My research is primarily focused around 1) machine learning methods for understanding healthcare delivery and outcomes in the population, 2) analyses of correlated data (e.g. longitudinal and clustered data), and 3) survival analysis and competing risks analyses. We have developed tree-based and ensemble regression methods for censored and multilevel data, combination classifiers using different types of learning methods, and methodology to identify representative trees from an ensemble. These methods have been applied to important areas of biomedicine, specifically in patient prognostication, in developing clinical decision-making tools, and in identifying complex interactions between patient, provider, and health systems for understanding variations in healthcare utilization and delivery. My substantive areas of research are cancer and pediatric cardiovascular disease.
S. Sriram, PhD, is Associate Professor of Marketing in the University of Michigan Ross School of Business, Ann Arbor.
Prof. Sriram’s research interests are in the areas of brand and product portfolio management, multi-sided platforms, healthcare policy, and online education. His research uses state of the art econometric methods to answer important managerial and policy-relevant questions. He has studied topics such as measuring and tracking brand equity and optimal allocation of resources to maintain long-term brand profitability, cannibalization, consumer adoption of technology products, and strategies for multi-sided platforms. Substantively, his research has spanned several industries including consumer packaged goods, technology products and services, retailing, news media, the interface of healthcare and marketing, and MOOCs.
Samuel K Handelman, Ph.D., is Research Assistant Professor in the department of Internal Medicine, Gastroenterology, of Michigan Medicine at the University of Michigan, Ann Arbor. Prof. Handelman is focused on multi-omics approaches to drive precision/personalized-therapy and to predict population-level differences in the effectiveness of interventions. He tends to favor regression-style and hierarchical-clustering approaches, partially because he has a background in both statistics and in cladistics. His scientific monomania is for compensatory mechanisms and trade-offs in evolution, but he has a principled reason to focus on translational medicine: real understanding of these mechanisms goes all the way into the clinic. Anything less that clinical translation indicates that we don’t understand what drove the genetics of human populations.
Antonios M. Koumpias, Ph.D., is Assistant Professor of Economics in the department of Social Sciences at the University of Michigan, Dearborn. Prof. Koumpias is an applied microeconomist with research interests in public economics, with an emphasis on behavioral tax compliance, and health economics. In his research, he employs quasi-experimental methods to disentangle the causal impact of policy interventions that occur at the aggregate (e.g. states) or the individual (e.g. taxpayers) level in a comparative case study setting. Namely, he relies on regression discontinuity designs, regression kink designs, matching methods, and synthetic control methods to perform program evaluation that estimates the causal treatment effect of the policy in question. Examples include the use of a regression discontinuity design to estimate the impact of a tax compliance reminders on payments of overdue income tax liabilities in Greece, matching methods to measure the influence of mass media campaigns in Pakistan on income tax filing and the synthetic control method to evaluate the long-term effect of state Medicaid expansions on mortality.
Srijan Sen, MD, PhD, is the Frances and Kenneth Eisenberg Professor of Depression and Neurosciences. Dr. Sen’s research focuses on the interactions between genes and the environment and their effect on stress, anxiety, and depression. He also has a particular interest in medical education, and leads a large multi-institution study that uses medical internship as a model of stress.
Professor Saigal has held faculty positions at the Haas School of Business, Berkeley and the department of Industrial Engineering and Management Sciences at Northwestern University, has been a researcher at the Bell Telephone Laboratories and numerous short term visiting positions. He currently teaches courses in Financial Engineering. In the recent past he taught courses in optimization, and Management Science. His current research involves data based studies of operational problems in the areas of Finance, Transportation, Renewable Energy and Healthcare, with an emphasis on the management and pricing of risks. This involves the use of data analytics, optimization, stochastic processes and financial engineering tools. His earlier research involved theoretical investigation into interior point methods, large scale optimization and software development for mathematical programming. He is an author of two books on optimization and large set of publications in top refereed journals. He has been an associate editor of Management Science and is a member of SIAM, AMS and AAAS. He has served as the Director of the interdisciplinary Financial Engineering Program and as the Director of Interdisciplinary Professional Programs (now Integrative Design + Systems) at the College of Engineering.
Dr. Aebersold’s professional and academic career is focused on advancing the science of learning applied in simulation to align clinician and student practice behaviors with research evidence to improve learner and health outcomes. She focuses her scholarship in both high fidelity and virtual reality simulation and is a national leader and expert in simulation. Her scholarship has culminated in developing the Simulation Model to Improve Learner and Health Outcomes (SMILHO).
Current Research Grants and Programs:
- Closing the loop: new data tools for measuring change in the quality for nursing education and the value of new approaches to instruction (PI) University of Michigan School of Nursing.
- Interactive anatomy-augmented virtual simulation training (PI with Voepel-Lewis) Archie MD Award Number 045889
Profile: Building a Better Nurse
By Dan Meisler
Communications Manager, ARC
Michelle Aebersold has spent her career trying to “build a better nurse,” through training development, virtual clinical environments, and patient simulations.
As Director of Simulation and Educational Innovation at the U-M School of Nursing, Aebersold is focused on creating realistic learning environments for nursing students.
But it wasn’t until relatively recently that she realized she had an under-utilized but powerful tool at her disposal — data.
For years, Aebersold has been collecting data on how student performance is affected by participation in various simulations, but it wasn’t until speaking to faculty from the Michigan Institute for Data Science (MIDAS) that she realized the potential insights all of her historical datasets might have hidden inside.
“We’re trying to pull them all together to create a common thread, so that as we collect data on our students, we can follow them to say how they progressed. How many simulations and what type of simulations did they get and how did that impact their learning?” Aebersold said. “We hit students with a lot of simulations while they’re in school, but we don’t necessarily know which ones are better for certain things.”
Now, as MIDAS core faculty member, Aebersold will be able to easily collaborate with other MIDAS researchers to refine and analyze her data.
Eventually, she said, she’d like to be able to track nursing students as they enter their first jobs to see how their training translates to real-world performance. And a further goal for Aebersold is to help the practice of nursing education become similar to the training world-class athletes receive, in which, for example, subjects review videos of their performance to identify what works and what doesn’t.
“We’re going to introduce some things, like what can we do with virtual simulations, or what can we do with eye-tracking,” she said. “We really want to try to dive deeper, by being able to put all this information together using a lot of these data science methods.”
Aebersold has been at U-M since the mid-1980s, serving in a variety of clinical and administrative roles. She earned a Ph.D in Nursing from the University in 2008, and served as Director of the Clinical Learning Center in the School of Nursing for eight years thereafter. Since 2016, she’s been Director of Simulation and Educational Innovation.
One of Aebersold’s recent projects, “Closing the Loop: New Data Tools for measuring Changes in the Quality of Nursing Education,” applies modern data-science tools to help understand the correlation between traditional tests and student skills and competence when they enter the workforce, and whether simulations coupled with debriefing sessions translate into improvements in skills and in test outcomes.
Another potential project will focus on comparing the eye movements of novice nurses to expert nurses. Aebersold said initial findings have shown that nurses with more experience tend to focus their eyes on one thing for longer periods of time than those with less.
She said she’s enlisting help on that work from professors in the School of Information at U-M.
“By really understanding the difference between how experts do things and novices do things, you can help develop simulations that help novices get better,” Aebersold said.
She credits her father with starting her on the path to becoming a nurse; he was a police officer, and would sometimes take her to the local emergency room.
“I loved the fast pace,” she recalled, and the chance to have a real, positive impact on people’s lives.
After earning a nursing degree from Madonna University, she became a critical care nurse. She then gravitated toward supervision and administration, gaining a masters in business administration, also from Madonna University. She earned her Ph.D. from U-M while working as a nurse manager at the U-M health System.
She said all the technology, data, and innovative modes of study she’s brought together are all in service of one goal.
“For me, it all comes down to how can we make the patient care environment safer for our patients,” she said.
Zhenke Wu is an Assistant Professor of Biostatistics, and a core faculty member in the Michigan Institute of Data Science (MIDAS). He received his Ph.D. in Biostatistics from the Johns Hopkins University in 2014 and then stayed at Hopkins for his postdoctoral training before joining the University of Michigan. Dr. Wu’s research focuses on the design and application of statistical methods that inform health decisions made by individuals, or precision medicine. The original methods and software developed by Dr. Wu are now used by investigators from research institutes such as CDC and Johns Hopkins, as well as site investigators from developing countries, e.g., Kenya, South Africa, Gambia, Mali, Zambia, Thailand and Bangladesh.
Profile: At a “sweet spot” of data science
By Dan Meisler
Communications Manager, ARC
If you had to name two of the more exciting, emerging fields of data science, electronic health records (EHR) and mobile health might be near the top of the list.
Zhenke Wu, one of the newest MIDAS core faculty members, has one foot firmly in each field.
“These two fields share the common goal of learning from the experience of the population in the past to advance health and clinical decisions for those to follow. I am looking forward to more work that will bring the two fields closer to continuously generate insights about human health.” Wu said. “I’m in a sweet spot.”
Wu joined U-M in Fall 2016, after earning a PhD in Biostatistics from Johns Hopkins University, and a bachelor’s in Mathematics from Fudan University. He said the multitude of large-scale studies going on at U-M and access to EHR databases were factors in his coming to Michigan.
“The University of Michigan is an exciting place that has a diversity of large-scale databases and supportive research groups in the fields I’m interested in,” he said.
Wu is collaborating with the Michigan Genomics Initiative, which is a biorepository effort at Michigan Medicine to integrate genome-wide information with EHR from approximately 40,000 patients undergoing anesthesia prior to surgery or diagnostic procedures. He’s also collaborating with Dr. Srijan Sen, Associate Professor, Department of Psychiatry and Molecular and Behavioral Neuroscience Institute, on the MIDAS-supported project “Identifying Real-Time Data Predictors of Stress and Depression Using Mobile Technology,” the preliminary results of which recently matured into an NIH-funded R01 project “Mobile Technology to Identify Mechanisms Linking Genetic Variation and Depression” that will draw broad expertise from a multi-disciplinary team of medical and data science researchers.
“One of my goals is to use an integrated and rigorous approach to predict how a person’s health status will be in the near future,” Wu said.
Wu applies hierarchical Bayesian models to these problems, which he hopes will shed light on phenomena he describes as latent constructs that are “well-known, but less quantitatively understood, e.g., intelligence quotient (IQ) in psychology.”
As another example, he cites the current challenge in active surveillance of prostate cancer patients for aggressive tumors requiring removal and/or radiation, or indolent tumors permitting continued surveillance.
“The underlying status of aggressive versus indolent cancer is not observed, which needs to be learned from the results of biopsy and other clinical measurements,” he said. “The decisions and experience of urologists and their patients will greatly benefit from more accurate understanding of the tumor status… There are lots of scientific problems in clinical, biomedical, behavioral and social sciences where you have well-known but less quantitatively understood latent constructs. These are problems that Bayesian latent variable methods can formulate and address.”
Just as Wu has a hand in two hot-button big data areas, he also sees himself as straddling the line between application and methodology.
He says the large number of data sources — sensors, mobile apps, test results, and questionnaires, to name just a few — results in richness as well as some “messiness” that needs new methodologies to adjust, integrate and translate to new scientific insights. At the same time, a valid new methodology for dealing with, for example, electronic health data, will likely find numerous different applications.
Wu says his approach was heavily influenced by his work in the Pneumonia Etiology Research for Child Health (PERCH) funded by the Gates Foundation while he was at Johns Hopkins. Pneumonia is a clinical syndrome due to lung infection that can be caused by more than 30 different species of pathogens, including bacteria, viruses and fungi. The goal of the seven-country study that enrolled more than 5,000 cases and 5,000 controls from Africa and Southeast Asia is to estimate the frequency with which each pathogen caused pneumonia in the population and the probability of each individual being infected by the list of pathogens in the lung.
“In most settings, it is extremely difficult to identify the pathogen by directly sampling from the site of infection – the child’s lung. PERCH therefore looked for other sources of evidence by standardizing and comprehensively testing biofluids collected from sites peripheral to the lung. Using hierarchical Bayesian models to infer disease etiology by integrating such a large trove of data was extremely fun and exciting”, he said.
Wu’s initial interest in math, leading to biostatistics and now data science, stems from what he called a “greedy” desire to learn the guiding principles of how the world works by rigorous data science.
“If you have new problems, you can wait for other people to ask a clean math question, or you can go work with these messy problems and figure out interesting questions and their answers,” he said.
For more on Dr. Wu, see his profile on Michigan Experts.
Matias D. Cattaneo, Ph.D., is Professor of Economics and Statistics in the College of Literature, Science, and the Arts at the University of Michigan, Ann Arbor.
Prof. Cattaneo’s research interests include econometric theory, mathematical statistics, and applied econometrics, with focus on causal inference, program evaluation, high-dimensional problems and applied microeconomics. Most of his recent research relates to the development of new, improved semiparametric, nonparametric and high-dimensional inference procedures exhibiting demonstrable superior robustness properties with respect to tuning parameter and other implementation choices. His work is motivated by concrete empirical problems in social, biomedical and statistical sciences, covering a wide array of topics in settings related to treatment effects and policy evaluation, high-dimensional models, average derivatives and structural response functions, applied finance and applied decision theory, among others.
Anna Kratz, PhD, is Assistant Professor of Physical Medicine and Rehabilitation and the Center for Clinical Outcomes Development and Application (CODA) at the University of Michigan, Ann Arbor.
Dr. Kratz’s clinical research is focused on the characteristics and mechanisms of common symptoms (e.g. pain, fatigue, cognitive dysfunction) and functional outcomes in those with chronic clinical conditions. Using a combination of ambulatory measurement methods of physical activity (actigraphy), heart rate variability, galvanic skin response, and self-reported experiences, her research aims to overlay the patient’s day-to-day experience with physiological markers of stress, sleep quality, and physical activity. She utilizes a number of computational approaches, including multilevel statistical modeling, signal processing, and machine learning to analyze these data. The ultimate goal is to use insights from these data to design better clinical interventions to help patients better manage symptoms and optimize functioning and quality of life.