A dynamic Bayesian network model for predicting organ failure associations without predefining outcomes.
Ontology highlight
ABSTRACT:
SUBMITTER: De Blasi RA
PROVIDER: S-EPMC8081190 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Bayesian network is an increasingly popular method in modeling uncertain and complex problems, because its interpretability is often more useful than plain prediction. To satisfy the core requirement in medical research to obtain interpretable prediction with high accuracy, we constructed an inference engine for post-stroke outcomes based on Bayesian network classifiers. The prediction system that was trained on data of 3,605 patients with acute stroke forecasts the functional independence at 3 months and the mortality 1 year after stroke. Feature selection methods were applied to eliminate less relevant and redundant features from 76 risk variables. The Bayesian network classifiers were trained with a hill-climbing searching for the qualified network structure and parameters measured by maximum description length. We evaluated and optimized the proposed system to increase the area under the receiver operating characteristic curve (AUC) while ensuring acceptable sensitivity for the class-imbalanced data. The performance evaluation demonstrated that the Bayesian network with selected features by wrapper-type feature selection can predict 3-month functional independence with an AUC of 0.889 using only 19 risk variables and 1-year mortality with an AUC of 0.893 using 24 variables. The Bayesian network with 50 features filtered by information gain can predict 3-month functional independence with an AUC of 0.875 and 1-year mortality with an AUC of 0.895. We also built an online prediction service, Yonsei Stroke Outcome Inference System, to substantialize the proposed solution for patients with stroke.
| S-EPMC6137617 | biostudies-literature
Project description:We propose a novel approach to the estimation of multiple Graphical Models to analyse temporal patterns of association among a set of metabolites over different groups of patients. Our motivating application is the Southall And Brent REvisited (SABRE) study, a tri-ethnic cohort study conducted in the UK. We are interested in identifying potential ethnic differences in metabolite levels and associations as well as their evolution over time, with the aim of gaining a better understanding of different risk of cardio-metabolic disorders across ethnicities. Within a Bayesian framework, we employ a nodewise regression approach to infer the structure of the graphs, borrowing information across time as well as across ethnicities. The response variables of interest are metabolite levels measured at two time points and for two ethnic groups, Europeans and South-Asians. We use nodewise regression to estimate the high-dimensional precision matrices of the metabolites, imposing sparsity on the regression coefficients through the dynamic horseshoe prior, thus favouring sparser graphs. We provide the code to fit the proposed model using the software Stan, which performs posterior inference using Hamiltonian Monte Carlo sampling, as well as a detailed description of a block Gibbs sampling scheme.
| S-EPMC10763914 | biostudies-literature
Project description:Approximately 90% of pre-clinically validated drugs fail in clinical trials due to unanticipated clinical outcomes, costing over several hundred million US dollars per drug. Despite such critical importance, translating pre-clinical data to clinical outcomes remain a major challenge. Herein, we designed a modality-independent and unbiased approach to predict clinical outcomes of drugs. The approach exploits their multi-organ transcriptome patterns induced in mice and a unique mouse-transcriptome database “humanized” by machine learning algorithms and human clinical outcome datasets. The cross-validation with small-molecule, antibody and peptide drugs shows effective and efficient identification of the previously known outcomes of 5,519 adverse events and 11,312 therapeutic indications. In addition, the approach is adaptable to deducing potential molecular mechanisms underlying these outcomes. Furthermore, the approach identifies previously unsuspected repositioning targets. These results, together with the fact that it requires no prior structural or mechanistic information of drugs, illustrate its versatile applications to drug development process.
2020-01-09 | GSE142068 | GEO
Project description:The Gulf of Mexico is an ecologically and economically important marine ecosystem that is affected by a variety of natural and anthropogenic pressures. These complex and interacting pressures, together with the dynamic environment of the Gulf, present challenges for the effective management of its resources. The recent adoption of Bayesian networks to ecology allows for the discovery and quantification of complex interactions from data after making only a few assumptions about observations of the system. In this study, we apply Bayesian network models, with different levels of structural complexity and a varying number of hidden variables to account for uncertainty when modeling ecosystem dynamics. From these models, we predict focal ecosystem components within the Gulf of Mexico. The predictive ability of the models varied with their structure. The model that performed best was parameterized through data-driven learning techniques and accounted for multiple ecosystem components' associations and their interactions with human and natural pressures over time. Then, we altered sea surface temperature in the best performing model to explore the response of different ecosystem components to increased temperature. The magnitude and even direction of predicted responses varied by ecosystem components due to heterogeneity in driving factors and their spatial overlap. Our findings suggest that due to varying components' sensitivity to drivers, changes in temperature will potentially lead to trade-offs in terms of population productivity. We were able to discover meaningful interactions between ecosystem components and their environment and show how sensitive these relationships are to climate perturbations, which increases our understanding of the potential future response of the system to increasing temperature. Our findings demonstrate that accounting for additional sources of variation, by incorporating multiple interactions and pressures in the model layout, has the potential for gaining deeper insights into the structure and dynamics of ecosystems.
| S-EPMC6344104 | biostudies-literature
Project description:BackgroundLinear regression models are important tools for learning regulatory networks from gene expression time series. A conventional assumption for non-homogeneous regulatory processes on a short time scale is that the network structure stays constant across time, while the network parameters are time-dependent. The objective is then to learn the network structure along with changepoints that divide the time series into time segments. An uncoupled model learns the parameters separately for each segment, while a coupled model enforces the parameters of any segment to stay similar to those of the previous segment. In this paper, we propose a new consensus model that infers for each individual time segment whether it is coupled to (or uncoupled from) the previous segment.ResultsThe results show that the new consensus model is superior to the uncoupled and the coupled model, as well as superior to a recently proposed generalized coupled model.ConclusionsThe newly proposed model has the uncoupled and the coupled model as limiting cases, and it is able to infer the best trade-off between them from the data.
| S-EPMC8074473 | biostudies-literature
Project description:There is increasing interest to consider dependent failures and human errors in the offshore industry. Permanently abandoned wells dot most of the subsea environment. The nature of a well plugging and abandonment (Well P&A) run - usually the lowest-cost contractor engaged to plug several wells tapping the same reservoir makes it an ideal case study for incorporating failures based on common causes. The heavy use of operators during a cementing job also provides the case for analysis of human error in such tasks. One proposed method to analyse the above-mentioned is the use of Bayesian Belief Networks to achieve the following objectives (1) to capture better estimates of a well PA event by incorporating dependencies, and meet regulatory requirements by authorities; and (2) to use the same model to provide long term monitoring of a group of wells linked by common dependencies. This model has not only captured the dependencies of multiple variables, but also projected it in a dynamic manner to provide a risk profile for the next decade where well integrity failure is likely to happen. • Proposed adapted method capture better estimates of a well PA event by incorporating dependencies • Method allows for extension of model to long term monitoring of a group of wells linked by common dependencies.
| S-EPMC8686067 | biostudies-literature
Project description:BackgroundAmyotrophic lateral sclerosis (ALS) is an adult-onset neurodegenerative disease progressively affecting upper and lower motor neurons in the brain and spinal cord. Mean life expectancy is three to five years, with paralysis of muscles, respiratory failure and loss of vital functions being the common causes of death. Clinical manifestations of ALS are heterogeneous due to the mix of anatomic regions involvement and the variability in disease course; consequently, diagnosis and prognosis at the level of individual patient is really challenging. Prediction of ALS progression and stratification of patients into meaningful subgroups have been long-standing interests to clinical practice, research and drug development.MethodsWe developed a Dynamic Bayesian Network (DBN) model on more than 4500 ALS patients included in the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT), in order to detect probabilistic relationships among clinical variables and identify risk factors related to survival and loss of vital functions. Furthermore, the DBN was used to simulate the temporal evolution of an ALS cohort predicting survival and the time to impairment of vital functions (communication, swallowing, gait and respiration). A first attempt to stratify patients by risk factors and simulate the progression of ALS subgroups was also implemented.ResultsThe DBN model provided the prediction of ALS most probable trajectories over time in terms of important clinical outcomes, including survival and loss of autonomy in functional domains. Furthermore, it allowed the identification of biomarkers related to patients' clinical status as well as vital functions, and unrevealed their probabilistic relationships. For instance, DBN found that bicarbonate and calcium levels influence survival time; moreover, the model evidenced dependencies over time among phosphorus level, movement impairment and creatinine. Finally, our model provided a tool to stratify patients into subgroups of different prognosis studying the effect of specific variables, or combinations of them, on either survival time or time to loss of autonomy in specific functional domains.ConclusionsThe analysis of the risk factors and the simulation allowed by our DBN model might enable better support for ALS prognosis as well as a deeper insight into disease manifestations, in a context of a personalized medicine approach.
| S-EPMC6471677 | biostudies-literature
Project description:Despite the fact that preconditions of political participation were thoroughly examined before, there is still not enough understanding of which factors directly affect political participation and which factors correlate with participation due to common background variables. This article scrutinises the causal relations between the variables associated with participation in online activism and introduces a three-step approach in learning a reliable structure of the participation preconditions' network to predict political participation. Using Bayesian network analysis and structural equation modeling to stabilise the structure of the causal relations, the analysis showed that only age, political interest, internal political efficacy and no other factors, highlighted by the previous political participation research, have direct effects on participation in online activism. Moreover, the direct effect of political interest is mediated by the indirect effects of internal political efficacy and age via political interest. After fitting the parameters of the Bayesian network dependent on the received structure, it became evident that given prior knowledge of the explanatory factors that proved to be most important in terms of direct effects, the predictive performance of the model increases significantly. Despite this fact, there is still uncertainty when it comes to predicting online participation. This result suggests that there remains a lot to be done in participation research when it comes to identifying and distinguishing factors that stimulate new types of political activities.
| S-EPMC8699968 | biostudies-literature
Project description:BackgroundAlthough vaccination is one of the main countermeasures against influenza epidemic, it is highly essential to make informed prevention decisions to guarantee that limited vaccination resources are allocated to the places where they are most needed. Hence, one of the fundamental steps for decision making in influenza prevention is to characterize its spatio-temporal trend, especially on the key problem about how influenza transmits among adjacent places and how much impact the influenza of one place could have on its neighbors. To solve this problem while avoiding too much additional time-consuming work on data collection, this study proposed a new concept of spatio-temporal route as well as its estimation methods to construct the influenza transmission network.MethodsThe influenza-like illness (ILI) data of Sichuan province in 21 cities was collected from 2010 to 2016. A joint pattern based on the dynamic Bayesian network (DBN) model and the vector autoregressive moving average (VARMA) model was utilized to estimate the spatio-temporal routes, which were applied to the two stages of learning process respectively, namely structure learning and parameter learning. In structure learning, the first-order conditional dependencies approximation algorithm was used to generate the DBN, which could visualize the spatio-temporal routes of influenza among adjacent cities and infer which cities have impacts on others in influenza transmission. In parameter learning, the VARMA model was adopted to estimate the strength of these impacts. Finally, all the estimated spatio-temporal routes were put together to form the final influenza transmission network.ResultsThe results showed that the period of influenza transmission cycle was longer in Western Sichuan and Chengdu Plain than that in Northeastern Sichuan, and there would be potential spatio-temporal routes of influenza from bordering provinces or municipalities into Sichuan province. Furthermore, this study also pointed out several estimated spatio-temporal routes with relatively high strength of associations, which could serve as clues of hot spot areas detection for influenza surveillance.ConclusionsThis study proposed a new framework for exploring the potentially stable spatio-temporal routes between different places and measuring specific the sizes of transmission effects. It could help making timely and reliable prediction of the spatio-temporal trend of infectious diseases, and further determining the possible key areas of the next epidemic by considering their neighbors' incidence and the transmission relationships.
| S-EPMC7874476 | biostudies-literature
Project description:BackgroundIn 2015, the Zika virus spread from Brazil throughout the Americas, posing an unprecedented challenge to the public health community. During the epidemic, international public health officials lacked reliable predictions of the outbreak's expected geographic scale and prevalence of cases, and were therefore unable to plan and allocate surveillance resources in a timely and effective manner.MethodsIn this work, we present a dynamic neural network model to predict the geographic spread of outbreaks in real time. The modeling framework is flexible in three main dimensions (i) selection of the chosen risk indicator, i.e., case counts or incidence rate; (ii) risk classification scheme, which defines the high-risk group based on a relative or absolute threshold; and (iii) prediction forecast window (1 up to 12 weeks). The proposed model can be applied dynamically throughout the course of an outbreak to identify the regions expected to be at greatest risk in the future.ResultsThe model is applied to the recent Zika epidemic in the Americas at a weekly temporal resolution and country spatial resolution, using epidemiological data, passenger air travel volumes, and vector habitat suitability, socioeconomic, and population data for all affected countries and territories in the Americas. The model performance is quantitatively evaluated based on the predictive accuracy of the model. We show that the model can accurately predict the geographic expansion of Zika in the Americas with the overall average accuracy remaining above 85% even for prediction windows of up to 12 weeks.ConclusionsSensitivity analysis illustrated the model performance to be robust across a range of features. Critically, the model performed consistently well at various stages throughout the course of the outbreak, indicating its potential value at any time during an epidemic. The predictive capability was superior for shorter forecast windows and geographically isolated locations that are predominantly connected via air travel. The highly flexible nature of the proposed modeling framework enables policy makers to develop and plan vector control programs and case surveillance strategies which can be tailored to a range of objectives and resource constraints.
| S-EPMC6717993 | biostudies-literature