Search

BackgroundSuccessful management of gestational diabetes mellitus (GDM) reduces the risk of morbidity in women and newborns. A woman’s blood glucose readings and risk factors are used by clinical staff to make decisions regarding the initiation of pharmacological treatment in women with GDM. Mobile health (mHealth) solutions allow the real-time follow-up of women with GDM and allow timely treatment and management. Machine learning offers the opportunity to quickly analyze large quantities of data to automatically flag women at risk of requiring pharmacological treatment. ObjectiveThe aim of this study is to assess whether data collected through an mHealth system can be analyzed to automatically evaluate the switch to pharmacological treatment from diet-based management of GDM. MethodsWe collected data from 3029 patients to design a machine learning model that can identify when a woman with GDM needs to switch to medications (insulin or metformin) by analyzing the data related to blood glucose and other risk factors. ResultsThrough the analysis of 411,785 blood glucose readings, we designed a machine learning model that can predict the timing of initiation of pharmacological treatment. After 100 experimental repetitions, we obtained an average area under the receiver operating characteristic curve of 0.80 (SD 0.02) and an algorithm that allows the flexibility of setting the operating point rather than relying on a static heuristic method, which is currently used in clinical practice. ConclusionsUsing real-time data collected via an mHealth system may further improve the timeliness of the intervention and potentially improve patient care. Further real-time clinical testing will enable the validation of our algorithm using real-world data.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.anbehav.2007.01.013 Byline: Steven Hamblin, Peter L. Hurd Abstract: Game theory is not only the primary method for the formal modelling of interactions between individuals, but it also underlies how biologists think about social interactions on an intuitive level. Most biologists equate game theory with the notion of an evolutionary stable strategy (ESS). Maynard Smith's definition of an ESS formalized an intuitive concept of stable population equilibria in game theory models. This has proven extremely useful, both to formal modelling efforts, and to a much wider range of biologists in general. The formal definition of an ESS often cannot be met for an entire class of games, extensive form games with nodes off the supported path. Games of this form are the most reasonable models for a great many animal behaviours. This means that formal ESSs will not exist for these games, even though evolutionary stable strategies, in the intuitive sense, do exist. More powerful analytical solution concepts, such as evolutionarily stable sets (ES sets), are required to describe stable endpoints formally, but finding such solutions can be extremely difficult. In this paper we use genetic algorithms as an alternative method of searching for such solutions in a well-studied game of biological communication. Using this technique, we show a previously unknown solution to this game. We discuss the properties of biological communication that make it a particularly difficult subject to model using ESSs as the solution concept, and suggest that these issues also apply to a larger class of social models. Author Affiliation: Department of Psychology, University of Alberta, Canada Article History: Received 27 September 2006; Revised 28 October 2006; Accepted 12 January 2007 Article Note: (miscellaneous) MS. number: A10572

Genetic algorithms are a heuristic global optimisation technique mimicking the action of natural selection to solve hard optimisation problems, which has enjoyed growing usage in evolution and ecology. However, there is little standardisation in how genetic algorithms are implemented in these fields and even less practical advice for those hoping to implement genetic algorithms for their own models. This article aims to demystify genetic algorithms and provide assistance to researchers; basic programming knowledge is important for working with genetic algorithms, but none is required to read this article., I review the basics of genetic algorithm methodology and provide suggestions on problems that may or may not benefit from genetic algorithm methods. The genetic operators (selection, replacement, mutation, crossover) and their rate parameters (mutation rate, etc.) are a source of potential confusion and to ease their selection, I present recommendations informed by historical usage and best practices, concluding with potential pitfalls., Good reasons for employing genetic algorithms include: solving optimisation problems beyond the reach of analytical techniques, relaxing model assumptions, evolving behaviour in individual-based models, and simulating co-evolutionary processes. However, genetic algorithms are not always the correct technique to use. Simpler methods may sometimes outperform genetic algorithms, and certain problem features may cause trouble., Genetic algorithms strike a balance between exploration of the search space and exploitation of good solutions, driven by the choice of genetic operators and rate parameters. I outline a basic set of parameter values and operator choices for genetic algorithm models as a starting point and provide advice on how to modify them to explore the exploitation/exploration trade-off. Finally, I provide general advice on analysis and reporting of these models., There are a number of potential issues that can surprise unwary users, such as rate parameter values that lead to pathological outcomes; I suggest ways to detect and correct these problems. Also, contrary to popular usage, genetic algorithms can find solutions to game theory problems but cannot guarantee their stability. Finally, while genetic algorithms offer great power and flexibility by drawing inspiration from evolutionary processes, they are (usually) not a faithful model of genetics or evolution. [ABSTRACT FROM AUTHOR]

Our ability to collect large datasets is growing rapidly. Such richness of data offers great promise in terms of addressing detailed scientific questions in great depth. However, this benefit is not without scientific difficulty: many traditional analysis methods become computationally intractable for very large datasets. However, one can frequently still simulate data from scientific models for which direct calculation is no longer possible. In this paper we propose a Bayesian perspective for such analyses, and argue for the advantage of a simulation-based approximate Bayesian method that remains tractable when tractability of other methods is lost. This method, which is known as "approximate Bayesian computation" [ABC], has now been used in a variety of contexts, such as the analysis of tumor data (a tumor being a complex population of cells), and the analysis of human genetic variation data (which arise from a population of individual people). We review a number of ABC methods, with specific attention to the use of ABC in agent-based models, and give pointers to software that allows straightforward implementation of the ABC approach. In this way we demonstrate the utility of simulation-based analyses of large datasets within a rigorous statistical framework.