Using Bayesian Networks to Model Emergency Medical Services

Existing Structural Expectation-Maximization (EM) algorithms for learning Bayesian networks from incomplete data usually adopt the greedy hill climbing search method, which may make the algorithms find sub-optimal solutions. In this paper, we present a new Structural EM algorithm which employs a hybrid evolutionary algorithm as the search method. The experimental results on the data sets generated from several benchmark networks illustrate that our algorithm outperforms some state-of-the-art learning algorithms.

At present, most of the algorithms for learning Bayesian Networks (BNs) use EM algorithm to deal with incomplete data. They are of low efficiency because EM algorithm has to perform iterative process of probability reasoning to complete the incomplete data. In this paper we present an efficient BN learning algorithm, which use the combination of EMI method and a scoring function based on mutual information theory. The algorithm first uses EMI method to estimate, from incomplete data, probability distributions over local structures of BNs, then evaluates BN structures with the scoring function and searches for the best one. The detailed procedure of the algorithm is depicted in the paper. The experimental results on Asia and Alarm networks show that when achieving high accuracy, the algorithm is much more efficient than two EM based algorithms, SEM and EM-EA algorithms.

Bayesian networks can be used to model gene regulatory networks because of its capability of capturing causal relationships between genes. However, learning Bayesian network is an NP-hard problem. Hill climbing methods are used in BN learning, in which K2 is a frequently used greedy search algorithm. But the performance of K2 algorithm is greatly affected by a prior ordering of input nodes and relatively low accuracy of the learned structures may be observed. To solve these problems, we propose a new algorithm (BPSOBN) to explore the use of Binary Particle Swarm Optimization (BPSO) algorithms for learning Bayesian networks. The result of experiments show that our BPSO based algorithm can obtain better networks than hill climbing methods. BPSOBN also shows the effectiveness for network reconstruction to gene expression data measured during the yeast cell cycle.

Cancer can be a result of accumulation of different types of genetic mutations such as copy number aberrations. The data from tumors are cross-sectional and do not contain the temporal order of the genetic events. Finding the order in which the genetic events have occurred and progression pathways are of vital importance in understanding the disease. In order to model cancer progression, we propose Progression Networks, a special case of Bayesian networks, that are tailored to model disease progression. Progression networks have similarities with Conjunctive Bayesian Networks (CBNs) [1],a variation of Bayesian networks also proposed for modeling disease progression. We also describe a learning algorithm for learning Bayesian networks in general and progression networks in particular. We reduce the hard problem of learning the Bayesian and progression networks to Mixed Integer Linear Programming (MILP). MILP is a Non-deterministic Polynomial-time complete (NP-complete) problem for which very good heuristics exists. We tested our algorithm on synthetic and real cytogenetic data from renal cell carcinoma. We also compared our learned progression networks with the networks proposed in earlier publications. The software is available on the website https://bitbucket.org/farahani/diprog.

Bayesian networks have become a popular knowledge representation scheme for probabilistic knowledge. One of the main challenges in Bayesian networks structure learning is the development of inductive learning techniques that scale up to large and possibly physically distributed data sets. We consider an approach to learning the structure of BN from distributed data. This is based on the collective learning strategy, where a local structure is obtained at each site and the global structure is obtained by cross learning and combining. Local learning is used to identify the local structure of local nodes and local links of cross nodes from local sample data sets. Cross learning can find the entire cross-links of cross nodes. Combined together, the local BNs and BN learnt from cross learning and removes any extra local links. We use the collective learning algorithm in distributed flood decision supporting system. The result shows that the Bayesian network structure is the same compare the collective learning algorithm from distributed data sets with learning from concentrated data sets. And meanwhile the collective learning algorithm is more efficient than transmitting all samples to a central site.

Creating an ideal system of care to address the care forpatients with ST-elevation myocardial infarction (STEMI) iscomplex from both the system’s and patient/family’s perspec-tives. In general, this care is unlike most other hospital care.It typically involves very fast and complex decision makingand, often, sudden transportation to another facility forpercutaneous coronary intervention (PCI). All of this occurswith a potentially critically ill patient and at a time when thefamily is often not immediately available. In this report, weaddress key perspectives from the patient and public point ofview of the current system of care for STEMI patients andhighlight the barriers and gaps that must be addressed by anideal system of care (Table 1).

ABSTRACTBackground: The development of measures to monitor and evaluate the performance and quality of emergency medical services (EMS) systems has been a focus of attention for many years. The Medicare Rural Hospital Flexibility Program (Flex Program), established by Congress in 1997, provides grants to states to implement initiatives to strengthen rural healthcare delivery systems, including better integration of EMS into those systems of care. Objective: Building on national efforts to develop EMS performance measures, we sought to identify measures relevant to the rural communities and hospitals supported by the Flex Program. The measures are intended for use in monitoring rural EMS performance at the community level as well as for use by State Flex Programs and the Federal Office of Rural Health Policy (FORHP) to demonstrate the impact of the Flex Program. Methods: To evaluate the performance of EMS in rural communities, we conducted a literature search, reviewed research on performance measures conducted by key EMS organizations, and recruited a panel of EMS experts to identify and rate rurally-relevant EMS performance measures as well as emergent protocols for episodes of trauma, ST Elevation Myocardial Infarction (STEMI), and stroke. The rated measures were assessed for inclusion in the final measure set. Results: The Expert Panel identified 17 program performance measures to support EMS services in rural communities. These measures monitor the capacity of local agencies to collect and report quality and financial data, use the data to improve agency performance, and train rural EMS employees in emergent protocols for all age groups. Conclusion: The system of care approach on which this rural EMS measures set is based can support the FORHP's goal of better focusing State Flex Program activity to improve program impact on the performance of rural EMS services in the areas of financial viability, quality improvement, and local/regional health system performance.

The transcriptional response to exogenously supplied nitric oxide in Saccharomyces cerevisiae was modeled using an integrated framework of Bayesian network learning and experimental feedback. A Bayesian network learning algorithm was used to generate network models of transcriptional output, followed by model verification and revision through experimentation. Using this framework, we generated a network model of the yeast transcriptional response to nitric oxide and a panel of other environmental signals. We discovered two environmental triggers, the diauxic shift and glucose repression, that affected the observed transcriptional profile. The computational method predicted the transcriptional control of yeast flavohemoglobin YHB1 by glucose repression, which was subsequently experimentally verified. A freely available software application, ExpressionNet, was developed to derive Bayesian network models from a combination of gene expression profile clusters, genetic information and experimental conditions.

93 Patients With Sickle Cell Disease Pain Crises Are Often Undertreated in the Out-of-Hospital Setting: A Multi-Agency Cohort Study

We present an improved method for learning Bayesian network (BN) structures. The new approach incorporate the idea of simulated annealing algorithm (SA) into the selection operator of genetic algorithm(GA). The BN structure with the highest score is given high priority in selection, as well as the structure with lower score could also be given opportunity to be selected. That is high score prior genetic-simulated annealing algorithm to Bayesian network structure learning(GSA_BNSL).This strategy will reserve optimal gene while avoiding the premature caused by the misleading from high score individual in the population. Experiments on comparison of several BN learning algorithms are carried out using typical data set of data mining. The result indicates that the GSA_BNSL is able to obtain an optimized BN structure with higher accuracy rate.

User's personal social networks are big and cluttered, yet contain highly valuable information. Organizing users' friends into circles or communities is a fundamental task in social network research. Social network sites allow users to manually categorize their friends into social circles, however this process is laborious and inadaptable to changes. In this paper, we study novel ways of automatically determining users' social circles. We treat this task as a classification problem on a user's ego-network, a network of connections between friends. Based on Bayesian Network (BN), we develop a model for determining whether a query user Uq is in main user Um's social circle. First, we transform the original social network data to make it suitable for BN modeling, and build an Initial Bayesian Network (IBN) of Um using the state-of-the-art BN learning algorithm. Then, we propose a new method to improve the IBN by adding important parents to the class variable. Lastly, leveraging carefully designed threshold, we use the final BN to determine the existence of Uq in the social circle of U <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</sub> . Modeling social circle with BN allows us to quantify user's social circle existence with probability and run query with missing values/evidences. Using ground-truth data from Facebook and Twitter, experimental results indicate that our BN model could accurately determine user's existence in social circle and outperforms four baseline predictors, namely Naïve Bayes, IBL, OneR and J48, showing promising application potential in the social circle research area.

Chapter 11 - Molecular Phylogenetics

A new 3D object retrieval approach is proposed based on a novel Bayesian networks lightfield descriptor (BLD). To overcome the disadvantages of the existing 3D object retrieval methods, firstly, we explore Bayesian network for building a new lightfield descriptor, 3D object is put into lightfield, and multi-views information can be obtained along a sphere, and then features of images can be extracted out. The BLD of 3D object would be got according to feature sequences based on Bayesian network learning algorithm. Secondly, 3D object is retrieved based on graph model measurement and relevant feedback learning. Beneficial from the statistical learning and graph model optimization, proposed BLD is robustness as compared to the existing methods. Experimental results demonstrate that proposed approach is with better performance than the existing methods.

Background. On July 12, 2010, Boston Medical Center (BMC), the busiest emergency department (ED) in Massachusetts, with more than 100,000 adult patient visits per year, consolidated its two fully functional EDs into one. In preparation for this consolidation, BMC implemented systems changes to mitigate potential negative effects on both BMC and emergency medical services (EMS) providers, including Boston Emergency Medical Services (Boston EMS), the provider of 9-1-1 EMS to the City of Boston. Objective. To examine the impact of the closure of an ED on an urban EMS system in a setting where ambulance diversion is not allowed. Methods. We performed a before-and-after study that examined the effects of an ED closure on BMC and Boston EMS. We examined ED and Boston EMS volumes and ambulance turnaround intervals from June 1, 2010, to July 11, 2010 (preclosure) as compared with July 12, 2010, to August 26, 2010 (postclosure). Mean ED and Boston EMS volumes and Boston EMS turnaround intervals were calculated in four-hour shifts. We used multivariate analysis to analyze electronic medical systems data from BMC and Boston EMS and linear regression. We used autoregressive integrated moving average (ARIMA) models to determine the effect of the ED closure on turnaround intervals, ED volumes, and transport volumes. All analyses were adjusted for shift, ED volume, day of the week, and citywide EMS transport volumes. Results. After ED closure, there was a statistically significant increase of 0.89 minutes (p = 0.02) in the mean EMS turnaround intervals. Additionally, the total ED volume decreased by 3.67 visits per shift (p < 0.001). The ratio of patients transported by Boston EMS to BMC remained unchanged (p = 0.11) for two weeks before and two weeks after the closure. Conclusions. The closure of one ED resulted in a statistically significant increase in turnaround intervals and a significant decrease in ED volume independent of EMS volumes. In the absence of ambulance diversion, ratios of EMS turnaround intervals and EMS volumes according to hospital destination can be used as alternatives to ambulance diversion times to examine the effects of system-level changes such as closure of an ED on an urban EMS system. Key words: emergency department; EMS system; closure; impact; consolidation

During a mass gathering, some participants may receive health care for injuries or illnesses that occur during the event. In-event first responders provide initial assessment and management at the event. However, when further definitive care is required, municipal ambulance services provide additional assessment, treatment, and transport of participants to acute care settings, such as hospitals. The impact on both ambulance services and hospitals from mass-gathering events is the focus of this literature review. Aim This literature review aimed to develop an understanding of the impact of mass gatherings on local health services, specifically pertaining to in-event and external health services. This research used a systematic literature review methodology. Electronic databases were searched to find articles related to the aim of the review. Articles focused on mass-gathering health, provision of in-event health services, ambulance service transportation, and hospital utilization. Twenty-four studies were identified for inclusion in this review. These studies were all case-study-based and retrospective in design. The majority of studies (n=23) provided details of in-event first responder services. There was variation noted in reporting of the number and type of in-event health professional services at mass gatherings. All articles reported that patients were transported to hospital by the ambulance service. Only nine articles reported on patients presenting to hospital. However, details pertaining to the impact on ambulance and hospital services were not reported. There is minimal research focusing on the impact of mass gatherings on in-event and external health services, such as ambulance services and hospitals. A recommendation for future mass-gathering research and evaluation is to link patient-level data from in-event mass gatherings to external health services. This type of study design would provide information regarding the impact on health services from a mass gathering to more accurately inform future health planning for mass gatherings across the health care continuum. Ranse J , Hutton A , Keene T , Lenson S , Luther M , Bost N , Johnston ANB , Crilly J , Cannon M , Jones N , Hayes C , Burke B . Health service impact from mass gatherings: a systematic literature review. Prehosp Disaster Med. 2017;32(1):71-77.