Stacked classifiers for individualized prediction of glycemic control following initiation of metformin therapy in type 2 diabetes

Artificial intelligence for diabetes care: current and future prospects

Artificial intelligence (AI) use in diabetes care is increasingly being explored to personalise care for people with diabetes and adapt treatments for complex presentations. However, the rapid advancement of AI also introduces challenges such as potential biases, ethical considerations, and implementation challenges in ensuring that its deployment is equitable. Ensuring inclusive and ethical developments of AI technology can empower both health-care providers and people with diabetes in managing the condition. In this Review, we explore and summarise the current and future prospects of AI across the diabetes care continuum, from enhancing screening and diagnosis to optimising treatment and predicting and managing complications.

Exploring metformin monotherapy response in Type-2 diabetes: Computational insights through clinical, genomic, and proteomic markers using machine learning algorithms

BACKGROUND

In 2016, the UK had 4.5 million people with diabetes, predominantly Type-2 Diabetes Mellitus (T2DM). The NHS allocates £10 billion (9% of its budget) to manage diabetes. Metformin is the primary treatment for T2DM, but 35% of patients don't benefit from it, leading to complications. This study aims to delve into metformin's efficacy using clinical, genomic, and proteomic data to uncover new biomarkers and build a Machine Learning predictor for early metformin response detection.

METHODS

Here we report analysis from a T2DM dataset of individuals prescribed metformin monotherapy from the Diastrat cohort recruited at the Altnagelvin Area Hospital, Northern Ireland.

RESULTS

In the clinical data analysis, comparing responders (those achieving HbA1c ≤ 48 mmol/mol) to non-responders (with HbA1c > 48 mmol/mol), we identified that creatinine levels and bodyweight were more negatively correlated with response than non-response. In genomic analysis, we identified statistically significant (p-value <0.05) variants rs6551649 (LPHN3), rs6551654 (LPHN3), rs4495065 (LPHN3) and rs7940817 (TRPC6) which appear to differentiate the responders and non-responders. In proteomic analysis, we identified 15 statistically significant (p-value <0.05, q-value <0.05) proteomic markers that differentiate controls, responders, non-responders and treatment groups, out of which the most significant were HAOX1, CCL17 and PAI that had fold change ∼2. A machine learning model was build; the best model predicted non-responders with 83% classification accuracy.

CONCLUSION

Further testing in prospective validation cohorts is required to determine the clinical utility of the proposed model.

Anti-diabetic drug discovery using the bioactive compounds of Momordica charantia by molecular docking and molecular dynamics analysis

Diabetes mellitus (DM) is a multifactorial life-threatening endocrine disease characterized by abnormalities in glucose metabolism. It is a chronic metabolic disease that involves multiple enzymes such as α-amylase and α-glucosidases. Inhibition of these enzymes has been identified as a promising method for managing diabetes, and researchers are currently focusing on discovering novel α-amylase and α-glucosidase inhibitors for diabetes therapy. Hence, we have selected 12 bioactive compounds from the Momordica charantia (MC) plant and performed a virtual screening and molecular dynamics investigation to identify natural inhibitors of α-amylase and α-glucosidases. Our in silico result revealed that phytocompound Rutin showed the highest binding affinity against α-amylase (1HNY) enzymes at (-11.68 kcal/mol), followed by Karaviloside II (-9.39), Momordicoside F (-9.19), Campesterol (-9.11. While docking against α-glucosidases (4J5T), Rutin again showed the greatest binding affinity (-11.93 kcal/mol), followed by Momordicine (-9.89), and Campesterol (-8.99). Molecular dynamics (MD) simulation research is currently the gold standard for drug design and discovery. Consequently, we conducted simulations of 100 nanoseconds (ns) to assess the stability of protein-ligand complexes based on parameters like RMSD, RMSF, RG, PCA, and FEL. The significance of our findings indicates that rutin from MC might serve as an effective natural therapeutic agent for diabetes management due to its strongest binding affinities with α-amylase and α-glucosidase enzymes. Further research in animals and humans is essential to validate the efficacy of these drug molecules.Communicated by Ramaswamy H. Sarma.

Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

The increasing prevalence of diabetes, high avoidable morbidity and mortality due to diabetes and diabetic complications, and related substantial economic burden make diabetes a significant health challenge worldwide. A shortage of diabetes specialists, uneven distribution of medical resources, low adherence to medications, and improper self-management contribute to poor glycemic control in patients with diabetes. Recent advancements in digital health technologies, especially artificial intelligence (AI), provide a significant opportunity to achieve better efficiency in diabetes care, which may diminish the increase in diabetes-related health-care expenditures. Here, we review the recent progress in the application of AI in the management of diabetes and then discuss the opportunities and challenges of AI application in clinical practice. Furthermore, we explore the possibility of combining and expanding upon existing digital health technologies to develop an AI-assisted digital health-care ecosystem that includes the prevention and management of diabetes.

Machine Learning as a Support for the Diagnosis of Type 2 Diabetes

Diabetes is a chronic, metabolic disease characterized by high blood sugar levels. Among the main types of diabetes, type 2 is the most common. Early diagnosis and treatment can prevent or delay the onset of complications. Previous studies examined the application of machine learning techniques for prediction of the pathology, and here an artificial neural network shows very promising results as a possible valuable aid in the management and prevention of diabetes. Additionally, its superior ability for long-term predictions makes it an ideal choice for this field of study. We utilized machine learning methods to uncover previously undiscovered associations between an individual’s health status and the development of type 2 diabetes, with the goal of accurately predicting its onset or determining the individual’s risk level. Our study employed a binary classifier, trained on scratch, to identify potential nonlinear relationships between the onset of type 2 diabetes and a set of parameters obtained from patient measurements. Three datasets were utilized, i.e., the National Center for Health Statistics’ (NHANES) biennial survey, MIMIC-III and MIMIC-IV. These datasets were then combined to create a single dataset with the same number of individuals with and without type 2 diabetes. Since the dataset was balanced, the primary evaluation metric for the model was accuracy. The outcomes of this study were encouraging, with the model achieving accuracy levels of up to 86% and a ROC AUC value of 0.934. Further investigation is needed to improve the reliability of the model by considering multiple measurements from the same patient over time.

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.

Waist-to-hip circumference and waist-to-height ratio could strongly predict glycemic control than body mass index among adult patients with diabetes in Ethiopia: ROC analysis

Background

Poorly controlled blood glucose is prevalent and contributes to the huge burden of diabetes related morbidity, and central obesity has a great role in the pathogenesis of diabetes and its adverse complications, which could predict such risks, yet evidence is lacking. Hence, this paper is to evaluate the predictive performance of central obesity indices for glycemic control among adult patients with diabetes in eastern Ethiopia.

Methods

A survey of 432 randomly chosen patients with diabetes was conducted using a pretested questionnaire supplemented by chart review, anthropometrics, and biomarkers by trained data collectors. The poor glycemic control was assessed using a fasting blood glucose (FBS) level of above 130 and/or an HgA1c level above 7%. Weight, height, waist circumference (WC), and hip circumference (HC) were measured under standard procedures and we calculated waist-to-hip circumference ratio (WHR) and waist-to-height ratio (WHtR). The receiver operating characteristics curve was used to assess the predictive performance of obesity indices for glycemic control using area under the curve (AUC) and corresponding validity measures.

Results

A total of 432 (92%) patients with diabetes were enrolled with a mean age of 49.6 (±12.4) years. The mean fasting blood glucose level was 189 (±72) mg dl-1 where 330 (76.4%) (95% CI: 74.4–78.4%) and 93.3% of them had poor glycemic control based on FBS and HgA1c, respectively. WC (AUC = 0.90; 95% CI: 0.85–0.95), WHR (AUC = 0.64; 95% CI: 0.43–0.84), and WHtR (AUC = 0.87; 95% CI: 0.83–0.94) have a higher predictive performance for poor glycemic control at cut-off points above 100 cm, 0.95, and 0.62, respectively. However, obesity indices showed a lower predictive performance for poor glycemic control based on FBS. Body mass index (BMI) had a poor predictive performance for poor glycemic control (AUC = 0.26; 95% CI: 0.13–0.40).

Conclusions

Poor glycemic control is a public health concern and obesity indicators, typically WC, WHR, and WHtR, have a better predictive performance for poor glycemic control than BMI.

Greater Glycemic Burden Is Associated with Further Poorer Glycemic Control in Newly-Diagnosed Type 2 Diabetes Mellitus Patients

Aims: hyperglycemia impairs pancreatic β-cell function instantly, also known as glucotoxicity. It is unknown whether this insult is temporary or sustained, and little real-world evidence needs to reflect the relationship between hyperglycemic burden, per se, and glycemic durability. Materials and Methods: a retrospective observational cohort study was conducted to recruit newly-diagnosed type 2 diabetes mellitus (T2DM) patients. Durability was defined as the episode from first glycated hemoglobin A1c (HbA1c) below 7.0% to where it exceed 8.0% (with treatment failure) or where study ended (without treatment failure). Glycemic burden was defined with the area above a burden value line (HbA1c = 6.5%) but under the HbA1c curve (AUC), and it was then divided into two compartments with the demarcation timepoint once HbA1c was treated below or equal to 7.0%; the former AUC' represented the initial insult; the latter AUC" represented the residual part. Multivariable regression models assessed factors associated with durability in whole participants and two distinct subgroups: patients with baseline HbA1c > 7.0% or ≤7.0%. Results: 1048 eligible participants were recruited and analyzed: 291 patients with treatment failure (durability 26.8 ± 21.1 months); 757 patients without treatment failure (durability 45.1 ± 31.8 months). Besides age, glycemic burden was the only constant determinant in the two subgroups. AUC' or AUC" increased treatment failure, respectively, in baseline HbA1c > 7.0% or ≤7.0% subgroup [per 1%/90 days hazard ratio (95% confidence interval): 1.026 (1.018-1.034) and 1.128 (1.016-1.253)]. Other determinants include baseline HbA1c, initial OAD, and education level. Conclusions: in patients with newly-diagnosed T2DM, glycemic durability was negatively associated with greater glycemic burden.

Beta cell functionality and hepatic insulin resistance are major contributors to type 2 diabetes remission and starting pharmacological therapy: from CORDIOPREV randomized controlled trial

In order to assess whether previous hepatic IR (Hepatic-IR_fasting) and beta-cell functionality could modulate type 2 diabetes remission and the need for starting glucose-lowering treatment, newly-diagnosed type 2 diabetes participants who had never received glucose-lowering treatment (190 out of 1002) from the CORonary Diet Intervention with Olive oil and cardiovascular PREVention study (a prospective, randomized and controlled clinical trial), were randomized to consume a Mediterranean or a low-fat diet. Type 2 diabetes remission was defined according to the American Diabetes Association recommendation for levels of HbA1c, fasting plasma glucose and 2h plasma glucose after oral glucose tolerance test, and having maintained them for at least 2 consecutive years. Patients were classified according to the median of Hepatic-IR_fasting and beta-cell functionality, measured as the disposition index (DI) at baseline. Cox proportional hazards regression determined the potential for Hepatic-IR_fasting and DI indexes as predictors of diabetes remission and the probability of starting pharmacological treatment after a 5-year follow-up. Low-Hepatic-IR_fasting or high-DI patients had a higher probability of diabetes remission than high-Hepatic-IR_fasting or low-DI subjects (HR:1.79; 95% CI 1.06-3.05; and HR:2.66; 95% CI 1.60-4.43, respectively) after a dietary intervention with no pharmacological treatment and no weight loss. The combination of low-Hepatic-IR_fasting and high-DI presented the highest probability of remission (HR:4.63; 95% CI 2.00-10.70). Among patients maintaining diabetes, those with high- Hepatic-IR_fasting and low-DI showed the highest risk of starting glucose-lowering therapy (HR:3.24;95% CI 1.50-7.02). Newly-diagnosed type 2 diabetes patients with better beta-cell functionality and lower Hepatic-IR_fasting had a higher probability of type 2 diabetes remission in a dietary intervention without pharmacological treatment or weight loss, whereas among patients not achieving remission, those with worse beta-cell functionality and higher Hepatic-IR_fasting index had the highest risk of starting glucose-lowering treatment after 5 years of follow-up.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.

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.

Machine Learning Approaches to Predict Risks of Diabetic Complications and Poor Glycemic Control in Nonadherent Type 2 Diabetes

Purpose: The objective of this study was to evaluate the efficacy of machine learning algorithms in predicting risks of complications and poor glycemic control in nonadherent type 2 diabetes (T2D). Materials and Methods: This study was a real-world study of the complications and blood glucose prognosis of nonadherent T2D patients. Data of inpatients in Sichuan Provincial People's Hospital from January 2010 to December 2015 were collected. The T2D patients who had neither been monitored for glycosylated hemoglobin A nor had changed their hyperglycemia treatment regimens within the last 12 months were the object of this study. Seven types of machine learning algorithms were used to develop 18 prediction models. The predictive performance was mainly assessed using the area under the curve of the testing set. Results: Of 800 T2D patients, 165 (20.6%) met the inclusion criteria, of which 129 (78.2%) had poor glycemic control (defined as glycosylated hemoglobin A ≥7%). The highest area under the curves of the testing set for diabetic nephropathy, diabetic peripheral neuropathy, diabetic angiopathy, diabetic eye disease, and glycosylated hemoglobin A were 0.902 ± 0.040, 0.859 ± 0.050, 0.889 ± 0.059, 0.832 ± 0.086, and 0.825 ± 0.092, respectively. Conclusion: Both univariate analysis and machine learning methods reached the same conclusion. The duration of T2D and the duration of unadjusted hypoglycemic treatment were the key risk factors of diabetic complications, and the number of hypoglycemic drugs was the key risk factor of glycemic control of nonadherent T2D. This was the first study to use machine learning algorithms to explore the potential adverse outcomes of nonadherent T2D. The performances of the final prediction models we developed were acceptable; our prediction performances outperformed most other previous studies in most evaluation measures. Those models have potential clinical applicability in improving T2D care.

Application of Machine Learning in Translational Medicine: Current Status and Future Opportunities

The exponential increase in our ability to harness multi-dimensional biological and clinical data from experimental to real-world settings has transformed pharmaceutical research and development in recent years, with increasing applications of artificial intelligence (AI) and machine learning (ML). Patient-centered iterative forward and reverse translation is at the heart of precision medicine discovery and development across the continuum from target validation to optimization of pharmacotherapy. Integration of advanced analytics into the practice of Translational Medicine is now a fundamental enabler to fully exploit information contained in diverse sources of big data sets such as “omics” data, as illustrated by deep characterizations of the genome, transcriptome, proteome, metabolome, microbiome, and exposome. In this commentary, we provide an overview of ML applications in drug discovery and development, aligned with the three strategic pillars of Translational Medicine (target, patient, dose) and offer perspectives on their potential to transform the science and practice of the discipline. Opportunities for integrating ML approaches into the discipline of Pharmacometrics are discussed and will revolutionize the practice of model-informed drug discovery and development. Finally, we posit that joint efforts of Clinical Pharmacology, Bioinformatics, and Biomarker Technology experts are vital in cross-functional team settings to realize the promise of AI/ML-enabled Translational and Precision Medicine.

Use of Machine Learning Approaches in Clinical Epidemiological Research of Diabetes

PURPOSE OF REVIEW

Machine learning approaches-which seek to predict outcomes or classify patient features by recognizing patterns in large datasets-are increasingly applied to clinical epidemiology research on diabetes. Given its novelty and emergence in fields outside of biomedical research, machine learning terminology, techniques, and research findings may be unfamiliar to diabetes researchers. Our aim was to present the use of machine learning approaches in an approachable way, drawing from clinical epidemiological research in diabetes published from 1 Jan 2017 to 1 June 2020.

RECENT FINDINGS

Machine learning approaches using tree-based learners-which produce decision trees to help guide clinical interventions-frequently have higher sensitivity and specificity than traditional regression models for risk prediction. Machine learning approaches using neural networking and "deep learning" can be applied to medical image data, particularly for the identification and staging of diabetic retinopathy and skin ulcers. Among the machine learning approaches reviewed, researchers identified new strategies to develop standard datasets for rigorous comparisons across older and newer approaches, methods to illustrate how a machine learner was treating underlying data, and approaches to improve the transparency of the machine learning process. Machine learning approaches have the potential to improve risk stratification and outcome prediction for clinical epidemiology applications. Achieving this potential would be facilitated by use of universal open-source datasets for fair comparisons. More work remains in the application of strategies to communicate how the machine learners are generating their predictions.

Does the Encounter Type Matter When Defining Diabetes Complications in Electronic Health Records?

BACKGROUND

Electronic health records (EHRs) and claims records are widely used in defining type 2 diabetes mellitus (T2DM) complications across different types of health care encounters.

OBJECTIVE

This study investigates whether using different EHR encounter types to define diabetes complications may lead to different results when examining associations between diabetes complications and their risk factors in patients with T2DM.

RESEARCH DESIGN

The study cohort of 64,855 adult patients with T2DM was created from EHR data from the Research Action for Health Network (REACHnet), using the Surveillance Prevention, and Management of Diabetes Mellitus (SUPREME-DM) definitions. Incidence of coronary heart disease (CHD) and stroke events were identified using International Classification of Diseases (ICD)-9/10 codes and grouped by encounter types: (1) inpatient (IP) or emergency department (ED) type, or (2) any health care encounter type. Cox proportional hazards regression was used to estimate associations between diabetes complications (ie, CHD and stroke) and risk factors (ie, low-density lipoprotein cholesterol and hemoglobin A1c).

RESULTS

The incidence rates of CHD and stroke in all health care settings were more than twice the incidence rates of CHD and stroke in IP/ED settings. The age-adjusted and multivariable-adjusted hazard ratios for incident CHD and stroke across different levels of low-density lipoprotein cholesterol and hemoglobin A1c were similar between IP/ED and all settings.

CONCLUSION

While there are large variations in incidence rates of CHD and stroke as absolute risks, the associations between both CHD and stroke and their respective risk factors measured by hazard ratios as relative risks are similar, regardless of alternative definitions.

Analysis on diagnosing diabetic retinopathy by segmenting blood vessels, optic disc and retinal abnormalities

The main intention of mass screening programmes for Diabetic Retinopathy (DR) is to detect and diagnose the disorder earlier than it leads to vision loss. Automated analysis of retinal images has the likelihood to improve the efficacy of screening programmes when compared over the manual image analysis. This article plans to develop a framework for the detection of DR from the retinal fundus images using three evaluations based on optic disc, blood vessels and retinal abnormalities. Initially, the pre-processing steps like green channel conversion and Contrast Limited Adaptive Histogram Equalisation is done. Further, the segmentation procedure starts with optic disc segmentation by open-close watershed transform, blood vessel segmentation by grey level thresholding and abnormality segmentation (hard exudates, haemorrhages, Microaneurysm and soft exudates) by top hat transform and Gabor filtering mechanisms. From the three segmented images, the feature like local binary pattern, texture energy measurement, Shanon's and Kapur's entropy are extracted, which is subjected to optimal feature selection process using the new hybrid optimisation algorithm termed as Trial-based Bypass Improved Dragonfly Algorithm (TB - DA). These features are given to hybrid machine learning algorithm with the combination of NN and DBN. As a modification, the same hybrid TB - DA is used to enhance the training of hybrid classifier, which outputs the categorisation as normal, mild, moderate or severe images based on three components.