Multiple Linear Regression and Artificial Neural Network to Predict Blood Glucose in Overweight Patients

Predicting three-month fasting blood glucose and glycated hemoglobin changes in patients with type 2 diabetes mellitus based on multiple machine learning algorithms

Fasting blood glucose (FBG) and glycosylated hemoglobin (HbA1c) are key indicators reflecting blood glucose control in type 2 diabetes mellitus (T2DM) patients. The purpose of this study is to establish a predictive model for blood glucose changes in T2DM patients after 3 months of treatment, achieving personalized treatment.A retrospective study was conducted on type 2 diabetes mellitus real-world medical data from 4 cities in Sichuan Province, China from January 2015 to December 2020. After data preprocessing, data inputting, data sampling, and feature screening, 16 kinds of machine learning methods were used to construct prediction models, and 5 prediction models with the best prediction performance were screened respectively. A total of 100,000 cases were included to establish the FBG model, and 2,169 cases were established to establish the HbA1c model. The best prediction model both of FBG and HbA1c finally obtained are realized by ensemble learning and modified random forest inputting, the AUC values are 0.819 and 0.970, respectively. The most important indicators of the FBG and HbA1c prediction model were FBG and HbA1c. Medication compliance, follow-up outcome, dietary habits, BMI, and waist circumference also had a greater impact on FBG levels. The prediction accuracy of the models of the two blood glucose control indicators is high and has certain clinical applicability.HbA1c and FBG are mutually important predictors, and there is a close relationship between them.

Fuzzy identification of bioactive components for different efficacies of rhubarb by the back propagation neural network association analysis of UPLC-Q-TOF/MSE and integrated effects

Background

Rhei Radix et Rhizoma (rhubarb), as one of the typical representatives of multi-effect traditional Chinese medicines (TCMs), has been utilized in the treatment of various diseases due to its multicomponent nature. However, there are few systematic investigations for the corresponding effect of individual components in rhubarb. Hence, we aimed to develop a novel strategy to fuzzily identify bioactive components for different efficacies of rhubarb by the back propagation (BP) neural network association analysis of ultra-performance liquid chromatography/quadrupole time-of-flight mass spectrometry for every data (UPLC-Q-TOF/MS^E) and integrated effects.

Methods

Through applying the fuzzy chemical identification, most components of rhubarb were classified into different chemical groups. Meanwhile the integration effect values of different efficacies can be determined by animal experiment evaluation and multi-attribute comprehensive indexes. Then the BP neural network was employed for association analysis of components and different efficacies by correlating the component contents determined from UPLC-Q-TOF/MS^E profiling and the integration effect values. Finally, the effect contribution of one type of components may be totaled to demonstrate the universal and individual characters for different efficacies of rhubarb.

Results

It suggested that combined anthraquinones, flavanols and their polymers may be the universal character to the multi-functional properties of rhubarb. Other components contributed to the individuality of rhubarb efficacies, including stilbene glycosides, anthranones and their dimers, free anthraquinones, chromones, gallic acid and gallotannins, butyrylbenzenes and their glycosides.

Conclusions

Our findings demonstrated that the bioactive components for different efficacies of rhubarb were not exactly the same and can be systematically differentiated by the network-oriented strategy. These efforts will advance our knowledge and understanding of the bioactive components in rhubarb and provide scientific evidence to support the expansion of its use in clinical applications and the further development of some products based on this medicinal herb.

Supplementary information

The online version contains supplementary material available at 10.1186/s13020-022-00612-9.

Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network

PURPOSE

Timely diagnosis of diabetic retinopathy (DR) can significantly improve the prognosis of patients. In this study, we established a prediction model by analyzing the relationship between diabetic retinopathy and related metabolic and biochemical indicators.

METHODS

A total of 427 type 2 diabetes mellitus (T2DM) patients were selected from the datadryad website data. Logistic regression (MLR) was used to input layer variables of the model were screened. Then, Tan-Sigmoid was selected as the transfer function of the hidden layer node, and the linear function was used as the output layer function to establish the back propagation artificial neural network (BP-ANN) model. The model was applied to 183 patients with type 2 diabetes mellitus (T2DM) in our hospital to predict DR.

RESULTS

A total of 167 patients (39.2%) with DR were obtained from the Datadryad database. Input variables were screened by MLR model, and it was concluded that the age, sex, albumin and creatinine, diabetes course were independently associated with the occurrence of DR. The above variables were used to establish BP-ANN model. The area under receiver operating characteristic curve (AUC) was significantly higher than that of MLR model (0.88 vs 0.74, P<0.05), the probability threshold of the model was 0.3. Type 2 diabetes mellitus (T2DM) were selected in our hospital, including 92 patients with DR (50.2%). The above BP-ANN model was used to predict the incidence of DR, and the AUC area was significantly higher than that of the MLR model (0.77 vs 0.70, P<0.05), the probability threshold was 0.7.

CONCLUSION

We established the BP-ANN model and applied it to diagnose DR. Taking diabetic course, age, sex, albumin and creatinine as the inputs of BP-ANN, the existence of DR could be well predicted. Meanwhile, the generalization ability of the model could be improved by selecting different probability thresholds in different ROC curves.

Comparison of Diagnosis Accuracy between a Backpropagation Artificial Neural Network Model and Linear Regression in Digestive Disease Patients: an Empirical Research

Introduction

A Noninvasive diagnosis model for digestive diseases is the vital issue for the current clinical research. Our systematic review is aimed at demonstrating diagnosis accuracy between the BP-ANN algorithm and linear regression in digestive disease patients, including their activation function and data structure.

Methods

We reported the systematic review according to the PRISMA guidelines. We searched related articles from seven electronic scholarly databases for comparison of the diagnosis accuracy focusing on BP-ANN and linear regression. The characteristics, patient number, input/output marker, diagnosis accuracy, and results/conclusions related to comparison were extracted independently based on inclusion criteria.

Results

Nine articles met all the criteria and were enrolled in our review. Of those enrolled articles, the publishing year ranged from 1991 to 2017. The sample size ranged from 42 to 3222 digestive disease patients, and all of the patients showed comparable biomarkers between the BP-ANN algorithm and linear regression. According to our study, 8 literature demonstrated that the BP-ANN model is superior to linear regression in predicting the disease outcome based on AUROC results. One literature reported linear regression to be superior to BP-ANN for the early diagnosis of colorectal cancer.

Conclusion

The BP-ANN algorithm and linear regression both had high capacity in fitting the diagnostic model and BP-ANN displayed more prediction accuracy for the noninvasive diagnosis model of digestive diseases. We compared the activation functions and data structure between BP-ANN and linear regression for fitting the diagnosis model, and the data suggested that BP-ANN was a comprehensive recommendation algorithm.

Forecasting the seasonality and trend of pulmonary tuberculosis in Jiangsu Province of China using advanced statistical time-series analyses

Objective

Forecasting the seasonality and trend of pulmonary tuberculosis is important for the rational allocation of health resources; however, this foresting is often hampered by inappropriate prediction methods. In this study, we performed validation research by comparing the accuracy of the autoregressive integrated moving average (ARIMA) model and the back-propagation neural network (BPNN) model in a southeastern province of China.

Methods

We applied the data from 462,214 notified pulmonary tuberculosis cases registered from January 2005 to December 2015 in Jiangsu Province to modulate and construct the ARIMA and BPNN models. Cases registered in 2016 were used to assess the prediction accuracy of the models. The root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and mean error rate (MER) were used to evaluate the model fitting and forecasting effect.

Results

During 2005–2015, the annual pulmonary tuberculosis notification rate in Jiangsu Province was 56.35/100,000, ranging from 40.85/100,000 to 79.36/100,000. Through screening and comparison, the ARIMA (0, 1, 2) (0, 1, 1)₁₂ and BPNN (3-9-1) were defined as the optimal fitting models. In the fitting dataset, the RMSE, MAPE, MAE and MER were 0.3901, 6.0498, 0.2740 and 0.0608, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, 0.3236, 6.0113, 0.2508 and 0.0587, respectively, for the BPNN model. In the forecasting dataset, the RMSE, MAPE, MAE and MER were 0.1758, 4.6041, 0.1368 and 0.0444, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, and 0.1382, 3.2172, 0.1018 and 0.0330, respectively, for the BPNN model.

Conclusion

Both the ARIMA and BPNN models can be used to predict the seasonality and trend of pulmonary tuberculosis in the Chinese population, but the BPNN model shows better performance. Applying statistical techniques by considering local characteristics may enable more accurate mathematical modeling.

Artificial Intelligence for Diabetes Management and Decision Support: Literature Review

Background

Artificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis.

Objective

The objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges.

Methods

A review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review.

Results

We propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results.

Conclusions

We obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients’ quality of life.

Assessment of triglyceride and cholesterol in overweight people based on multiple linear regression and artificial intelligence model

Background

The prevalence of high hyperlipemia is increasing around the world. Our aims are to analyze the relationship of triglyceride (TG) and cholesterol (TC) with indexes of liver function and kidney function, and to develop a prediction model of TG, TC in overweight people.

Methods

A total of 302 adult healthy subjects and 273 overweight subjects were enrolled in this study. The levels of fasting indexes of TG (fs-TG), TC (fs-TC), blood glucose, liver function, and kidney function were measured and analyzed by correlation analysis and multiple linear regression (MRL). The back propagation artificial neural network (BP-ANN) was applied to develop prediction models of fs-TG and fs-TC.

Results

The results showed there was significant difference in biochemical indexes between healthy people and overweight people. The correlation analysis showed fs-TG was related to weight, height, blood glucose, and indexes of liver and kidney function; while fs-TC was correlated with age, indexes of liver function (P < 0.01). The MRL analysis indicated regression equations of fs-TG and fs-TC both had statistic significant (P < 0.01) when included independent indexes. The BP-ANN model of fs-TG reached training goal at 59 epoch, while fs-TC model achieved high prediction accuracy after training 1000 epoch.

Conclusions

In conclusions, there was high relationship of fs-TG and fs-TC with weight, height, age, blood glucose, indexes of liver function and kidney function. Based on related variables, the indexes of fs-TG and fs-TC can be predicted by BP-ANN models in overweight people.

Electronic supplementary material

The online version of this article (doi:10.1186/s12944-017-0434-5) contains supplementary material, which is available to authorized users.

Association of blood glucose and lipid levels with complete blood count indices to establish a regression model

Hyperglycemia and hyperlipidemia, which are usually diagnosed by analysis of blood glucose (GLU) and lipid levels, are two of the most common diseases in modern society. The purpose of the current study was to investigate the potential association between blood GLU and lipid levels with complete blood count (CBC) indices in overweight and healthy individuals and establish a regression model. There were 456 healthy and 421 overweight participants in the study. Data were collected on triglyceride (TG), total cholesterol (CHO), high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), blood GLU and CBC. The distribution characteristics and differences between healthy and overweight subjects were analyzed. Subsequently, the associations between TG, CHO, HDL, LDL and GLU with CBC were analyzed using correlation analysis and multiple linear regression (MLR). Significant differences were identified between the healthy and overweight individuals in TG, CHO, HDL, LDL, GLU and in the majority of the CBC indices. The correlation analysis indicated that there were strong correlations between TG, LDL, HDL, CHO and GLU with CBC indices in the healthy and overweight subjects. The MLR demonstrated that the regression models of TG, LDL, HDL and CHO, but no GLU, were statistically significant in the two groups (P<0.001). The HDL regression model exhibited the best regression parameters; the multiple correlation coefficients (R) were 0.351 and 0.308 in the healthy and overweight subjects, respectively. In the overweight and healthy subjects, there were strong correlations between TG, LDL, HDL and CHO with CBC indices, with HDL being the most relevant to the CBC indices. The CBC demonstrated statistical significance in the diagnosis of hyperlipidemia.