responses to environmental stimuli. Such work has an impact on the use of plants as a source of medicinals.
Artificial Intelligence and Diabetes Management
Patients with Type 1 diabetes are unable to produce insulin, an essential hormone needed to convert food into energy, and so they must depend on exogenous insulin to survive. Although there is no cure for diabetes, patients can avoid serious complications of the disease by keeping their blood glucose levels as close to normal as possible. Blood glucose data can be automatically collected and sent to a physician for analysis. This results in a large amount of data, and at present, data analysis is a time-consuming, manual process. The sheer volume of data makes it difficult for physicians to provide therapy recommendations in a timely manner. Frank Schwartz, J.O. Watson Endowed Chair for Diabetes Research and professor of endocrinology, and Cynthia Marling, associate professor of electrical engineering and computer science, are exploring the use of artificial intelligence to analyze data from patients with Type 1 diabetes and provide recommendations for therapy adjustment comparable to those an endocrinologist would make. They and their group aim to provide more frequent feedback for patients, enabling better glycemic control while reducing the time spent by endocrinologists on routine data analysis. They are conducting a preliminary clinical study, involving patients with Type 1 diabetes on insulin pump therapy, to evaluate the feasibility of providing intelligent decision support.
Continuous Glucose Monitoring to Analyze the Impact of Diabetes on Cognition, Language Processing, and Hearing
An interdisciplinary team of investigators is engaged in the analysis of continuous glucose monitoring data of diabetes patients to better understand the moment-by-moment as well as cumulative long-term effects of variations in glucose levels on cognitive, linguistic, and hearing abilities. The project, headed by Brooke Hallowell, professor of communication sciences and disorders, and Frank Schwartz, J.O. Watson Endowed Research Chair and professor of endocrinology, entails analysis of large data sets pertaining to behavioral test results and corresponding glucose levels in patients with Type 1 and Type 2 diabetes. This effort involves faculty members and students across multiple disciplines.
Medical Image Analysis
Imaging technologies are crucial for the diagnosis and treatment of an array of serious diseases. For example, cancer is often diagnosed and staged with a combination of magnetic resonance imaging (MRI) and computer-aided tomography (CAT). Biomedical engineers play a key role in the development of these devices and the interpretation of the data generated by these devices. The research group of Jundong Liu, associate professor of electrical engineering and computer science, develops advanced segmentation and registration techniques for longitudinal brain atrophy measurement in Alzheimer’s patients (in collaboration with the Sanders-Brown Center on Aging at the University of Kentucky), subcortical structure analysis (with the Vanderbilt University Institute of Imaging Sciences), and regional fat quantification in mice (with researchers from Ohio University’s Edison Biotechnology Institute).
Cochlear implants, which are electronic devices that are surgically implanted to the cochleas of patients with profound sensorineural hearing loss, have provided hearing to those patients through electrical stimulations. The goals of Li Xu, associate professor of communication sciences and disorders, and his research group are to understand the mechanisms of electrical hearing and to identify ways to improve the function of the auditory prostheses. In particular, using signal processing techniques, Xu's team is trying to identify features of stimulation that are important for speech perception, tone perception, and music perception in patients with cochlear implants. Meanwhile, in collaboration with physicians in Beijing, Xu is studying the tone perception and production development in native tone-language-speaking children with cochlear implants.