Elle O’Brien

By |

My research focuses on building infrastructure for public health and health science research organizations to take advantage of cloud computing, strong software engineering practices, and MLOps (machine learning operations). By equipping biomedical research groups with tools that facilitate automation, better documentation, and portable code, we can improve the reproducibility and rigor of science while scaling up the kind of data collection and analysis possible.

Research topics include:
1. Open source software and cloud infrastructure for research,
2. Software development practices and conventions that work for academic units, like labs or research centers, and
3. The organizational factors that encourage best practices in reproducibility, data management, and transparency

The practice of science is a tug of war between competing incentives: the drive to do a lot fast, and the need to generate reproducible work. As data grows in size, code increases in complexity and the number of collaborators and institutions involved goes up, it becomes harder to preserve all the “artifacts” needed to understand and recreate your own work. Technical AND cultural solutions will be needed to keep data-centric research rigorous, shareable, and transparent to the broader scientific community.

View MIDAS Faculty Research Pitch, Fall 2021


Ben Green

By |

Ben studies the social and political impacts of government algorithms. This work falls into several categories. First, evaluating how people make decisions in collaboration with algorithms. This work involves developing machine learning algorithms and studying how people use them in public sector prediction and decision settings. Second, studying the ethical and political implications of government algorithms. Much of this work draws on STS and legal theory to interrogate topics such as algorithmic fairness, smart cities, and criminal justice risk assessments. Third, developing algorithms for public sector applications. In addition to academic research, Ben spent a year developing data analytics tools as a data scientist for the City of Boston.

Allison Earl

By |

My primary research interests are understanding the causes and consequences of biased selection and attention to persuasive information, particularly in the context of health promotion. Simply stated, I am interested in what we pay attention to and why, and how this attention (or inattention) influences attitudinal and behavioral outcomes, such as persuasion and healthy behavior. In particular, my work has addressed disparities in attention to information about HIV prevention for African-Americans compared to European-Americans as a predictor of disparities in health outcomes. I am also exploring barriers to attention to health information by African-Americans, including the roles of stigma, shame, fear, and perceptions of irrelevance. At a more basic attitudes and persuasion level, I am currently pursuing work relevant to how we select information for liked versus disliked others, and how the role of choice influences how we process information we agree versus disagree with.

Daniel P. Keating

By |

The primary tools currently in use are variations of linear models (regression, MLM, SEM, and so on) as we pursue the initial aims of the NICHD funded work. We are expanding into new areas that require new tools. Our adolescent sample is diverse, selected through quota sampling of high schools close enough to UM to afford the use of neuroimaging tools, but it is not population representative. To overcome this, we have begun work to calibrate our sample with the nationally representative Monitoring the Future study, implementing pseudo-weighting and multilevel regression and post-stratification. To enable much more powerful analyses, we are aiming toward the harmonization of multiple, high quality longitudinal databases from adolescence through early adulthood. This would benefit traditional analyses by allowing cross-validation with high power, but also provide opportunities for newer data science tools such as computational modeling and machine learning approaches.

Anne Fernandez

By |

Dr. Fernandez is a clinical psychologist with extensive training in both addiction and behavioral medicine. She is the Clinical Program Director at the University of Michigan Addiction Treatment Service. Her research focuses on the intersection of addiction and health across two main themes: 1) Expanding access to substance use disorder treatment and prevention services particularly in healthcare settings and; 2) applying precision health approaches to addiction-related healthcare questions. Her current grant-funded research includes an NIH-funded randomized controlled pilot trial of a preoperative alcohol intervention, an NIH-funded precision health study to leverage electronic health records to identify high-risk alcohol use at the time of surgery using natural language processing and other machine-learning based approaches, a University of Michigan funded precision health award to understand and prevent new persistent opioid use after surgery using prediction modeling, and a federally-funded evaluation of the state of Michigan’s substance use disorder treatment expansion.

Niko Kaciroti

By |

Niko Kaciroti is a Research Scientist at the Departments of Pediatrics and Biostatistics. He received his PhD in Biostatistics from the University of Michigan. Since then he has collaborated in multidisciplinary research at the University of Michigan and with researchers from other universities in the United States and internationally. Dr. Kaciroti is a faculty member at the Center for Computational Medicine and Bioinformatics. His main research interest is in using Bayesian models for analyzing longitudinal data from clinical trials with missing values, as well as using Bayesian methods for nonlinear and dynamic models. Dr. Kaciroti is an elected member of the International Statistical Institute and serves as statistical editor for the American Journal of Preventive Medicine and the International Journal of Behavior Nutrition and Physical Activity.

Rahul Ladhania

By |

Rahul Ladhania is an Assistant Professor of Health Informatics in the Department of Health Management & Policy at the University of Michigan School of Public Health. He also has a secondary (courtesy) appointment with the Department of Biostatistics at SPH. Rahul’s research is in the area of causal inference and machine learning in public and behavioral health. A large body of his work focuses on estimating personalized treatment rules and heterogeneous effects of policy, digital and behavioral interventions on human behavior and health outcomes in complex experimental and observational settings using statistical machine learning methods.

Rahul co-leads the Machine Learning team at the Behavior Change For Good Initiative (Penn), where he is working on two `mega-studies’ (very large multi-arm randomized trials): one in partnership with a national fitness chain, to estimate the effects of behavioral interventions on promoting gym visit habit formation; and the other in partnership with two large Mid-Atlantic health systems and a national pharmacy chain, to estimate the effects of text-based interventions on increasing flu shot vaccination rates. His other projects involve partnerships with step-counting apps and mobile-based games to learn user behavior patterns, and design and evaluate interventions and their heterogeneous effects on user behavior.

Ranjan Pal

By |

Cyber-security is a complex and multi-dimensional research field. My research style comprises an inter-disciplinary (primarily rooted in economics, econometrics, data science (AI/ML/Bayesian and Frequentist Statistics), game theory, and network science) investigation of major socially pressing issues impacting the quality of cyber-risk management in modern networked and distributed engineering systems such as IoT-driven critical infrastructures, cloud-based service networks, and app-based systems (e.g., mobile commerce, smart homes) to name a few. I take delight in proposing data-driven, rigorous, and interdisciplinary solutions to both, existing fundamental challenges that pose a practical bottleneck to (cost) effective cyber-risk management, and futuristic cyber-security and privacy issues that might plague modern (networked) engineering systems. I strongly strive for originality, practical significance, and mathematical rigor in my solutions. One of my primary end goals is to conceptually get arms around complex, multi-dimensional information security and privacy problems in a way that helps, informs, and empowers practitioners and policy makers to take the right steps in making the cyber-space more secure.

Frederick George Conrad

By |

Fred Conrad’s research concerns the development of new methods and data sources for conducting social research. His work is largely focused on survey methodology, but he also explores the use of social media content as a complement to survey data and as a source of large-scale qualitative insights. His focus is on data quality and reducing measurement error. For example, live video interviews promote more thoughtful responses, e.g., less straightlining – the tendency to give the same answer to a battery of survey questions, but they also promote less candor when answering questions on sensitive topics. Measurement error in social media include misclassification in the automated interpretation of content using methods such as sentiment analysis and topic modeling, as well as selective self-presentation (only posting flattering content). Equally challenging is not knowing the extent to which users differ from the population to which one might wish to generalize results.

Lisa Levinson

By |

My research interests are in natural language semantics and psycholinguistics, focusing on verbs. I conduct behavioral psycholinguistic experiments with methodologies such as self-paced reading and maze tasks, as well as surveys of linguistic and semantic judgments. I also study semantic variation using corpora and datasets such as the Twitter Decahose, to better understand how words have developed diverging meanings in different communities, age groups, or regions. I use primarily R and Python to collect, manage, and analyze data. I direct the UM WordLab in the linguistics department, working with students (especially undergraduates) on experimental and computational research focusing on lexical representations.