Dataset Information

Forecasting tuberculosis using diabetes-related google trends data.

ABSTRACT: Online activity-based data can be used to aid infectious disease forecasting. Our aim was to exploit the converging nature of the tuberculosis (TB) and diabetes epidemics to forecast TB case numbers. Thus, we extended TB prediction models based on traditional data with diabetes-related Google searches. We obtained data on the weekly case numbers of TB in Germany from June 8th, 2014, to May 5th, 2019. Internet search data were obtained from a Google Trends (GTD) search for 'diabetes' to the corresponding interval. A seasonal autoregressive moving average (SARIMA) model (0,1,1) (1,0,0) [52] was selected to describe the weekly TB case numbers with and without GTD as an external regressor. We cross-validated the SARIMA models to obtain the root mean squared errors (RMSE). We repeated this procedure with autoregressive feed-forward neural network (NNAR) models using 5-fold cross-validation. To simulate a data-poor surveillance setting, we also tested traditional and GTD-extended models against a hold-out dataset using a decreased 52-week-long period with missing values for training. Cross-validation resulted in an RMSE of 20.83 for the traditional model and 18.56 for the GTD-extended model. Cross-validation of the NNAR models showed a mean RMSE of 19.49 for the traditional model and 18.99 for the GTD-extended model. When we tested the models trained on a decreased dataset with missing values, the GTD-extended models achieved significantly better prediction than the traditional models (p < 0.001). The GTD-extended models outperformed the traditional models in all assessed model evaluation parameters. Using online activity-based data regarding diabetes can improve TB forecasting, but further validation is warranted.

SUBMITTER: Frauenfeld L

PROVIDER: S-EPMC7480530 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Some of the temporal variations and clock-like rhythms that govern several different health-related behaviors can be traced in near real-time with the help of search engine data. This is especially useful when studying phenomena where little or no traditional data exist. One specific area where traditional data are incomplete is the study of diurnal mood variations, or daily changes in individuals' overall mood state in relation to depression-like symptoms.The objective of this exploratory study was to analyze diurnal variations for interest in depression on the Web to discover hourly patterns of depression interest and help seeking.Hourly query volume data for 6 depression-related queries in Finland were downloaded from Google Trends in March 2017. A continuous wavelet transform (CWT) was applied to the hourly data to focus on the diurnal variation. Longer term trends and noise were also eliminated from the data to extract the diurnal variation for each query term. An analysis of variance was conducted to determine the statistical differences between the distributions of each hour. Data were also trichotomized and analyzed in 3 time blocks to make comparisons between different time periods during the day.Search volumes for all depression-related query terms showed a unimodal regular pattern during the 24 hours of the day. All queries feature clear peaks during the nighttime hours around 11 PM to 4 AM and troughs between 5 AM and 10 PM. In the means of the CWT-reconstructed data, the differences in nighttime and daytime interest are evident, with a difference of 37.3 percentage points (pp) for the term "Depression," 33.5 pp for "Masennustesti," 30.6 pp for "Masennus," 12.8 pp for "Depression test," 12.0 pp for "Masennus testi," and 11.8 pp for "Masennus oireet." The trichotomization showed peaks in the first time block (00.00 AM-7.59 AM) for all 6 terms. The search volumes then decreased significantly during the second time block (8.00 AM-3.59 PM) for the terms "Masennus oireet" (P<.001), "Masennus" (P=.001), "Depression" (P=.005), and "Depression test" (P=.004). Higher search volumes for the terms "Masennus" (P=.14), "Masennustesti" (P=.07), and "Depression test" (P=.10) were present between the second and third time blocks.Help seeking for depression has clear diurnal patterns, with significant rise in depression-related query volumes toward the evening and night. Thus, search engine query data support the notion of the evening-worse pattern in diurnal mood variation. Information on the timely nature of depression-related interest on an hourly level could improve the chances for early intervention, which is beneficial for positive health outcomes.

Project description:Type 2 diabetes leads to premature death and reduced quality of life for 8% of Americans. Nutrition management is critical to maintaining glycemic control, yet it is difficult to achieve due to the high individual differences in glycemic response to nutrition. Anticipating glycemic impact of different meals can be challenging not only for individuals with diabetes, but also for expert diabetes educators. Personalized computational models that can accurately forecast an impact of a given meal on an individual's blood glucose levels can serve as the engine for a new generation of decision support tools for individuals with diabetes. However, to be useful in practice, these computational engines need to generate accurate forecasts based on limited datasets consistent with typical self-monitoring practices of individuals with type 2 diabetes. This paper uses three forecasting machines: (i) data assimilation, a technique borrowed from atmospheric physics and engineering that uses Bayesian modeling to infuse data with human knowledge represented in a mechanistic model, to generate real-time, personalized, adaptable glucose forecasts; (ii) model averaging of data assimilation output; and (iii) dynamical Gaussian process model regression. The proposed data assimilation machine, the primary focus of the paper, uses a modified dual unscented Kalman filter to estimate states and parameters, personalizing the mechanistic models. Model selection is used to make a personalized model selection for the individual and their measurement characteristics. The data assimilation forecasts are empirically evaluated against actual postprandial glucose measurements captured by individuals with type 2 diabetes, and against predictions generated by experienced diabetes educators after reviewing a set of historical nutritional records and glucose measurements for the same individual. The evaluation suggests that the data assimilation forecasts compare well with specific glucose measurements and match or exceed in accuracy expert forecasts. We conclude by examining ways to present predictions as forecast-derived range quantities and evaluate the comparative advantages of these ranges.

Dataset Information

Forecasting tuberculosis using diabetes-related google trends data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets