Trajectories of Glycemic Change in a National Cohort of Adults With Previously Controlled Type 2 Diabetes

Longitudinal trajectories of glycemic control among U.S. Adults with newly diagnosed diabetes

AIMS

To identify longitudinal trajectories of glycemic control among adults with newly diagnosed diabetes, overall and by diabetes type.

METHODS

We analyzed claims data from OptumLabs® Data Warehouse for 119,952 adults newly diagnosed diabetes between 2005 and 2018. We applied a novel Mixed Effects Machine Learning model to identify longitudinal trajectories of hemoglobin A1c (HbA1c) over 3 years of follow-up and used multinomial regression to characterize factors associated with each trajectory.

RESULTS

The study population was comprised of 119,952 adults with newly diagnosed diabetes, including 696 (0.58%) with type 1 diabetes. Among patients with type 1 diabetes, 52.6% were diagnosed at very high HbA1c, partially improved, but never achieved control; 32.5% were diagnosed at low HbA1c and deteriorated over time; and 14.9% had stable low HbA1c. Among patients with type 2 diabetes, 67.7% had stable low HbA1c, 14.4% were diagnosed at very high HbA1c, partially improved, but never achieved control; 10.0% were diagnosed at moderately high HbA1c and deteriorated over time; and 4.9% were diagnosed at moderately high HbA1c and improved over time.

CONCLUSIONS

Claims data identified distinct longitudinal trajectories of HbA1c after diabetes diagnosis, which can be used to anticipate challenges and individualize care plans to improve glycemic control.

Time trajectories of key cardiometabolic parameters and of cardiovascular risk in subjects with diabetes in a real world setting

BACKGROUND AND AIMS

Diabetes is associated with increased cardiovascular risk. Glycated haemoglobin (HbA_1c), lipid parameters and blood pressure are known risk factors for adverse outcome. The aim of the study was to explore the time trajectories of these key parameters and of the associated cardiovascular risk.

METHODS

We linked the diabetes electronic health records to the laboratory information system so as to investigate the trajectories of key metabolic parameters from 3 years prior to the diagnosis of diabetes to 10 years after diagnosis. We calculated the cardiovascular risk at the different time points during this period using the United Kingdom Prospective Study (UKPDS) risk engine.

RESULTS

The study included 21,288 patients. The median age at diagnosis was 56 years and 55.3% were male. There was a sharp decrease in HbA_1c after diagnosis of diabetes, but there was a progressive rise thereafter. All lipid parameters after diagnosis also improved in the year of diagnosis, and these improvements persisted even up to 10 years post-diagnosis. There was no discernible trend in mean systolic or diastolic blood pressures following diagnosis of diabetes. There was a slight decrease in the UKPDS-estimated cardiovascular risk after diagnosis of diabetes followed by a progressive increase. Estimated glomerular filtration rate declined at an average rate of 1.33 ml/min/1.73 m²/year.

CONCLUSIONS

Our data suggest that lipid control should be tightened with increasing duration of diabetes since this is more readily achievable than HbA_1c lowering and since other factors such as age and duration of diabetes are unmodifiable.

Machine Learning Models for Predicting Adverse Pregnancy Outcomes in Pregnant Women with Systemic Lupus Erythematosus

Predicting adverse outcomes is essential for pregnant women with systemic lupus erythematosus (SLE) to minimize risks. Applying statistical analysis may be limited for the small sample size of childbearing patients, while the informative medical records could be provided. This study aimed to develop predictive models applying machine learning (ML) techniques to explore more information. We performed a retrospective analysis of 51 pregnant women exhibiting SLE, including 288 variables. After correlation analysis and feature selection, six ML models were applied to the filtered dataset. The efficiency of these overall models was evaluated by the Receiver Operating Characteristic Curve. Meanwhile, real-time models with different timespans based on gestation were also explored. Eighteen variables demonstrated statistical differences between the two groups; more than forty variables were screened out by ML variable selection strategies as contributing predictors, while the overlap of variables were the influential indicators testified by the two selection strategies. The Random Forest (RF) algorithm demonstrated the best discrimination ability under the current dataset for overall predictive models regardless of the data missing rate, while Multi-Layer Perceptron models ranked second. Meanwhile, RF achieved best performance when assessing the real-time predictive accuracy of models. ML models could compensate the limitation of statistical methods when the small sample size problem happens along with numerous variables acquired, while RF classifier performed relatively best when applied to such structured medical records.

Multi-cohort and longitudinal Bayesian clustering study of stage and subtype in Alzheimer's disease

Understanding Alzheimer's disease (AD) heterogeneity is important for understanding the underlying pathophysiological mechanisms of AD. However, AD atrophy subtypes may reflect different disease stages or biologically distinct subtypes. Here we use longitudinal magnetic resonance imaging data (891 participants with AD dementia, 305 healthy control participants) from four international cohorts, and longitudinal clustering to estimate differential atrophy trajectories from the age of clinical disease onset. Our findings (in amyloid-β positive AD patients) show five distinct longitudinal patterns of atrophy with different demographical and cognitive characteristics. Some previously reported atrophy subtypes may reflect disease stages rather than distinct subtypes. The heterogeneity in atrophy rates and cognitive decline within the five longitudinal atrophy patterns, potentially expresses a complex combination of protective/risk factors and concomitant non-AD pathologies. By alternating between the cross-sectional and longitudinal understanding of AD subtypes these analyses may allow better understanding of disease heterogeneity.

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 treatment failure during the first year in newly diagnosed type 2 diabetes patients: a retrospective, observational study

Background

Diabetes patients who fail to achieve early glycemic control may increase the future risk of complications and mortality. The aim of the study was to identify factors that predict treatment failure (TF) during the first year in adults with newly diagnosed type 2 diabetes mellitus (T2DM).

Methods

This retrospective cohort study conducted at a medical center in Taiwan enrolled 4,282 eligible patients with newly diagnosed T2DM between 2002 and 2017. Data were collected from electronic medical records. TF was defined as the HbA1c value >7% at the end of 1-year observation. A subgroup analysis of 2,392 patients with baseline HbA1c ≥8% was performed. Multivariable logistic regression analysis using backward elimination was applied to establish prediction models.

Results

Of all study participants, 1,439 (33.6%) were classified as TF during the first year. For every 1% increase in baseline HbA1c, the risk of TF was 1.17 (95% CI 1.15–1.20) times higher. Patients with baseline HbA1c ≥8% had a higher rate of TF than those with HbA1c <8% (42.0 vs 23.0%, p < 0.001). Medication adherence, self-monitoring of blood glucose (SMBG), regular exercise, gender (men), non-insulin treatment, and enrollment during 2010–2017 predicted a significant lower risk of TF in both of the primary and subgroup models.

Conclusions

Newly diagnosed diabetes patients with baseline HbA1c ≥8% did have a much higher rate of TF during the first year. Subgroup analysis for them highlights the important predictors of TF, including medication adherence, performing SMBG, regular exercise, and gender, in achieving glycemic control.

The Need for Ethnoracial Equity in Artificial Intelligence for Diabetes Management: Review and Recommendations

There is clear evidence to suggest that diabetes does not affect all populations equally. Among adults living with diabetes, those from ethnoracial minority communities—foreign-born, immigrant, refugee, and culturally marginalized—are at increased risk of poor health outcomes. Artificial intelligence (AI) is actively being researched as a means of improving diabetes management and care; however, several factors may predispose AI to ethnoracial bias. To better understand whether diabetes AI interventions are being designed in an ethnoracially equitable manner, we conducted a secondary analysis of 141 articles included in a 2018 review by Contreras and Vehi entitled “Artificial Intelligence for Diabetes Management and Decision Support: Literature Review.” Two members of our research team independently reviewed each article and selected those reporting ethnoracial data for further analysis. Only 10 articles (7.1%) were ultimately selected for secondary analysis in our case study. Of the 131 excluded articles, 118 (90.1%) failed to mention participants’ ethnic or racial backgrounds. The included articles reported ethnoracial data under various categories, including race (n=6), ethnicity (n=2), race/ethnicity (n=3), and percentage of Caucasian participants (n=1). Among articles specifically reporting race, the average distribution was 69.5% White, 17.1% Black, and 3.7% Asian. Only 2 articles reported inclusion of Native American participants. Given the clear ethnic and racial differences in diabetes biomarkers, prevalence, and outcomes, the inclusion of ethnoracial training data is likely to improve the accuracy of predictive models. Such considerations are imperative in AI-based tools, which are predisposed to negative biases due to their black-box nature and proneness to distributional shift. Based on our findings, we propose a short questionnaire to assess ethnoracial equity in research describing AI-based diabetes interventions. At this unprecedented time in history, AI can either mitigate or exacerbate disparities in health care. Future accounts of the infancy of diabetes AI must reflect our early and decisive action to confront ethnoracial inequities before they are coded into our systems and perpetuate the very biases we aim to eliminate. If we take deliberate and meaningful steps now toward training our algorithms to be ethnoracially inclusive, we can architect innovations in diabetes care that are bound by the diverse fabric of our society.

Clinical Inertia and 2-Year Glycaemic Trajectories in Patients with Non-Newly Diagnosed Type 2 Diabetes Mellitus in Primary Care: A Retrospective Cohort Study

OBJECTIVE

To analyse diabetes treatment, treatment change and self-management behaviours in association with 2-year glycaemic trajectories in patients with non-newly diagnosed type 2 diabetes mellitus in Chinese primary care.

METHODS

This was an observational, multi-centre, longitudinal, retrospective cohort study. Clinical data of 4690 subjects were extracted from electronic medical records, including serial glycated haemoglobin A_1c (HbA_1c) measurements, antidiabetic medication records and compliance to exercise, diet, medications and self-monitoring of blood glucose (SMBG). Patterns of longitudinal HbA1c trajectories were identified using the percentage of HbA_1c measurements <7.5% from the second available HbA_1c measurement. Clinical relevance of the clusters was assessed through multivariable analysis.

RESULTS

Approximately half of the participants demonstrated good glycaemic control; of these, 34.5% demonstrated stable, good control, and 13.7% demonstrated relatively good control. About 16.2% demonstrated moderate control, and 35.6% demonstrated poor control. From the good to poor control groups, the percentage of subjects treated with insulin at baseline and during the follow-up period increased gradually, while the percentage of subjects adhering to exercise, diet, medications and SMBG decreased gradually. Compared with baseline, the adherence to exercise, diet, medications and SMBG improved significantly. Approximately 50% and 26% of subjects in the two poorest control groups, respectively, experienced treatment changes. After multivariable adjustments, baseline HbA_1c ≥7.5%, HbA_1c change ≥-0.5% from baseline to visit 1, insulin treatment, treatment change, poor adherence to diet, exercise, SMBG during the follow-up period and HbA_1c measurements <3 per year were significantly associated with poorer glycaemic control.

CONCLUSION

We identified four longitudinal HbA_1c trajectories in patients with non-newly diagnosed type 2 diabetes. Even if baseline HbA_1c is suboptimal, aggressive treatment changes, good adherence during the follow-up period, ≥3 HbA_1c measurements per year and reducing HbA_1c levels to a certain extent by the first follow-up visit were important for good, stable, long-term glycaemic control.

Distinct trajectories of HbA1c in newly diagnosed Type 2 diabetes from the DPV registry using a longitudinal group-based modelling approach

AIM

To identify groups of heterogeneous HbA_1c trajectories over time in newly diagnosed Type 2 diabetes.

METHODS

The study comprised 6355 adults with newly diagnosed Type 2 diabetes (55% men, median age 62 years, baseline BMI 31 kg/m² ) from the Diabetes Patienten Verlaufsdokumentation (DPV) prospective multicentre diabetes registry (Germany, Austria). Individuals were assessed during the first 5 years after diabetes diagnosis if they had ≥ 3 aggregated HbA_1c measurements during follow-up. Latent class growth modelling was used to determine distinct subgroups that followed similar longitudinal HbA_1c patterns (SAS: Proc Traj). Multinomial logistic regression models were used to investigate which variables were associated with the respective HbA_1c trajectory groups.

RESULTS

Four distinct longitudinal HbA_1c trajectory (glycaemic control) groups were found. The largest group (56% of participants) maintained stable good glycaemic control (HbA_1c 42-45 mmol/mol). Twenty-six percent maintained stable moderate glycaemic control (HbA_1c 57-62 mmol/mol). A third group (12%) initially showed severe hyperglycaemia (HbA_1c 97 mmol/mol) but reached good glycaemic control within 1 year. The smallest group (6%) showed stable poor glycaemic control (HbA_1c 79-88 mmol/mol). Younger age at diabetes diagnosis, male sex, and higher BMI were associated with the stable moderate or poor glycaemic control groups. Insulin therapy was strongly associated with the highly improved glycaemic control group.

CONCLUSIONS

Four subgroups with distinct HbA_1c trajectories were determined in newly diagnosed Type 2 diabetes using a group-based modelling approach. Approximately one-third of people with newly diagnosed Type 2 diabetes need either better medication adherence or earlier intensification of glucose-lowering therapy.

Longitudinal changes in glycated haemoglobin following treatment intensification after inadequate response to two oral antidiabetic agents in patients with type 2 diabetes

AIMS

To identify change in glycated haemoglobin (HbA1c) for 1 year after treatment intensification in patients with HbA1c >53 mmol/mol (7.0%) while on two classes of oral antidiabetic drugs (OADs).

MATERIAL AND METHODS

A retrospective cohort study was conducted using a regional health plan claims database for the period January 1, 2010 to March 31, 2017. Patients with type 2 diabetes (T2DM) whose treatment was intensified with insulin, a glucagon-like peptide-1 receptor agonist or a third OAD within 365 days of having HbA1c ≥53 mmol/mol (7.0%) on two OADs were included. The HbA1c trajectory for 1 year after intensification was estimated using a mixed-effects regression model.

RESULTS

The analysis included 1226 patients with a mean ± SD HbA1c at treatment intensification of 74.2 ± 18.7 mmol/mol (8.93 ± 1.7%). HbA1c was higher in the insulin group (74.2 mmol/mol) than in the non-insulin group (70.6 mmol/mol), as was the HbA1c decrease (P < 0.01) over the 1-year follow-up, particularly in patients with baseline HbA1c >9%. After intensification, insulin- and non-insulin-treated patients achieved an average change by month in HbA1c of -4.7 mmol/mol and -2.6 mmol/mol points, respectively. The analysis predicted HbA1c to be the lowest at 6 to 10 months post intensification, depending on intensification treatment and HbA1c at intensification; however, on average, HbA1c remained above 64.0 mmol/mol (8.0%).

CONCLUSION

In patients with T2DM, intensification following an HbA1c value ≥53 mmol/mol (7.0%) while on two OADs was associated with a significant improvement in glycaemic control. Patients intensified with insulin had a higher baseline HbA1c but greater HbA1c reduction than those intensified with a non-insulin agent. However, HbA1c remained above 64 mmol/mol (8.0%) overall. Additional opportunity exists to further intensify therapy to improve glycaemic control.

Mixed effect machine learning: A framework for predicting longitudinal change in hemoglobin A1c

Accurate and reliable prediction of clinical progression over time has the potential to improve the outcomes of chronic disease. The classical approach to analyzing longitudinal data is to use (generalized) linear mixed-effect models (GLMM). However, linear parametric models are predicated on assumptions, which are often difficult to verify. In contrast, data-driven machine learning methods can be applied to derive insight from the raw data without a priori assumptions. However, the underlying theory of most machine learning algorithms assume that the data is independent and identically distributed, making them inefficient for longitudinal supervised learning. In this study, we formulate an analytic framework, which integrates the random-effects structure of GLMM into non-linear machine learning models capable of exploiting temporal heterogeneous effects, sparse and varying-length patient characteristics inherent in longitudinal data. We applied the derived mixed-effect machine learning (MEml) framework to predict longitudinal change in glycemic control measured by hemoglobin A1c (HbA1c) among well controlled adults with type 2 diabetes. Results show that MEml is competitive with traditional GLMM, but substantially outperformed standard machine learning models that do not account for random-effects. Specifically, the accuracy of MEml in predicting glycemic change at the 1st, 2nd, 3rd, and 4th clinical visits in advanced was 1.04, 1.08, 1.11, and 1.14 times that of the gradient boosted model respectively, with similar results for the other methods. To further demonstrate the general applicability of MEml, a series of experiments were performed using real publicly available and synthetic data sets for accuracy and robustness. These experiments reinforced the superiority of MEml over the other methods. Overall, results from this study highlight the importance of modeling random-effects in machine learning approaches based on longitudinal data. Our MEml method is highly resistant to correlated data, readily accounts for random-effects, and predicts change of a longitudinal clinical outcome in real-world clinical settings with high accuracy.

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.