Status of glycosylated hemoglobin and prediction of glycemic control among patients with insulin-treated type 2 diabetes in North China: a multicenter observational study

Application of machine learning in affordable and accessible insulin management for type 1 and 2 diabetes: A comprehensive review

Proper insulin management is vital for maintaining stable blood sugar levels and preventing complications associated with diabetes. However, the soaring costs of insulin present significant challenges to ensuring affordable management. This paper conducts a comprehensive review of current literature on the application of machine learning (ML) in insulin management for diabetes patients, particularly focusing on enhancing affordability and accessibility within the United States. The review encompasses various facets of insulin management, including dosage calculation and response, prediction of blood glucose and insulin sensitivity, initial insulin estimation, resistance prediction, treatment adherence, complications, hypoglycemia prediction, and lifestyle modifications. Additionally, the study identifies key limitations in the utilization of ML within the insulin management literature and suggests future research directions aimed at furthering accessible and affordable insulin treatments. These proposed directions include exploring insurance coverage, optimizing insulin type selection, assessing the impact of biosimilar insulin and market competition, considering mental health factors, evaluating insulin delivery options, addressing cost-related issues affecting insulin usage and adherence, and selecting appropriate patient cost-sharing programs. By examining the potential of ML in addressing insulin management affordability and accessibility, this work aims to envision improved and cost-effective insulin management practices. It not only highlights existing research gaps but also offers insights into future directions, guiding the development of innovative solutions that have the potential to revolutionize insulin management and benefit patients reliant on this life-saving treatment.

Prediction of glycosylated hemoglobin level in patients with cardiovascular diseases and type 2 diabetes mellitus with respect to anti-diabetic medication

Blood glycosylated hemoglobin level can be affected by various factors in patients with type 2 diabetes and cardiovascular diseases. Frequent measurements are expensive, and a suitable estimation method could improve treatment outcomes.

Patients and methods

93 patients were recruited in this research. We analyzed a number of parameters such as age, glucose level, blood pressure, Body Mass Index, cholesterol level, echocardiography et al. Patients were prescribed metformin. One group (n=60) additionally was taking sitagliptin. We applied eight machine learning methods (k nearest neighbors, Random Forest, Support Vector Machine, Extra Trees, XGBoost, Linear Regression including Lasso, and ElasticNet) to predict exact values of glycosylated hemoglobin in two years.

Results

We applied a feature selection approach using step-by-step removal of them, Linear Regression on remaining features, and Pearson's correlation coefficient on the validation set. As a result, we got four different subsets for each group. We compared all eight Machine Learning methods using different hyperparameters on validation sets and chose the best models. We tested the best models on the external testing set and got R2 = 0.88, C Index = 0.857, Accuracy = 0.846, and MAE (Mean Absolute Error) = 0.65 for the first group, R2 = 0.86, C Index = 0.80, Accuracy = 0.75, and MAE = 0.41 for the second group.

Conclusion

The resulting algorithms could be used to assist clinical decision-making on prescribing anti-diabetic medications in pursuit of achieving glycemic control.

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.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.

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.

Glycemic control and its associated factors in type 2 diabetes patients at Felege Hiwot and Debre Markos Referral Hospitals

Poor glycemic control is a main public health problem among type 2 diabetes mellitus (T2DM) patients and a significant cause of the development of diabetic complications. This study aimed to assess the glycemic control status and its associated factors among type 2 diabetes patients in Felege-Hiwot and Debre Markos Referral Hospitals. A retrospective cohort study was conducted at Felege-Hiwot and Debre Markos Referral Hospitals from December 2014 to December 2015. We have reviewed the chart of these patients until January 2020. Type 2 diabetic patients on follow-up at Felege-Hiwot and Debre Markos Referral Hospitals who fulfilled the inclusion criteria of the study were included. The primary outcome was the level of blood glucose during the study period. Good glycemic control was defined as patients whose average fasting blood glucose measurement for three consecutive visits was between 70 and 130 mg/dL. A generalized linear mixed autoregressive order one model was used to identify the determinants of glycemic control. A total of 191 patients with 1740 observations were included in the study. The overall prevalence of good glycemic control was 58.4% (95% CI: 57.159.7%). The factors associated with good glycemic control at 95% confidence level adjusted odds ratio were being residing in rural (CI: 0.454, 0.614), negative proteinuria (CI: 1.211, 1.546), diastolic blood pressure < 90 (CI: 1.101, 1.522), systolic blood pressure < 140 (CI: 1.352, 1.895), serum creatinine (CI: 0.415, 0.660), duration per visit (CI: 0.913, 0.987), duration since diagnosis (CI: 0.985, 0.998), weight ≥ 78 kg (CI: 0.603, 0.881). Age 38–50, 51–59 and 60–66 years (CI: 1.267, 1.776), (CI: 1.057, 1.476) and (CI: 1.004, 1.403), respectively. The overall prevalence of poor glycemic control was high at Debre Markos and Felege Hiwot Referral Hospital. Living in a rural area, older age (≥ 67 years), positive proteinuria, higher weight (≥ 78 kg), higher serum creatinine levels, higher duration per visit, higher time duration of T2DM since diagnosis, and developing hypertension (SBP ≥ 140, DBP ≥ 90) were the predictors of lower good glycemic control achievements of T2DM patients. In response to this finding, an aggressive intervention that targets improving glycemic control is required.

Predictors of blood glucose change and microvascular complications of type 2 diabetes mellitus patients in Felege Hiwot and Debre Markos referral hospital, North West Ethiopia

BACKGROUND

Microvascular complications lead to disability, dependency, and accelerated morbidity and mortality. This study aimed to identify predictors of blood glucose change and time to microvascular complications among patients with type 2 diabetes.

METHODS

A retrospective cohort study was conducted among type 2 diabetes mellitus patients enrolled between December 2014 and December 2015 at Felege Hiwot and Debre Markos Referral Hospital. A total of 318 T2DM patients were included in the study. Joint modelling of longitudinal and survival analysis was employed to identify predictors of Blood Glucose Change and Microvascular Complications in Type 2 Diabetes Mellitus Patients.

RESULTS

The prevalence of microvascular complications in Type 2 diabetes patients was 26.3%, 95%confidence interval(CI):(21.5, 31.1). Of which, half of the patients developed a microvascular complication after 30 months from the onset of the follow-up. The significant predictors of developing microvascular complication were positive proteinurea (adjusted hazard ratio (AHR) = 1.418, 95%CI: 1.080, 1.861), Serum creatinine (AHR = 3.704, 95%CI: 1.992, 6.887), Weight (AHR = 1.058, 95%CI: 1.023, 1.094), and log fasting blood glucose(log(FBS))(AHR = 1.013, 95%CI: 1.010, 1.015). The predictors of fasting blood glucose progression were higher baseline FBS(est(estimate) = 0.002,95%CI:0.0018, 0.0022), Systolic blood pressure (SBP) (est = 0.003, 95%CI: 0.002, 0.004), diastolic blood pressure (DBP) (est = 0.002, 95%CI: 0.0002, 0.004), and age (est = 0.003, 95%CI: 0.001, 0.004).

CONCLUSION

The progression of the fasting blood glucose level for rural patients was faster than for urban patients. Patients having higher baseline FBS, previous hypertension history, higher SBP, higher DBP, older age, and fewer visits to the hospital have a relatively more progressive change in blood sugar levels. Patients having higher triglyceride levels, positive proteinuria, higher fasting blood sugar, higher weight, and a lesser number of hospital visits have a higher risk of developing a complication. In response to this finding, an aggressive intervention that targets to prevent microvascular complications is required.

Artificial intelligence and diabetes technology: A review

Artificial intelligence (AI) is widely discussed in the popular literature and is portrayed as impacting many aspects of human life, both in and out of the workplace. The potential for revolutionizing healthcare is significant because of the availability of increasingly powerful computational platforms and methods, along with increasingly informative sources of patient data, both in and out of clinical settings. This review aims to provide a realistic assessment of the potential for AI in understanding and managing diabetes, accounting for the state of the art in the methodology and medical devices that collect data, process data, and act accordingly. Acknowledging that many conflicting definitions of AI have been put forth, this article attempts to characterize the main elements of the field as they relate to diabetes, identifying the main perspectives and methods that can (i) affect basic understanding of the disease, (ii) affect understanding of risk factors (genetic, clinical, and behavioral) of diabetes development, (iii) improve diagnosis, (iv) improve understanding of the arc of disease (progression and personal/societal impact), and finally (v) improve treatment.

Predictors of poor glycemic control among type 2 diabetes mellitus patients treated with antidiabetic medications: A cross-sectional study in China

This study aimed to clarify of the predictors of poor glycemic control in type 2 diabetes mellitus (T2DM) patients treated with antidiabetic medications in China.This study was a retrospective, cross-sectional study based on SuValue database. T2DM patients aged 18 years or older performing glycosylated hemoglobin A1c (HbA1c) examinations from January 1st, 2018 to December 31st, 2018 were included and have been treated with antidiabetic medications for at least 6 months. HbA1c < 7.0% was defined as adequate glycemic control. Multivariate analysis was performed for the factors associated with poor glycemic control.A total of 13972 T2DM patients were included in this study. The adequate glycemic control rate was 44.04% (n = 6153). In the multivariate analysis, predictors of poor glycemic control include longer T2DM duration (5-10 years vs <5 years and >10 years vs <5 years, odds ratio [OR] = 1.499 and 1.581, P < .001 and P = .008), myocardial infarction (OR = 1.141, P = .041), diabetic neuropathy (OR = 1.409, P < .001), secondary hospital (OR = 1.877, P < .001), underdeveloped regions (OR = 1.786, P < .001), insulin only (OR = 3.912, P < .001), combination of oral antidiabetic agents and/or insulin use (P < .001).In conclusion, longer T2DM duration, secondary hospital, myocardial infarction, diabetic neuropathy, undeveloped regions and use of polypharmacy and insulin were associated with poor glycemic control among T2DM patients treated with antidiabetic medications. Patient education and training of health care providers may be short-term strategy to achieve adequate glycemic control.

Population diversity of cardiovascular outcome trials and real-world patients with diabetes in a Chinese tertiary hospital

BACKGROUND

Recent cardiovascular outcome trials (CVOTs) changed the therapeutic strategy of guidelines for type 2 diabetes. We compared the characteristics of patients from real-world hospital settings with those of participants in recent pragmatic randomized trials.

METHODS

This electronic medical record (EMR)-based retrospective observational study investigated the data of patients with diabetes from inpatient and outpatient settings in West China Hospital of Sichuan University from January 1, 2011, to June 30, 2019. We identified patients meeting the inclusion criteria of a pragmatic randomized trial (EMPA-REG OUTCOME) based on EMRs and compared their baseline characteristics with those of the trial participants. The cutoff for the clinical significance of each characteristic was set as its minimal clinically important difference based on expert consultation.

RESULTS

We included 48,257 inpatients and 36,857 outpatients with diabetes and found that 8389 (17.4%) inpatients and 2646 (7.2%) outpatients met the inclusion criteria for the EMPA-REG OUTCOME trial. Compared with the trial population, the real-world inpatients meeting the eligibility criteria of the EMPA-REG OUTCOME had similar age, blood pressure, and lipid profiles but comprised of fewer males, metformin users, anti-hypertensive drug users, and aspirin users, and had a lower body mass index. The group of outpatients meeting the eligibility criteria had fewer males, similar age, fewer metformin users, fewer insulin users, fewer anti-hypertensive drug users, and fewer aspirin users compared with the trial population.

CONCLUSIONS

The trial population in EMPA-REG OUTCOME represents only a small portion of patients with diabetes from the inpatient and outpatient departments of a Chinese tertiary medical center. Evidence localization in different clinical settings and validation are essential to enabling extrapolation of the results from CVOTs in patients with diabetes to Chinese clinical practice.

Glycemic Control of Diabetes Mellitus Patients in Referral Hospitals of Amhara Region, Ethiopia: A Cross-Sectional Study

Background

Glycemic control is the level of glucose in diabetes patient. Evidence regarding glycemic control is scarce in resource-limited settings, and this study was conducted to generate information regarding the prevalence and predictors of glycemic control among diabetes mellitus patients attending their care from the referral hospitals of the Amhara region, Ethiopia.

Methods

A cross-sectional study design was implemented. A simple random sampling technique was used. Data were collected from March 2018 to January 2020. The data were collected using interviews, chart review, and blood samples. Hemoglobin A1c was measured using high-performance liquid chromatography. Data were entered into Epi-info software and analyzed by SPSS software. Descriptive statistics were used to estimate the prevalence of glycemic control; linear regression was used to identify the predictors of HbA1c.

Results

A total of 2554 diabetes patients were included giving for the response rate of 95.83%. The mean age of the study participants was 54.08 years [SD (standard deviation) ± 8.38 years]. The mean HbA1c of the study participants was 7.31% [SD ± 0.94%]. Glycemic control was poor in 55.32% [95% CI: 53.4%-57.25%] of diabetes patients. The glycemic control of diabetes patients was determined by BMI (β 0.1; [95% CI: 0.09-0.1]), type 2 diabetes (β -0.14; [95% CI: -0.11-0.16]), age (β 0.22; [95% CI: 0.02-0.024]), duration of the disease (β 0.04; [95% CI: 0.037-0.042]), the presence of hypertension (β 0.12; [95% CI:0.09-0.16]), regular physical exercise (β -0.06; [95% CI: -0.03-0.09]), medication adherence (β -0.16; [95% CI: -0.14-0.18]), and male (β 0.34; [95% CI: 0.31-.037]).

Conclusion

The glycemic control of diabetes patients was poor, and it needs the attention of decision-makers.