The complexity of analysing dynamical systems often lies in the difficulty to monitor each of their dynamic properties. In this article, we use qualitative models to present an exhaustive way of representing every possible state of a given system, and combine it with Bayesian networks to integrate quantitative information and reasoning under uncertainty. The result is a combined model able to give explanations relying on expert knowledge to predict the behaviour of a system. We illustrate our approach with a deterministic model to show how the combination is done, then extend this model to integrate uncertainty and demonstrate its benefits
Abstract BackgroundFrailty is a syndrome that is defined as an accumulation of deficits in physical, psychological, and social domains. On a global scale, there is an urgent need to create frailty-ready healthcare systems due to the healthcare burden that frailty confers on systems and the increased risk of falls, healthcare utilization, disability, and premature mortality. Several studies have been conducted to develop prediction models for predicting frailty. Most studies used logistic regression as a technique to develop a prediction model. One area that has experienced significant growth is the application of Bayesian techniques, partly due to an increasing number of practitioners valuing the Bayesian paradigm as matching that of scientific discovery. ObjectiveWe compared ten different Bayesian networks as proposed by ten experts in the field of frail elderly people to predict frailty with a choice from ten dichotomized determinants for frailty. MethodsWe used the opinion of ten experts who could indicate, using an empty Bayesian network graph, the important predictors for frailty and the interactions between the different predictors. The candidate predictors were age, sex, marital status, ethnicity, education, income, lifestyle, multimorbidity, life events, and home living environment. The ten Bayesian network models were evaluated in terms of their ability to predict frailty. For the evaluation, we used the data of 479 participants that filled in the Tilburg Frailty indicator (TFI) questionnaire for assessing frailty among community-dwelling older people. The data set contained the aforementioned variables and the outcome ”frail”. The model fit of each model was measured using the Akaike information criterion (AIC) and the predictive performance of the models was measured using the area under the curve (AUC) of the receiver operator characteristic (ROC). The AUCs of the models were validated using bootstrapping with 100 repetitions. The relative importance of the predictors in the models was calculated using the permutation feature importance algorithm (PFI). ResultsThe ten Bayesian networks of the ten experts differed considerably regarding the predictors and the connections between the predictors and the outcome. However, all ten networks had corrected AUCs 0.700. Evaluating the importance of the predictors in each model, ”diseases or chronic disorders” was the most important predictor in all models (10 times). The predictors ”lifestyle” and ”monthly income” were also often present in the models (both 6 times). One or more diseases or chronic disorders, an unhealthy lifestyle, and a monthly income below 1,800 euro increased the likelihood of frailty. ConclusionsAlthough the ten experts all made different graphs, the predictive performance was always satisfying (AUCs 0.700). While it is true that the predictor importance varied all the time, the top three of the predictor importance consisted of “diseases or chronic disorders”, “lifestyle” and “monthly income”. All in all, asking for the opinion of experts in the field of frail elderly to predict frailty with Bayesian networks may be more rewarding than a data-driven forecast with Bayesian networks because they have expert knowledge regarding interactions between the different predictors.
LINK
Bayesian networks have shown to be a useful tool for the evaluation of forensic findings given activity level propositions. In this paper, we demonstrate how case specific experiments can be used to assign probabilities to the states of the nodes of a Bayesian network for the evaluation of fingermarks given activity level propositions. The transfer, persistence and recovery of fingermarks on knives is studied in experiments where a knife is either used to stab a victim or to cut food, representing the activities that were disputed in the case of the murder of Meredith Kercher. Two Bayesian networks are constructed, exploring the effect of different uses of the experimental data by assigning the probabilities based on the results of the experiments. The evaluation of the findings using the Bayesian networks demonstrates the potential for fingermarks in addressing activity level propositions.
