Most of my research related to data science involves decision making around clinical trials. In particular, I am interested in how databases of past clinical trial results can inform future trial design and other decisions. Some of my work has involved using machine learning and mathematical optimization to design new combination therapies for cancer based on the results of past trials. Other work has used network meta-analysis to combine the results of randomized controlled trials (RCTs) to better summarize what is currently known about a disease, to design further trials that would be maximally informative, and to study the quality of the control arms used in Phase III trials (which are used for drug approvals). Other work combines toxicity data from clinical trials with toxicity data from other data sources (claims data and adverse event reporting databases) to accelerate detection of adverse drug reactions to newly approved drugs. Lastly, some of my work uses Bayesian inference to accelerate clinical trials with multiple endpoints, learning the link between different endpoints using past clinical trial results.
Dr. Douville is a critical care anesthesiologist with an investigative background in bioinformatics and perioperative outcomes research. He studies techniques for utilizing health care data, including genotype, to deliver personalized medicine in the perioperative period and intensive care unit. His research background has focused on ways technology can assist health care delivery to improve patient outcomes. This began designing microfluidic chips capable of recreating fluid mechanics of atelectatic alveoli and monitoring the resulting barrier breakdown real-time. His interest in bioinformatics was sparked when he observed how methodology designed for tissue engineering could be modified to the nano-scale to enable genomic analysis. Additionally, his engineering training provided the framework to apply data-driven modeling techniques, such as finite element analysis, to complex biological systems.
I use machine-learning techniques to implement decision support systems and tools that facilitate more personalized care for disease management and healthcare utilization to ultimately deliver efficient, effective, and equitable therapy for chronic diseases. To test and advance these general principles, I have built operational programs that are guiding—and improving—patient care in costly in low resource settings, including emerging countries.
Dr. Valley’s research focuses on understanding and improving decision-making in the intensive care unit (ICU). His primary line of research seeks to identify the patients most likely to benefit from intensive care, allowing clinicians to safely triage patients between the ICU and the general ward. Ultimately, he hopes to identify ICU-based therapies that can be transferred to the general ward to improve hospital efficiency and reduce healthcare costs. Dr. Valley’s research interests also include enhancing diagnosis in critical illness, improving the ICU experience for family members of ICU patients, and reducing barriers to cost-effective pulmonary and critical care.
I am a pulmonary and critical care physician who is passionate about improving critical care delivery by applying advanced methods for causal inference to observational data. My prior work has leveraged real-world data clinical and administrative data to study the epidemiology of critical illness, the organization of critical care, and health care financing.
My current work leverages real-world clinical data to understand whether and how care team fragmentation (transitions of physicians and other providers while a patient is still hospitalized) influences clinical outcomes like survival and recovery. Answering these questions correctly requires methods that are attentive to the complex causal structure underlying the relationship, depicted here. It features time-varying exposures (A), confounders (L), and mediators (M), all of which can influence clinical outcomes (Y). Arrows in the figure identify directional (i.e., causal) relationships between variables.
My applied research focuses on simulation models of the progression of multiple chronic complications and comorbidities of diabetes and its precursors. I study the effectiveness and cost-effectiveness of early interventions in the progression of diabetes. My methodological research synthesizes secondary data from complementary studies to model complex processes.
I conduct research on the use of consumer-facing technologies for chronic disease self management. My work predominantly centers on the use of mobile applications that collect and manage patient generated health data overt time.
My work falls into three general application areas. I am an applied (accredited) biostatistician with a strong team science motivation and I collaborate with scientists in primarily the biomedical sciences, contributing expertise in experimental design, statistical analysis/modeling, and data visualization. I have held faculty appointments in Schools of Medicine and Nursing, and also worked as a senior scientist in the Human Research Program at the NASA Johnson Space Center. I currently direct an Applied Biostatistics Laboratory and Data Management Core within the UM School of Nursing, and maintain several collaborative research programs within the School, at NASA, and with collaborators elsewhere.
My research involves developing novel data collection strategies and image reconstruction techniques for Magnetic Resonance Imaging. In order to accelerate data collection, we take advantage of features of MRI data, including sparsity, spatiotemporal correlations, and adherence to underlying physics; each of these properties can be leveraged to reduce the amount of data required to generate an image and thus speed up imaging time. We also seek to understand what image information is essential for radiologists in order to optimize MRI data collection and personalize the imaging protocol for each patient. We deploy machine learning algorithms and optimization techniques in each of these projects. In some of our work, we can generate the data that we need to train and test our algorithms using numerical simulations. In other portions, we seek to utilize clinical images, prospectively collected MRI data, or MRI protocol information in order to refine our techniques.
We seek to develop technologies like cardiac Magnetic Resonance Fingerprinting (cMRF), which can be used to efficiently collect multiple forms of information to distinguish healthy and diseased tissue using MRI. By using rapid methods like cMRF, quantitative data describing disease processes can be gathered quickly, enabling more and sicker patients can be assessed via MRI. These data, collected from many patients over time, can also be used to further refine MRI technologies for the assessment of specific diseases in a tailored, patient-specific manner.