I am Research Faculty with the Michigan Center for Integrative Research in Critical Care (MCIRCC). Our team builds predictive algorithms, analyzes signals, and implements statistical models to advance Critical Care Medicine. We use electronic healthcare record data to build predictive algorithms. One example of this is Predicting Intensive Care Transfers and other Unforeseen Events (PICTURE), which uses commonly collected vital signs and labs to predict patient deterioration on the general hospital floor. Additionally, our team collects waveforms from the University Hospital, and we store this data utilizing Amazon Web Services. We use these signals to build predictive algorithms to advance precision medicine. Our flagship algorithm called Analytic for Hemodynamic Instability (AHI), predicts patient deterioration using a single-lead electrocardiogram signal. We use Bayesian methods to analyze metabolomic biomarker data from blood and exhaled breath to understand Sepsis and Acute Respiratory Distress Syndrome. I also have an interest in statistical genetics.
Efficient, low regret contextual multi-armed bandit approaches for real time learning including Thompson sampling, UCB, and knowledge gradient descent. Integration of optimization and predictive analytics for determining the time to next measurement, which modality to use, and the optimal control of risk factors to manage chronic disease. Integration of soft voting ensemble classifiers and multiple models Kalman filters for disease state prediction, Real-time (online) contextual multi-armed bandits integrated with optimization of hospital bed type dynamic control decisions for reducing 30-day readmission rates in hospitals. Robustness in system optimization when the system model is uncertain with emphasis on quantile regression forests, sample average approximation, robust optimization and distributionally robust optimization. Health care delivery systems models with prediction and control for inpatient and outpatient. Work has been done on Emergency Department redesign for improved patient flow; Capacity management and planning and scheduling for outpatient care, including integrated services networks; admission control with machine learning to ICUs, stepdown, and regular care units Surgical planning and scheduling for access delay control; Planning and scheduling for Clinical Research Units.
I am a statistician and my research focuses on applied public health work in a variety of fields specific to injury prevention, including substance use, violence, motor vehicle crash, and traumatic brain injury. Within those applications, I apply analytic methods for longitudinal data analysis, spatial and spatio-temporal data analysis, and predictive modeling (e.g., for clinical prediction of future injury risk applied to injuries like stroke, Benzodiazepine overdose, and firearm injury). I am also MPI of the System for Opioid Overdose Surveillance–a near-real-time system for monitoring fatal and nonfatal overdoses in Michigan; the system generates automated spatial and temporal summaries of recent overdose trends.
Current research includes a project funded by Toyota that uses Markov Models and Machine Learning to predict heart arrhythmia, an NSF-funded project to detect Acute Respiratory Distress Syndrome (ARDS) from x-ray images and projects using tensor analysis on health care data (funded by the Department of Defense and National Science Foundation).
Analysis of a large corpus of student writing in response to concept-focused prompts. Data includes drafts, peer feedback, and revisions for each of approximately 60,000 document and 180,000 pieces of feedback. The goal is to use tools of natural language processing to develop the capacity to provide students and faculty with feedback that will foster deeper conceptual learning among students and enhanced pedagogy among faculty.
My research is focused on developing efficient and effective statistical and computational methods for genetic and genomic studies. These studies often involve large-scale and high-dimensional data; examples include genome-wide association studies, epigenome-wide association studies, and various functional genomic sequencing studies such as bulk and single cell RNAseq, bisulfite sequencing, ChIPseq, ATACseq etc. Our method development is often application oriented and specifically targeted for practical applications of these large-scale genetic and genomic studies, thus is not restricted in a particular methodology area. Our previous and current methods include, but are not limited to, Bayesian methods, mixed effects models, factor analysis models, sparse regression models, deep learning algorithms, clustering algorithms, integrative methods, spatial statistics, and efficient computational algorithms. By developing novel analytic methods, I seek to extract important information from these data and to advance our understanding of the genetic basis of phenotypic variation for various human diseases and disease related quantitative traits.
My research interests are to improve safety associated with motor-vehicle transportation by addressing both active safety (increased crash avoidance) and passive safety (increased crash protection) issues through the development and application of a wide range of research methodologies. These methodologies are targeted at developing a better understanding and modeling of driver behavior, including physical and cognitive attributes, driver decision-making processes and human intention prediction. I am currently interested in applying data science to study the following topics:
*Driver state detection and prediction;
*Improve user intersection with automated vehicle technologies;
*Communication and interaction between vehicle and vulnerable road users
*Driving style classification
*Human factors issues associated with connected and automated vehicle technologies
The Schloss lab is broadly interested in beneficial and pathogenic host-microbiome interactions with the goal of improving our understanding of how the microbiome can be used to reach translational outcomes in the prevention, detection, and treatment of colorectal cancer, Crohn’s disease, and Clostridium difficile infection. To address these questions, we test traditional ecological theory in the microbial context using a systems biology approach. Specifically, the laboratory specializes in using studies involving human subjects and animal models to understand how biological diversity affects community function using a variety of culture-independent genomics techniques including sequencing 16S rRNA gene fragments, metagenomics, and metatranscriptomics. In addition, they use metabolomics to understand the functional role of the gut microbiota in states of health and disease. To support these efforts, they develop and apply bioinformatic tools to facilitate their analysis. Most notable is the development of the mothur software package (https://www.mothur.org), which is one of the most widely used tools for analyzing microbiome data and has been cited more than 7,300 times since it was initially published in 2009. The Schloss lab deftly merges the ability to collect data to answer important biological questions using cutting edge wet-lab techniques and computational tools to synthesize these data to answer their biological questions.
Given the explosion in microbiome research over the past 15 years, the Schloss lab has also stood at the center of a major effort to train interdisciplinary scientists in applying computational tools to study complex biological systems. These efforts have centered around developing reproducible research skills and applying modern data visualization techniques. An outgrowth of these efforts at the University of Michigan has been the institutionalization of The Carpentries organization on campus (https://carpentries.org), which specializes in peer-to-peer instruction of programming tools and techniques to foster better reproducibility and build a community of practitioners.
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.
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.