-
A binary prototype for time-series surveillance and intervention
Despite much research on early detection of anomalies from surveillance data, a systematic framework for appropriately acting on these signals is lacking. We addressed this gap by formulating a hidden Markov-style model for time-series surveillance, where the system state, the observed data, and the decision rule are all binary. We incur a delayed cost, $c$, whenever the system is abnormal and no action is taken, or an immediate cost, $k$, with action, where $k<c$. If action costs are too high, then surveillance is detrimental, and intervention should never occur. If action costs are sufficiently low, then surveillance is detrimental, and intervention should always occur. Only when action costs are intermediate and surveillance costs are sufficiently low is surveillance beneficial. Our equations provide a framework for assessing which approach may apply under a range of scenarios and, if surveillance is warranted, facilitate methodical classification of intervention strategies. Our model thus offers a conceptual basis for designing real-world public health surveillance systems.
-
Bayesian Inference for Sexual Contact Networks Using Longitudinal Survey Data
Characterizing sexual contact networks is essential for understanding sexually transmitted infections, but principled parameter inference for mechanistic network models remains challenging. We develop a discrete-time simulation framework that enables parameter estimation using approximate Bayesian computation. The interpretable model incorporates relationship formation, dissolution, concurrency, casual contacts, and population turnover. Applying our framework to survey data from 403 men who have sex with men in Stockholm, we provide principled uncertainty quantification for key network dynamics. Our analysis estimates the timescale for seeking a new steady relationship at 25 weeks and for relationship dissolution at 42 weeks. Casual contacts occur more frequently for single individuals (every 1.8 weeks) than for partnered individuals (every 4.5 weeks). However, while cross-sectional data constrains these parameters, migration rates remain poorly identified. We demonstrate that simple longitudinal data can resolve this issue. Tracking participant retention between survey waves directly informs migration rates, though survey dropout is a potential confounder. Furthermore, simple binary survey questions can outperform complex timeline follow-back methods for estimating contact frequencies. This framework provides a foundation for uncertainty quantification in network epidemiology and offers practical strategies to improve inference from surveys, the primary data source for studying sexual behavior.
-
Systems and methods for performing random walks on knowledge graphs
Systems, methods and computer program products are provided for performing random walks on knowledge graphs. Knowledge graphs are received and for each knowledge graph there is constructed a multilayer network having unipartite layers and bipartite layers and interlayer couplings that (i) connect nodes of the unipartite layers and the bipartite layers representing the same entity (ii) are directed and (iii) weighted with a weight that depends on an activity of a target node in the unipartite layer or bipartite layer in which the target node resides. A walk on a random walk model of the multilayer network that takes into account saliencies of the different interlayer and intralayer connections of the nodes is then processed and one or more actions based on the random walk model are performed.
-
Biomarker Shedding at the Institute for Disease Modeling Symposium
Yuke Wang and I presented our work on biomarker shedding at the Institute for Disease Modeling Symposium hosted by the Bill and Melinda Gates Foundation in Seattle, WA.
-
BST228: Applied Bayesian Analysis
BST228 Applied Bayesian Analysis is a practical introduction to the Bayesian analysis of biomedical data taught in the Department of Biostatistics at the Harvard T.H. Chan School of Public Health taught by Prof Stephenson and Dr Hoffmann. It is an intermediate graduate-level course in the philosophy, analytic strategies, implementation, and interpretation of Bayesian data analysis. Specific topics that will be covered include: the Bayesian paradigm; Bayesian analysis of basic models; Markov Chain Monte Carlo for posterior inference; Stan R software package for Bayesian data analysis; linear regression; hierarchical regression models; generalized linear models; meta-analysis; models for missing data.