Dataset Information

Continuous updating of individual headache forecasting models using Bayesian methods.

ABSTRACT:

Objective

To illustrate the benefits of deploying individual headache forecasting models using continuous updating with Bayesian methods.

Background

The ability to reliably forecast headache attacks within an individual over time would enhance the study of attacks and allow preemptive treatment. However, deploying a suitable forecasting model in a clinical setting will likely involve several unique challenges related to heterogeneity in the predictor weights, limited or sparse data, and the need for a quick "warm-up." The use of Bayesian methods offers solutions to each of these specific challenges.

Methods

This was a post hoc analysis of a cohort study of individuals with episodic migraine attacks. Individuals completed daily diaries that allowed the estimation of several forecasting models, each using different types of ancillary information incorporated into formal prior probability distributions. An in silico analysis was conducted that mimicked the deployment of these models in a clinical-like setting where the parameters of the models were continuously updated and evaluated each day using root mean square error (RMSE).

Results

Individuals (N = 95) were followed for 50 days and contributed 3359 days of nonmissing diary data. During the observation period, there were 1293/3359 (38.5%) days with a headache attack. Self-reported baseline headache frequency was associated with the corresponding predicted probability of future attacks, r = 0.15-0.39. At Day 25, the correlation between baseline information and predicted attack likelihood was r = 0.29 (95% CI: 0.09-0.47). Additionally, the use of prior probability distributions for model parameters improved the model fit, especially early in the deployment of the models (e.g., Day 5 RMSE 0.45 vs. 0.43). Models using informative prior probability distributions outperformed the models estimated without this information during the first 42 days of observation, although performance became more similar as more data were collected.

Conclusions

This analysis demonstrates the value of Bayesian methods in using additional available information to improve forecasting model performance, especially early in the deployment of a forecasting model. To obtain the full value of such models or to apply any model in clinical settings, a model with adequate discrimination and calibration will be needed.

SUBMITTER: Houle TT

PROVIDER: S-EPMC8672809 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Continuous updating of individual headache forecasting models using Bayesian methods.

Houle Timothy T TT Deng Hao H Tegeler Charles H CH Turner Dana P DP

Headache 20210826 8

<h4>Objective</h4>To illustrate the benefits of deploying individual headache forecasting models using continuous updating with Bayesian methods.<h4>Background</h4>The ability to reliably forecast headache attacks within an individual over time would enhance the study of attacks and allow preemptive treatment. However, deploying a suitable forecasting model in a clinical setting will likely involve several unique challenges related to heterogeneity in the predictor weights, limited or sparse dat ...[more]

PMID: 34435659

Similar Datasets

Project description:Harvesting large carnivores can be a management tool for meeting politically set goals for their desired abundance. However, harvesting carnivores creates its own set of conflicts in both society and among conservation professionals, where one consequence is a need to demonstrate that management is sustainable, evidence-based, and guided by science. Furthermore, because large carnivores often also have high degrees of legal protection, harvest quotas have to be carefully justified and constantly adjusted to avoid damaging their conservation status. We developed a Bayesian state-space model to support adaptive management of Eurasian lynx harvesting in Scandinavia. The model uses data from the annual monitoring of lynx abundance and results from long-term field research on lynx biology, which has provided detailed estimates of key demographic parameters. We used the model to predict the probability that the forecasted population size will be below or above the management objectives when subjected to different harvest quotas. The model presented here informs decision makers about the policy risks of alternative harvest levels. Earlier versions of the model have been available for wildlife managers in both Sweden and Norway to guide lynx harvest quotas and the model predictions showed good agreement with observations. We combined monitoring data with data on vital rates and were able to estimate unobserved additional mortality rates, which are most probably due to poaching. In both countries, the past quota setting strategy suggests that there has been a de facto threshold strategy with increasing proportion, which means that there is no harvest below a certain population size, but above this threshold there is an increasing proportion of the population harvested as the population size increases. The annual assessment of the monitoring results, the use of forecasting models, and a threshold harvest approach to quota setting will all reduce the risk of lynx population sizes moving outside the desired goals. The approach we illustrate could be adapted to other populations of mammals worldwide.

Project description:BackgroundFloating 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.MethodsCase 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.ResultsOf 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.ConclusionThe 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.

Project description:Many previous studies on visual search have reported inter-trial effects, that is, observers respond faster when some target property, such as a defining feature or dimension, or the response associated with the target repeats versus changes across consecutive trial episodes. However, what processes drive these inter-trial effects is still controversial. Here, we investigated this question using a combination of Bayesian modeling of belief updating and evidence accumulation modeling in perceptual decision-making. In three visual singleton ('pop-out') search experiments, we explored how the probability of the response-critical states of the search display (e.g., target presence/absence) and the repetition/switch of the target-defining dimension (color/ orientation) affect reaction time distributions. The results replicated the mean reaction time (RT) inter-trial and dimension repetition/switch effects that have been reported in previous studies. Going beyond this, to uncover the underlying mechanisms, we used the Drift-Diffusion Model (DDM) and the Linear Approach to Threshold with Ergodic Rate (LATER) model to explain the RT distributions in terms of decision bias (starting point) and information processing speed (evidence accumulation rate). We further investigated how these different aspects of the decision-making process are affected by different properties of stimulus history, giving rise to dissociable inter-trial effects. We approached this question by (i) combining each perceptual decision making model (DDM or LATER) with different updating models, each specifying a plausible rule for updating of either the starting point or the rate, based on stimulus history, and (ii) comparing every possible combination of trial-wise updating mechanism and perceptual decision model in a factorial model comparison. Consistently across experiments, we found that the (recent) history of the response-critical property influences the initial decision bias, while repetition/switch of the target-defining dimension affects the accumulation rate, likely reflecting an implicit 'top-down' modulation process. This provides strong evidence of a disassociation between response- and dimension-based inter-trial effects.

Project description:Importance:Whether surgery or radiotherapy is the preferred treatment for patients with localized prostate cancer continues to be debated, and randomized clinical trials cannot yet fully address this question. Furthermore, there may be heterogeneity in responses, and the optimal treatment for a patient will depend on his clinical and tumor characteristics. Objectives:To use a unified statistical approach to compare the association of surgery and radiotherapy with both metastatic clinical failure (CF) and survival in localized prostate cancer and to develop an online calculator for individualized, treatment-specific outcome prediction. Design, Setting, and Participants:Cohort study for statistical analysis and development of individualized predictions using Bayesian multistate models that jointly consider both CF and survival and adjust for confounding factors. This study used data from patients treated at the University of Michigan between January 1, 1996, and July 1, 2013, with detailed information on treatment, patient and tumor characteristics, and outcomes. Primary analyses were performed in 2017 and 2018. Participants were a cohort of 4544 patients with localized prostate cancer undergoing primary treatment. Exposures:Radical prostatectomy and external beam radiotherapy. Main Outcomes and Measures:The clinical outcomes were metastatic CF, death after CF, and death from other causes. The adjustment factors were age, prostate gland volume, prostate-specific antigen level, comorbidities, Gleason score, perineural invasion, cT category, race, and treatment year. An online calculator was developed to estimate risks for multiple outcomes for any patient based on 2 treatment choices and on his clinical and tumor characteristics. Results:Among 4544 men (mean [SD] age, 61.2 [8.0] years), 3769 underwent radical prostatectomy, 775 received external beam radiotherapy, 157 (3.5%) had CF, 90 (2.0%) died after CF, and 378 (8.3%) died of other causes. Across all patients, there was no significant difference in risk of CF for surgery vs radiotherapy (hazard ratio, 0.80; 95% CI, 0.52-1.23). However, using multistate models, in some cases individualized predictions resulted in different expected outcomes between surgery and radiotherapy for a given patient. Conclusions and Relevance:In this study, after adjustment for measured confounders, the hazard of CF was similar between treatments on average. However, these data indicate a greater oncologic benefit for some individual patients if treated with surgery and for other patients if treated with radiotherapy. Individualized predictions provide a novel approach to facilitate treatment decision making.

Project description:BackgroundMonkeypox virus is gaining attention due to its severity and spread among people. This study sheds light on the modeling and forecasting of new monkeypox cases. Knowledge about the future situation of the virus using a more accurate time series and stochastic models is required for future actions and plans to cope with the challenge.MethodsWe conduct a side-by-side comparison of the machine learning approach with the traditional time series model. The multilayer perceptron model (MLP), a machine learning technique, and the Box-Jenkins methodology, also known as the ARIMA model, are used for classical modeling. Both methods are applied to the Monkeypox cumulative data set and compared using different model selection criteria such as root mean square error, mean square error, mean absolute error, and mean absolute percentage error.ResultsWith a root mean square error of 150.78, the monkeypox series follows the ARIMA (7,1,7) model among the other potential models. Comparatively, we use the multilayer perceptron (MLP) model, which employs the sigmoid activation function and has a different number of hidden neurons in a single hidden layer. The root mean square error of the MLP model, which uses a single input and ten hidden neurons, is 54.40, significantly lower than that of the ARIMA model. The actual confirmed cases versus estimated or fitted plots also demonstrate that the multilayer perceptron model has a better fit for the monkeypox data than the ARIMA model.Conclusions and recommendationWhen it comes to predicting monkeypox, the machine learning method outperforms the traditional time series. A better match can be achieved in future studies by applying the extreme learning machine model (ELM), support vector machine (SVM), and some other methods with various activation functions. It is thus concluded that the selected data provide a real picture of the virus. If the situations remain the same, governments and other stockholders should ensure the follow-up of Standard Operating Procedures (SOPs) among the masses, as the trends will continue rising in the upcoming 10 days. However, governments should take some serious interventions to cope with the virus.LimitationIn the ARIMA models selected for forecasting, we did not incorporate the effect of covariates such as the effect of net migration of monkeypox virus patients, government interventions, etc.

Dataset Information

Continuous updating of individual headache forecasting models using Bayesian methods.

Objective

Background

Methods

Results

Conclusions

Publications

Continuous updating of individual headache forecasting models using Bayesian methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets