Causality analysis in type 1 diabetes mellitus with application to blood glucose level prediction

Generative deep learning for the development of a type 1 diabetes simulator

BACKGROUND

Type 1 diabetes (T1D) simulators, crucial for advancing diabetes treatments, often fall short of capturing the entire complexity of the glucose-insulin system due to the imprecise approximation of the physiological models. This study introduces a simulation approach employing a conditional deep generative model. The aim is to overcome the limitations of existing T1D simulators by synthesizing virtual patients that more accurately represent the entire glucose-insulin system physiology.

METHODS

Our methodology utilizes a sequence-to-sequence generative adversarial network to simulate virtual T1D patients causally. Causality is embedded in the model by introducing shifted input-output pairs during training, with a 90-min shift capturing the impact of input insulin and carbohydrates on blood glucose. To validate our approach, we train and evaluate the model using three distinct datasets, each consisting of 27, 12, and 10 T1D patients, respectively. In addition, we subject the trained model to further validation for closed-loop therapy, employing a state-of-the-art controller.

RESULTS

The generated patients display statistical similarity to real patients when evaluated on the time-in-range results for each of the standard blood glucose ranges in T1D management along with means and variability outcomes. When tested for causality, authentic causal links are identified between the insulin, carbohydrates, and blood glucose levels of the virtual patients. The trained generative model demonstrates behaviours that are closer to reality compared to conventional T1D simulators when subjected to closed-loop insulin therapy using a state-of-the-art controller.

CONCLUSIONS

These results highlight our approach's capability to accurately capture physiological dynamics and establish genuine causal relationships, holding promise for enhancing the development and evaluation of therapies in diabetes.

Primary driving factors of ecological environment system change based on directed weighted network illustrating with the Three-River Headwaters Region

The primary driving factors of ecological environment change have received significant attention. However, previous research methods for identifying the main drivers of ecological environment change have primarily relied on correlation analysis and regression analysis. While these methods can reveal co-occurrences, associations, and correlations among elemental characteristics, they often struggle to uncover the deep-seated interactions among elements within complex, unstable, nonlinear, and high-dimensional systems. To address this, we used the Three-River Headwaters Region as a case study and introduced a complex network model from the perspective of the ecological environment system to investigate the main driving factors of ecological environment change. In our analysis, we considered 12 factors related to the atmosphere, hydrology, vegetation, and soil, including evaporation, long-wave radiation, short-wave radiation, specific humidity, soil temperature, precipitation rate, soil water content, air temperature, air pressure, vegetation normalization index, wind speed, and natural surface runoff. Watersheds were selected as the fundamental units for constructing ecological environment datasets. We applied the Ensemble Empirical Mode Decomposition (EEMD) method and Hilbert-Huang Transform (HHT) to analyze causal relationships between time series pairs and constructed two directed weighted network models based on sub-catchments. The results showed that both network models yielded consistent conclusions, with the sparse network exhibiting higher efficiency. Radiation and temperature were identified as the primary driving factors of ecosystem change, and the water cycle was determined to be the ultimate manifestation of ecological system change throughout the Three-River Headwaters Region. Furthermore, based on node out-strength, we generated a vegetation protection priority map.

Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion

Blood glucose level prediction is a critical aspect of diabetes management. It enables individuals to make informed decisions about their insulin dosing, diet, and physical activity. This, in turn, improves their quality of life and reduces the risk of chronic and acute complications. One conundrum in developing time-series forecasting models for blood glucose level prediction is to determine an appropriate length for look-back windows. On the one hand, studying short histories foists the risk of information incompletion. On the other hand, analysing long histories might induce information redundancy due to the data shift phenomenon. Additionally, optimal lag lengths are inconsistent across individuals because of the domain shift occurrence. Therefore, in bespoke analysis, either optimal lag values should be found for each individual separately or a globally suboptimal lag value should be used for all. The former approach degenerates the analysis's congruency and imposes extra perplexity. With the latter, the fine-tunned lag is not necessarily the optimum option for all individuals. To cope with this challenge, this work suggests an interconnected lag fusion framework based on nested meta-learning analysis that improves the accuracy and precision of predictions for personalised blood glucose level forecasting. The proposed framework is leveraged to generate blood glucose prediction models for patients with type 1 diabetes by scrutinising two well-established publicly available Ohio type 1 diabetes datasets. The models developed undergo vigorous evaluation and statistical analysis from mathematical and clinical perspectives. The results achieved underpin the efficacy of the proposed method in blood glucose level time-series prediction analysis.