A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis

BACKGROUND

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important.

OBJECTIVE

In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity.

METHODS

PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events.

RESULTS

In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia.

CONCLUSIONS

Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced.

TRIAL REGISTRATION

PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Long-Term Prediction of Blood Glucose Levels in Type 1 Diabetes Using a CNN-LSTM-Based Deep Neural Network

BACKGROUND

In this work, we leverage state-of-the-art deep learning-based algorithms for blood glucose (BG) forecasting in people with type 1 diabetes.

METHODS

We propose stacks of convolutional neural network and long short-term memory units to predict BG level for 30-, 60-, and 90-minute prediction horizon (PH), given historical glucose measurements, meal information, and insulin intakes. The evaluation was performed on two data sets, Replace-BG and DIAdvisor, representative of free-living conditions and in-hospital setting, respectively.

RESULTS

For 90-minute PH, our model obtained mean absolute error of 17.30 ± 2.07 and 18.23 ± 2.97 mg/dL, root mean square error of 23.45 ± 3.18 and 25.12 ± 4.65 mg/dL, coefficient of determination of 84.13 ± 4.22% and 82.34 ± 4.54%, and in terms of the continuous glucose-error grid analysis 94.71 ± 3.89% and 91.71 ± 4.32% accurate predictions, 1.81 ± 1.06% and 2.51 ± 0.86% benign errors, and 3.47 ± 1.12% and 5.78 ± 1.72% erroneous predictions, for Replace-BG and DIAdvisor data sets, respectively.

CONCLUSION

Our investigation demonstrated that our method achieved superior glucose forecasting compared with existing approaches in the literature, and thanks to its generalizability showed potential for real-life applications.

Constrained IoT-Based Machine Learning for Accurate Glycemia Forecasting in Type 1 Diabetes Patients

Individuals with diabetes mellitus type 1 (DM1) tend to check their blood sugar levels multiple times daily and utilize this information to predict their future glycemic levels. Based on these predictions, patients decide on the best approach to regulate their glucose levels with considerations such as insulin dosage and other related factors. Nevertheless, modern developments in Internet of Things (IoT) technology and innovative biomedical sensors have enabled the constant gathering of glucose level data using continuous glucose monitoring (CGM) in addition to other biomedical signals. With the use of machine learning (ML) algorithms, glycemic level patterns can be modeled, enabling accurate forecasting of this variable. Constrained devices have limited computational power, making it challenging to run complex machine learning algorithms directly on these devices. However, by leveraging edge computing, using lightweight machine learning algorithms, and performing preprocessing and feature extraction, it is possible to run machine learning algorithms on constrained devices despite these limitations. In this paper we test the burdens of some constrained IoT devices, probing that it is feasible to locally predict glycemia using a smartphone, up to 45 min in advance and with acceptable accuracy using random forest.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.

Marginal structural models using calibrated weights with SuperLearner: application to type II diabetes cohort

As different scientific disciplines begin to converge on machine learning for causal inference, we demonstrate the application of machine learning algorithms in the context of longitudinal causal estimation using electronic health records. Our aim is to formulate a marginal structural model for estimating diabetes care provisions in which we envisioned hypothetical (i.e. counterfactual) dynamic treatment regimes using a combination of drug therapies to manage diabetes: metformin, sulfonylurea and SGLT-2i. The binary outcome of diabetes care provisions was defined using a composite measure of chronic disease prevention and screening elements [27] including (i) primary care visit, (ii) blood pressure, (iii) weight, (iv) hemoglobin A1c, (v) lipid, (vi) ACR, (vii) eGFR and (viii) statin medication. We used several statistical learning algorithms to describe causal relationships between the prescription of three common classes of diabetes medications and quality of diabetes care using the electronic health records contained in National Diabetes Repository. In particular, we generated an ensemble of statistical learning algorithms using the SuperLearner framework based on the following base learners: (i) least absolute shrinkage and selection operator, (ii) ridge regression, (iii) elastic net, (iv) random forest, (v) gradient boosting machines, and (vi) neural network. Each statistical learning algorithm was fitted using the pseudo-population generated from the marginalization of the time-dependent confounding process. Covariate balance was assessed using the longitudinal (i.e. cumulative-time product) stabilized weights with calibrated restrictions. Our results indicated that the treatment drop-in cohorts (with respect to metformin, sulfonylurea and SGLT-2i) may have improved diabetes care provisions in relation to treatment naive (i.e. no treatment) cohort. As a clinical utility, we hope that this article will facilitate discussions around the prevention of adverse chronic outcomes associated with type II diabetes through the improvement of diabetes care provisions in primary care.

Identifying Prenatal and Postnatal Determinants of Infant Growth: A Structural Equation Modelling Based Cohort Analysis

Background: The growth and maturation of infants reflect their overall health and nutritional status. The purpose of this study is to examine the associations of prenatal and early postnatal factors with infant growth (IG). Methods: A data-driven model was constructed by structural equation modelling to examine the relationships between pre- and early postnatal environmental factors and IG at age 12 months. The IG was a latent variable created from infant weight and waist circumference. Data were obtained on 274 mother–child pairs during pregnancy and the postnatal periods. Results: Maternal pre-pregnancy BMI emerged as an important predictor of IG with both direct and indirect (mediated through infant birth weight) effects. Infants who gained more weight from birth to 6 months and consumed starchy foods daily at age 12 months, were more likely to be larger by age 12 months. Infant physical activity (PA) levels also emerged as a determinant. The constructed model provided a reasonable fit (χ² (11) = 21.5, p < 0.05; RMSEA = 0.07; CFI = 0.94; SRMR = 0.05) to the data with significant pathways for all examined variables. Conclusion: Promoting healthy weight amongst women of child bearing age is important in preventing childhood obesity, and increasing daily infant PA is as important as a healthy infant diet.

Automated Landslide-Risk Prediction Using Web GIS and Machine Learning Models

Spatial susceptible landslide prediction is the one of the most challenging research areas which essentially concerns the safety of inhabitants. The novel geographic information web (GIW) application is proposed for dynamically predicting landslide risk in Chiang Rai, Thailand. The automated GIW system is coordinated between machine learning technologies, web technologies, and application programming interfaces (APIs). The new bidirectional long short-term memory (Bi-LSTM) algorithm is presented to forecast landslides. The proposed algorithm consists of 3 major steps, the first of which is the construction of a landslide dataset by using Quantum GIS (QGIS). The second step is to generate the landslide-risk model based on machine learning approaches. Finally, the automated landslide-risk visualization illustrates the likelihood of landslide via Google Maps on the website. Four static factors are considered for landslide-risk prediction, namely, land cover, soil properties, elevation and slope, and a single dynamic factor i.e., precipitation. Data are collected to construct a geospatial landslide database which comprises three historical landslide locations—Phu Chifa at Thoeng District, Ban Pha Duea at Mae Salong Nai, and Mai Salong Nok in Mae Fa Luang District, Chiang Rai, Thailand. Data collection is achieved using QGIS software to interpolate contour, elevation, slope degree and land cover from the Google satellite images, aerial and site survey photographs while the physiographic and rock type are on-site surveyed by experts. The state-of-the-art machine learning models have been trained i.e., linear regression (LR), artificial neural network (ANN), LSTM, and Bi-LSTM. Ablation studies have been conducted to determine the optimal parameters setting for each model. An enhancement method based on two-stage classifications has been presented to improve the landslide prediction of LSTM and Bi-LSTM models. The landslide-risk prediction performances of these models are subsequently evaluated using real-time dataset and it is shown that Bi-LSTM with Random Forest (Bi-LSTM-RF) yields the best prediction performance. Bi-LSTM-RF model has improved the landslide-risk predicting performance over LR, ANNs, LSTM, and Bi-LSTM in terms of the area under the receiver characteristic operator (AUC) scores by 0.42, 0.27, 0.46, and 0.47, respectively. Finally, an automated web GIS has been developed and it consists of software components including the trained models, rainfall API, Google API, and geodatabase. All components have been interfaced together via JavaScript and Node.js tool.

Classification accuracy and functional difference prediction in different brain regions of drug abuser prefrontal lobe basing on machine-learning

Taking different types of addictive drugs such as methamphetamine, heroin, and mixed drugs causes brain functional Changes. Based on the prefrontal functional near-infrared spectroscopy, this study was designed with an experimental paradigm that included the induction of resting and drug addiction cravings. Hemoglobin concentrations of 30 drug users (10 on methamphetamine, 10 on heroin, and 10 on mixed type) were collected. For these three types of individuals, the convolutional neural networks (CNN) was designed to classify eight Brodmann areas and the entire prefrontal area, and the average accuracy of the three classifications on each functional area was obtained. As a result, the classification accuracy was lower on the left side than on the right in the dorsolateral prefrontal cortex (DLPFC) of the drug users, while it was higher on the left than on the right in the ventrolateral prefrontal cortex (VLPFC), frontopolar prefrontal cortex (FPC), and orbitofrontal cortex (OFC). Then the differences in eight functional areas between the three types of individuals were statistically analyzed, and results showed significant differences in the right VLPFC and right OFC.