Good times bad times: Automated forecasting of seasonal cryptosporidiosis in Ontario using machine learning

Berke, Olaf; Trotz-Williams, Lise A.; Montigny, Simon de

doi:10.14745/ccdr.v46i06a07

Cited by 6 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the choice of approach should depend on the goals of the study and the characteristics of the data. Finally, these methods can also be used to validate the findings of the other [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data

et al. 2022

View full text Add to dashboard Cite

Background Identification of biomarkers, which are measurable characteristics of biological datasets, can be challenging. Although amplicon sequence variants (ASVs) can be considered potential biomarkers, identifying important ASVs in high-throughput sequencing datasets is challenging. Noise, algorithmic failures to account for specific distributional properties, and feature interactions can complicate the discovery of ASV biomarkers. In addition, these issues can impact the replicability of various models and elevate false-discovery rates. Contemporary machine learning approaches can be leveraged to address these issues. Ensembles of decision trees are particularly effective at classifying the types of data commonly generated in high-throughput sequencing (HTS) studies due to their robustness when the number of features in the training data is orders of magnitude larger than the number of samples. In addition, when combined with appropriate model introspection algorithms, machine learning algorithms can also be used to discover and select potential biomarkers. However, the construction of these models could introduce various biases which potentially obfuscate feature discovery. Results We developed a decision tree ensemble, LANDMark, which uses oblique and non-linear cuts at each node. In synthetic and toy tests LANDMark consistently ranked as the best classifier and often outperformed the Random Forest classifier. When trained on the full metabarcoding dataset obtained from Canada’s Wood Buffalo National Park, LANDMark was able to create highly predictive models and achieved an overall balanced accuracy score of 0.96 ± 0.06. The use of recursive feature elimination did not impact LANDMark’s generalization performance and, when trained on data from the BE amplicon, it was able to outperform the Linear Support Vector Machine, Logistic Regression models, and Stochastic Gradient Descent models (p ≤ 0.05). Finally, LANDMark distinguishes itself due to its ability to learn smoother non-linear decision boundaries. Conclusions Our work introduces LANDMark, a meta-classifier which blends the characteristics of several machine learning models into a decision tree and ensemble learning framework. To our knowledge, this is the first study to apply this type of ensemble approach to amplicon sequencing data and we have shown that analyzing these datasets using LANDMark can produce highly predictive and consistent models.

show abstract

Section: Introductionmentioning

confidence: 99%

LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Based on a simulation study employing the root mean squared prediction error (RMSE) and the mean absolute prediction error (MAE) as accuracy measures, the three ANNs outperformed the SARIMA modelling approach. Contrary to this, Berke et al forecast the monthly cryptosporidiosis incidence for Ontario and found no evidence for better performance of the ANN over the SARIMA approach as measured by the MAE and RMSE (Berke et al, 2020).…”

Section: Introductionmentioning

confidence: 95%

“…The NNAR is denoted similar to that of SARIMA models and as follows (Berke et al, 2020) Forecasts from the SARIMA model and the NNAR were compared through the Diebold-Mariano test (Diebold & Mariano, 1995).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting seasonal influenza activity in Canada—Comparing seasonal Auto‐Regressive integrated moving average and artificial neural network approaches for public health preparedness

Orang,

Berke,

Poljak

et al. 2024

Zoonoses and Public Health

Self Cite

View full text Add to dashboard Cite

IntroductionPublic health preparedness is based on timely and accurate information. Time series forecasting using disease surveillance data is an important aspect of preparedness. This study compared two approaches of time series forecasting: seasonal auto‐regressive integrated moving average (SARIMA) modelling and the artificial neural network (ANN) algorithm. The goal was to model weekly seasonal influenza activity in Canada using SARIMA and compares its predictive accuracy, based on root mean square prediction error (RMSE) and mean absolute prediction error (MAE), to that of an ANN.MethodsAn initial SARIMA model was fit using automated model selection by minimizing the Akaike information criterion (AIC). Further inspection of the autocorrelation function and partial autocorrelation function led to ‘manual’ model improvements. ANNs were trained iteratively, using an automated process to minimize the RMSE and MAE.ResultsA total of 378, 462 cases of influenza was reported in Canada from the 2010–2011 influenza season to the end of the 2019–2020 influenza season, with an average yearly incidence risk of 20.02 per 100,000 population. Automated SARIMA modelling was the better method in terms of forecasting accuracy (per RMSE and MAE). However, the ANN correctly predicted the peak week of disease incidence while the other models did not.ConclusionBoth the ANN and SARIMA models have shown to be capable tools in forecasting seasonal influenza activity in Canada. It was shown that applying both in tandem is beneficial, SARIMA better forecasted overall incidence while ANN correctly predicted the peak week.

show abstract

“…e results show that, compared to traditional one-dimensional FPCA and SARIMA, the combination of FPCA and time series analysis is more suitable for runoff prediction. Berke [11] et al used the ANN-SARIMA model to predict the monthly incidence of cryptosporidiosis and used MAPE and RMSE to check the error. e results show that the ANN-SARIMA model can effectively predict the public health time series of the monitoring system.…”

Section: Introductionmentioning

confidence: 99%

The Offset Azimuth Prediction of Light Buoy Based on Markov Chain Optimization Multiplicative Seasonal Model

Ren

Zhou

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Aimed at the problem of the large error caused by uncertain factors in the fitting process of the traditional multiplicative seasonal model, the advantages of the Markov chain in this study are applied to the multiplicative seasonal model to optimize the prediction results. Based on the residual value between the theoretical and actual values, the values of different intervals are divided into states. The transition probability matrix is established through different probabilities; then, the weighted sum of different prediction probabilities is carried out to select the optimal prediction state. The real number of Meizhou Bay portlight buoys is used to verify the prediction effect of the model, and MAE, MAPE, RMSE, RRMSE, SSE, R2 are used to calculate the error between the predicted value and the actual value. The results show that compared to the traditional multiplicative seasonal model and other prediction models, the prediction MAE of the MC-SARIMA model is decreased by 2.19003794, the MAPE is decreased by 0.66%, the RMSE is decreased by 2.092671823, the RRMSE is decreased by 0.006221352, the SSE is decreased by 404.0231931, and the R2 is increased by 0.224686247. It shows that the multiplicative seasonal model optimized by the Markov chain can predict the azimuth data of the light buoy more effectively than the traditional multiplicative seasonal model and other prediction models.

show abstract

Good times bad times: Automated forecasting of seasonal cryptosporidiosis in Ontario using machine learning

Cited by 6 publications

References 11 publications

LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data

LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data

Forecasting seasonal influenza activity in Canada—Comparing seasonal Auto‐Regressive integrated moving average and artificial neural network approaches for public health preparedness

The Offset Azimuth Prediction of Light Buoy Based on Markov Chain Optimization Multiplicative Seasonal Model

Contact Info

Product

Resources

About