Key result
Autoregressive Neural Networks outperform ARIMA models, predicting fasting glucose accurately in ~73% of cases.
Why the study?
Accurate prediction of glucose levels in diabetic patients using time series algorithms is needed to improve management strategies.
ARIMA may enhance univariate glucose forecasting in diabetes; leaves open prospective validation before any clinical adoption.
This work presents a comparison between two algorithms for the prediction of glucose levels in diabetic patients by using a univariate time series. The algorithms are applied to the history of fasting glucose levels to predict the five following values. The comparison is performed between 1) The Autoregressive Neural Networks (ARNN) and 2) The autoregressive integrated moving average (ARIMA) models. A total of 70 series are analyzed, and we show that the results obtained for the ARIMA model have error percentages higher than 25% of the predicted value to the expected value. In contrast, in 73% of the cases, the percentage error was less than 25% for the Autoregressive Neural Networks.
No takes yet. Share an insight, caveat, or question.
Vera et al. (2021) studied Diabetes (n=70). Autoregressive Neural Networks (ARNN) vs. Autoregressive integrated moving average (ARIMA) models was evaluated on Percentage error less than 25% between predicted and expected fasting glucose values. Autoregressive Neural Networks predicted fasting glucose levels with a percentage error of less than 25% in 73% of cases, whereas ARIMA models yielded error percentages higher than 25%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: