Multiple hypothesis screening using mixtures of non-local distributions with applications to genomic studies.

The analysis of large-scale datasets, especially in biomedical contexts, frequently involves a principled screening of multiple hypotheses. The celebrated two-group model jointly models the distribution of the test statistics with mixtures of two competing densities, the null and the alternative distributions. We investigate the use of weighted densities and, in particular, non-local densities as working alternative distributions, to enforce separation from the null and thus refine the screening procedure. We show how these weighted alternatives improve various operating characteristics, such as the Bayesian false discovery rate, of the resulting tests for a fixed mixture proportion with respect to a local, unweighted likelihood approach. Parametric and nonparametric model specifications are proposed, along with efficient samplers for posterior inference. By means of a simulation study, we exhibit how our model compares with both well-established and state-of-the-art alternatives in terms of various operating characteristics. Finally, to illustrate the versatility of our method, we conduct three differential expression analyses with publicly-available datasets from genomic studies of heterogeneous nature.

Bayesian learning of multiple directed networks from observational data.

Graphical modeling represents an established methodology for identifying complex dependencies in biological networks, as exemplified in the study of co-expression, gene regulatory, and protein interaction networks. The available observations often exhibit an intrinsic heterogeneity, which impacts on the network structure through the modification of specific pathways for distinct groups, such as disease subtypes. We propose to infer the resulting multiple graphs jointly in order to benefit from potential similarities across groups; on the other hand our modeling framework is able to accommodate group idiosyncrasies. We consider directed acyclic graphs (DAGs) as network structures, and develop a Bayesian method for structural learning of multiple DAGs. We explicitly account for Markov equivalence of DAGs, and propose a suitable prior on the collection of graph spaces that induces selective borrowing strength across groups. The resulting inference allows in particular to compute the posterior probability of edge inclusion, a useful summary for representing flow directions within the network. Finally, we detail a simulation study addressing the comparative performance of our method, and present an analysis of two protein networks together with a substantive interpretation of our findings.

A Bayesian spatiotemporal statistical analysis of out-of-hospital cardiac arrests.

We propose a Bayesian spatiotemporal statistical model for predicting out-of-hospital cardiac arrests (OHCAs). Risk maps for Ticino, adjusted for demographic covariates, are built for explaining and forecasting the spatial distribution of OHCAs and their temporal dynamics. The occurrence intensity of the OHCA event in each area of interest, and the cardiac risk-based clustering of municipalities are efficiently estimated, through a statistical model that decomposes OHCA intensity into overall intensity, demographic fixed effects, spatially structured and unstructured random effects, time polynomial dependence, and spatiotemporal random effect. In the studied geography, time evolution and dependence on demographic features are robust over different categories of OHCAs, but with variability in their spatial and spatiotemporal structure. Two main OHCA incidence-based clusters of municipalities are identified.

Early diagnosis of candidemia with explainable machine learning on automatically extracted laboratory and microbiological data: results of the AUTO-CAND project.

BACKGROUND: Candidemia is associated with a heavy burden of morbidity and mortality in hospitalized patients. The availability of blood culture results could require up to 48-72 h after blood draw; thus, early treatment decisions are made in the absence of a definite diagnosis. METHODS: In this retrospective study, we assessed the performance of different supervised machine learning algorithms for the early differential diagnosis of candidemia and bacteremia in adult patients on a large dataset automatically extracted within the AUTO-CAND project. RESULTS: Overall, 12,483 episodes of candidemia (1275; 10%) or bacteremia (11,208; 90%) were included in the analysis. A random forest classifier achieved the best diagnostic performance for candidemia, with sensitivity 0.98 and specificity 0.65 on the training set (true skill statistic [TSS] = 0.63) and sensitivity 0.74 and specificity 0.57 on the test set (TSS = 0.31). Then, the random classifier was trained in the subgroup of patients with available serum ß-D-glucan (BDG) and procalcitonin (PCT) values by exploiting the feature ranking learned in the entire dataset. Although no statistically significant differences were observed from the performance measures obtained by employing BDG and PCT alone, the performance measures of the classifier that included the features selected in the entire dataset, plus BDG and PCT, were the highest in most cases. CONCLUSIONS: Random forest classifiers trained on large datasets of automatically extracted data have the potential to improve current diagnostic algorithms for candidemia. However, further development through implementation of automatically extracted clinical features may be necessary to achieve crucial improvements.

Spatio-temporal prediction model of out-of-hospital cardiac arrest: Designation of medical priorities and estimation of human resources requirement.

AIMS: To determine the out-of-hospital cardiac arrest (OHCA) rates and occurrences at municipality level through a novel statistical model accounting for temporal and spatial heterogeneity, space-time interactions and demographic features. We also aimed to predict OHCAs rates and number at municipality level for the upcoming years estimating the related resources requirement. METHODS: All the consecutive OHCAs of presumed cardiac origin occurred from 2005 until 2018 in Canton Ticino region were included. We implemented an Integrated Nested Laplace Approximation statistical method for estimation and prediction of municipality OHCA rates, number of events and related uncertainties, using age and sex municipality compositions. Comparisons between predicted and real OHCA maps validated our model, whilst comparisons between estimated OHCA rates in different yeas and municipalities identified significantly different OHCA rates over space and time. Longer-time predicted OHCA maps provided Bayesian predictions of OHCA coverages in varying stressful conditions. RESULTS: 2344 OHCAs were analyzed. OHCA incidence either progressively reduced or continuously increased over time in 6.8% of municipalities despite an overall stable spatio-temporal distribution of OHCAs. The predicted number of OHCAs accounts for 89% (2017) and 90% (2018) of the yearly variability of observed OHCAs with prediction error ≤1OHCA for each year in most municipalities. An increase in OHCAs number with a decline in the Automatic External Defibrillator availability per OHCA at region was estimated. CONCLUSIONS: Our method enables prediction of OHCA risk at municipality level with high accuracy, providing a novel approach to estimate resource allocation and anticipate gaps in demand in upcoming years.

Real-life time and distance covered by lay first responders alerted by means of smartphone-application: Implications for early initiation of cardiopulmonary resuscitation and access to automatic external defibrillators.

AIM OF THE STUDY: To investigate the distance covered by lay first responders (LFR) alerted for an out-of- hospital cardiac arrest (OHCA), evaluate the time elapsed between mission acceptance and arrival at the OHCA site, as well as the distance between the LFRs to the closest automatic external defibrillator (AED). METHODS: The LFR route, thus time, distance information, and the average speed of each responder were estimated. The same methodology was used to calculate the distance between the closest AED and the LFRs, as well as the distance between the AED and OHCA site. RESULTS: Between June 1st, 2014 and December 31st, 2017, the LFR network was activated in occasion of 484 suspected OHCAs. 710 LFRs were automatically selected by the application and accepted the mission. On average 1.5 LFRs arrived at the OHCA site. LFRs covered a distance of 1196 m (IQR 596-2314) at a median speed of 6.9 m/s (IQR 4.5-9.8) or 24.8 Km/h. In 4.4% of the cases the speed of the LFRs was compatible with a brisk walk activity (<1.5 m/sec). The total intervention time of an LFR, who first retrieved an AED and then went to the OHCA site, was longer (275 s, IQR: 184 s-414 s) compared to the total intervention time of a LFR (197 s, IQR: 120 s-306 s; p < 0.001), who went to the OHCA site directly without retrieving an AED. CONCLUSIONS: The dispatch of LFRs directly to the OHCA site instead of first retrieving the AED, significantly decreases the time to CPR initiation. More studies are needed to assess the prognostic implications on survival and neurological outcome.

Evaluating health facility access using Bayesian spatial models and location analysis methods.

BACKGROUND: Floating catchment methods have recently been applied to identify priority regions for Automated External Defibrillator (AED) deployment, to aid in improving Out of Hospital Cardiac Arrest (OHCA) survival. This approach models access as a supply-to-demand ratio for each area, targeting areas with high demand and low supply for AED placement. These methods incorporate spatial covariates on OHCA occurrence, but do not provide precise AED locations, which are critical to the initial intent of such location analysis research. Exact AED locations can be determined using optimisation methods, but they do not incorporate known spatial risk factors for OHCA, such as income and demographics. Combining these two approaches would evaluate AED placement impact, describe drivers of OHCA occurrence, and identify areas that may not be appropriately covered by AED placement strategies. There are two aims in this paper. First, to develop geospatial models of OHCA that account for and display uncertainty. Second, to evaluate the AED placement methods using geospatial models of accessibility. We first identify communities with the greatest gap between demand and supply for allocating AEDs. We then use this information to evaluate models for precise AED location deployment. METHODS: Case study data set consisted of 2802 OHCA events and 719 AEDs. Spatial OHCA occurrence was described using a geospatial model, with possible spatial correlation accommodated by introducing a conditional autoregressive (CAR) prior on the municipality-level spatial random effect. This model was fit with Integrated Nested Laplacian Approximation (INLA), using covariates for population density, proportion male, proportion over 65 years, financial strength, and the proportion of land used for transport, commercial, buildings, recreation, and urban areas. Optimisation methods for AED locations were applied to find the top 100 AED placement locations. AED access was calculated for current access and 100 AED placements. Priority rankings were then given for each area based on their access score and predicted number of OHCA events. RESULTS: Of the 2802 OHCA events, 64.28% occurred in rural areas, and 35.72% in urban areas. Additionally, over 70% of individuals were aged over 65. Supply of AEDs was less than demand in most areas. Priority regions for AED placement were identified, and access scores were evaluated for AED placement methodology by ranking the access scores and the predicted OHCA count. AED placement methodology placed AEDs in areas with the highest priority, but placed more AEDs in areas with more predicted OHCA events in each grid cell. CONCLUSION: The methods in this paper incorporate OHCA spatial risk factors and OHCA coverage to identify spatial regions most in need of resources. These methods can be used to help understand how AED allocation methods affect OHCA accessibility, which is of significant practical value for communities when deciding AED placements.