Development of a model to predict 5-year risk of severe hypoglycemia in patients with type 2 diabetes

Development and validation of a prediction model for self-reported hypoglycemia risk in patients with type 2 diabetes: A longitudinal cohort study

AIMS/INTRODUCTION

To develop and validate a simple prediction model for hypoglycemia risk in patients with type 2 diabetes.

MATERIALS AND METHODS

We prospectively analyzed the data of 1,303 subjects in a third-class hospital in Tianjin and followed up their hypoglycemia events at 3 and 6 months. The hypoglycemia risk prediction models for 3 and 6 months were developed and the model performance was evaluated.

RESULTS

A total of 340 (28.4%) patients experienced hypoglycemia within 3 months and 462 (37.2%) within 6 months during the follow-up period. Age, central obesity, intensive insulin therapy, frequency of hypoglycemia in the past year, and hypoglycemia prevention education entered both model3month and model6month. The area under the receiver operating characteristic curve of model3month and model6month were 0.711 and 0.723, respectively. The Youden index was 0.315 and 0.361, while the sensitivities were 0.615 and 0.714, and the specificities were 0.717 and 0.631. The calibration curves showed that the models were similar to reality. The decision curves implied that the clinical net benefit of the model was clear.

CONCLUSIONS

The study developed 3 and 6 month hypoglycemia risk prediction models for patients with type 2 diabetes. The discrimination and calibration of the two prediction models were good, and might help to improve clinical decision-making and guide patients to more reasonable self-care and hypoglycemia prevention at home.

A novel electronic health record-based, machine-learning model to predict severe hypoglycemia leading to hospitalizations in older adults with diabetes: A territory-wide cohort and modeling study

BACKGROUND

Older adults with diabetes are at high risk of severe hypoglycemia (SH). Many machine-learning (ML) models predict short-term hypoglycemia are not specific for older adults and show poor precision-recall. We aimed to develop a multidimensional, electronic health record (EHR)-based ML model to predict one-year risk of SH requiring hospitalization in older adults with diabetes.

METHODS AND FINDINGS

We adopted a case-control design for a retrospective territory-wide cohort of 1,456,618 records from 364,863 unique older adults (age ≥65 years) with diabetes and at least 1 Hong Kong Hospital Authority attendance from 2013 to 2018. We used 258 predictors including demographics, admissions, diagnoses, medications, and routine laboratory tests in a one-year period to predict SH events requiring hospitalization in the following 12 months. The cohort was randomly split into training, testing, and internal validation sets in a 7:2:1 ratio. Six ML algorithms were evaluated including logistic-regression, random forest, gradient boost machine, deep neural network (DNN), XGBoost, and Rulefit. We tested our model in a temporal validation cohort in the Hong Kong Diabetes Register with predictors defined in 2018 and outcome events defined in 2019. Predictive performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC) statistics, and positive predictive value (PPV). We identified 11,128 SH events requiring hospitalization during the observation periods. The XGBoost model yielded the best performance (AUROC = 0.978 [95% CI 0.972 to 0.984]; AUPRC = 0.670 [95% CI 0.652 to 0.688]; PPV = 0.721 [95% CI 0.703 to 0.739]). This was superior to an 11-variable conventional logistic-regression model comprised of age, sex, history of SH, hypertension, blood glucose, kidney function measurements, and use of oral glucose-lowering drugs (GLDs) (AUROC = 0.906; AUPRC = 0.085; PPV = 0.468). Top impactful predictors included non-use of lipid-regulating drugs, in-patient admission, urgent emergency triage, insulin use, and history of SH. External validation in the HKDR cohort yielded AUROC of 0.856 [95% CI 0.838 to 0.873]. Main limitations of this study included limited transportability of the model and lack of geographically independent validation.

CONCLUSIONS

Our novel-ML model demonstrated good discrimination and high precision in predicting one-year risk of SH requiring hospitalization. This may be integrated into EHR decision support systems for preemptive intervention in older adults at highest risk.

Neural Networks With Gated Recurrent Units Reduce Glucose Forecasting Error Due to Changes in Sensor Location

BACKGROUND

Continuous glucose monitors (CGMs) have become important tools for providing estimates of glucose to patients with diabetes. Recently, neural networks (NNs) have become a common method for forecasting glucose values using data from CGMs. One method of forecasting glucose values is a time-delay feedforward (FF) NN, but a change in the CGM location on a participant can increase forecast error in a FF NN.

METHODS

In response, we examined a NN with gated recurrent units (GRUs) as a method of reducing forecast error due to changes in sensor location.

RESULTS

We observed that for 13 participants with type 2 diabetes wearing blinded CGMs on both arms for 12 weeks (FreeStyle Libre Pro-Abbott), GRU NNs did not produce significantly different errors in glucose prediction due to sensor location changes (P < .05).

CONCLUSION

We observe that GRU NNs can mitigate error in glucose prediction due to differences in CGM location.

6. Glycemic Goals and Hypoglycemia: Standards of Care in Diabetes-2024

The American Diabetes Association (ADA) "Standards of Care in Diabetes" includes the ADA's current clinical practice recommendations and is intended to provide the components of diabetes care, general treatment goals and guidelines, and tools to evaluate quality of care. Members of the ADA Professional Practice Committee, an interprofessional expert committee, are responsible for updating the Standards of Care annually, or more frequently as warranted. For a detailed description of ADA standards, statements, and reports, as well as the evidence-grading system for ADA's clinical practice recommendations and a full list of Professional Practice Committee members, please refer to Introduction and Methodology. Readers who wish to comment on the Standards of Care are invited to do so at professional.diabetes.org/SOC.

Development and validation of a real-world model to predict 1-year Level 3 (severe) hypoglycaemia risk in adults with diabetes (the iNPHORM study, United States)

AIMS

We aimed to develop and internally validate a real-world prognostic model for Level 3 hypoglycaemia risk compatible with outpatient care in the United States.

MATERIALS AND METHODS

iNPHORM is a 12-month, US-based panel survey. Adults (18-90 years old) with type 1 diabetes mellitus or insulin- and/or secretagogue-treated type 2 diabetes mellitus were recruited from a nationwide, probability-based internet panel. Among participants completing ≥ 1 follow-up questionnaire(s), we modelled 1-year Level 3 hypoglycaemia risk using Andersen and Gill's Cox survival and penalized regression with multiple imputation. Candidate variables were selected for their clinical relevance and ease of capture at point-of-care.

RESULTS

In total, 986 participants [type 1 diabetes mellitus: 17%; men: 49.6%; mean age: 51 (SD: 14.3) years] were analysed. Across follow-up, 035.1 (95% CI: 32.2-38.1)% reported ≥1 Level 3 event(s), and the rate was 5.0 (95% CI: 4.1-6.0) events per person-year. Our final model showed strong discriminative validity and parsimony (optimism corrected c-statistic: 0.77). Numerous variables were selected: age; sex; body mass index; marital status; level of education; insurance coverage; race; ethnicity; food insecurity; diabetes type; glycated haemoglobin value; glycated haemoglobin variability; number, type and dose of various medications; number of SH events requiring hospital care (past year and over follow-up); type and number of comorbidities and complications; number of diabetes-related health care visits (past year); use of continuous/flash glucose monitoring; and general health status.

CONCLUSIONS

iNPHORM is the first US-based primary prognostic study on Level 3 hypoglycaemia. Future model implementation could potentiate risk-tailored strategies that reduce real-world event occurrence and overall diabetes burden.

Risk factors of severe hypoglycemia among patients with type 2 diabetes mellitus in outpatient clinic of tertiary hospital in Indonesia

This study aimed to describe risk factors of severe hypoglycemia in type 2 diabetes mellitus (T2DM) patients in a tertiary care hospital in Indonesia. This study was a retrospective cohort study in the Endocrinology Outpatient Clinic of Dr. Cipto Mangunkusumo National General Hospital, Jakarta, Indonesia. All subjects more than 18 years old who had been visiting the clinic for at least a year were included. Subjects were interviewed whether they had any severe hypoglycemia events within the past year, while data on risk factor variables of severe hypoglycemia was taken from medical records one year before data collection. We recruited 291 subjects, among whom 25.4% suffered at least one episode of severe hypoglycemia within one year. History of severe hypoglycemia (OR 5.864, p ≤ 0.001), eGFR less than 60 mL/min/1.73m2 (OR 1.976, p = 0.028), and insulin use (OR 2.257, p = 0.021) were associated with increased risk of severe hypoglycemia. In conclusion, history of previous severe hypoglycemia, eGFR less than 60 mL/min/1.73m2, and insulin use were associated with severe hypoglycemia.

Development and Validation of an Electronic Health Record-Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus

BACKGROUND

The recent availability of high-quality data from clinical trials, together with machine learning (ML) techniques, presents exciting opportunities for developing prediction models for clinical outcomes.

METHODS

As a proof-of-concept, we translated a hypoglycemia risk model derived from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study into the HypoHazardScore, a risk assessment tool applicable to electronic health record (EHR) data. To assess its performance, we conducted a 16-week clinical study at the University of Minnesota where participants (N = 40) with type 2 diabetes mellitus (T2DM) had hypoglycemia assessed prospectively by continuous glucose monitoring (CGM).

RESULTS

The HypoHazardScore combines 16 risk factors commonly found within the EHR. The HypoHazardScore successfully predicted (area under the curve [AUC] = 0.723) whether participants experienced least one CGM-assessed hypoglycemic event (glucose <54 mg/dL for ≥15 minutes from two CGMs) while significantly correlating with frequency of CGM-assessed hypoglycemic events (r = 0.38) and percent time experiencing CGM-assessed hypoglycemia (r = 0.39). Compared to participants with a low HypoHazardScore (N = 19, score <4, median score of 4), participants with a high HypoHazardScore (N = 21, score ≥4) had more frequent CGM-assessed hypoglycemic events (high: 1.6 ± 2.2 events/week; low: 0.3 ± 0.5 events/week) and experienced more CGM-assessed hypoglycemia (high: 1.4% ± 2.0%; low: 0.2% ± 0.4% time) during the 16-week follow-up.

CONCLUSIONS

We demonstrated that a hypoglycemia risk model can be successfully adapted from the ACCORD data to the EHR, with validation by a prospective study using CGM-assessed hypoglycemia. The HypoHazardScore represents a significant advancement toward implementing an EHR-based decision support system that can help reduce hypoglycemia in patients with T2DM.

Data-based modeling for hypoglycemia prediction: Importance, trends, and implications for clinical practice

Background and objective

Hypoglycemia is a key barrier to achieving optimal glycemic control in people with diabetes, which has been proven to cause a set of deleterious outcomes, such as impaired cognition, increased cardiovascular disease, and mortality. Hypoglycemia prediction has come to play a role in diabetes management as big data analysis and machine learning (ML) approaches have become increasingly prevalent in recent years. As a result, a review is needed to summarize the existing prediction algorithms and models to guide better clinical practice in hypoglycemia prevention.

Materials and methods

PubMed, EMBASE, and the Cochrane Library were searched for relevant studies published between 1 January 2015 and 8 December 2022. Five hypoglycemia prediction aspects were covered: real-time hypoglycemia, mild and severe hypoglycemia, nocturnal hypoglycemia, inpatient hypoglycemia, and other hypoglycemia (postprandial, exercise-related).

Results

From the 5,042 records retrieved, we included 79 studies in our analysis. Two major categories of prediction models are identified by an overview of the chosen studies: simple or logistic regression models based on clinical data and data-based ML models (continuous glucose monitoring data is most commonly used). Models utilizing clinical data have identified a variety of risk factors that can lead to hypoglycemic events. Data-driven models based on various techniques such as neural networks, autoregressive, ensemble learning, supervised learning, and mathematical formulas have also revealed suggestive features in cases of hypoglycemia prediction.

Conclusion

In this study, we looked deep into the currently established hypoglycemia prediction models and identified hypoglycemia risk factors from various perspectives, which may provide readers with a better understanding of future trends in this topic.

Prediction Models for Prognosis of Hypoglycemia in Patients with Diabetes: A Systematic Review and Meta-Analysis

OBJECTIVE

To systematically summarize the reported prediction models for hypoglycemia in patients with diabetes, compare their performance, and evaluate their applicability in clinical practice.

METHODS

We selected studies according to the PRISMA, appraised studies according to the Prediction model Risk of Bias Assessment Tool (PROBAST), and extracted and synthesized the data according to the CHARMS. The databases of PubMed, Web of Science, Embase, and Cochrane Library were searched from inception to 31 October 2021 using a systematic review approach to capture all eligible studies developing and/or validating a prognostic prediction model for hypoglycemia in patients with diabetes. The risk bias and clinical applicability were assessed using the PROBAST. The meta-analysis of the performance of the prediction models were also conducted. The protocol of this study was recorded in PROSPERO (CRD42022309852).

RESULTS

Sixteen studies with 22 models met the eligible criteria. The predictors with the high frequency of occurrence among all models were age, HbA1c, history of hypoglycemia, and insulin use. A meta-analysis of C-statistic was performed for 21 prediction models, and the summary C-statistic and its 95% confidence interval and prediction interval were 0.7699 (0.7299-0.8098), 0.7699 (0.5862-0.9536), respectively. Heterogeneity exists between different hypoglycemia prediction models (τ² was 0.00734≠0).

CONCLUSIONS

The existing predictive models are not recommended for widespread clinical use. A high-quality hypoglycemia screening tool should be developed in future studies.

Examining Sensor Agreement in Neural Network Blood Glucose Prediction

Successful measurements of interstitial glucose are a key component in providing effective care for patients with diabetes. Recently, there has been significant interest in using neural networks to forecast future glucose values from interstitial measurements collected by continuous glucose monitors (CGMs). While prediction accuracy continues to improve, in this work we investigated the effect of physiological sensor location on neural network blood glucose forecasting. We used clinical data from patients with Type 2 Diabetes who wore blinded FreeStyle Libre Pro CGMs (Abbott) on both their right and left arms continuously for 12 weeks. We trained patient-specific prediction algorithms to test the effect of sensor location on neural network forecasting (N = 13, Female = 6, Male = 7). In 10 of our 13 patients, we found at least one significant (P < .05) increase in forecasting error in algorithms which were tested with data taken from a different location than data which was used for training. These reported results were independent from other noticeable physiological differences between subjects (eg, height, age, weight, blood pressure) and independent from overall variance in the data. From these results we observe that CGM location can play a consequential role in neural network glucose prediction.

A New Analysis Tool for Continuous Glucose Monitor Data

BACKGROUND

With the development of continuous glucose monitoring systems (CGMS), detailed glycemic data are now available for analysis. Yet analysis of this data-rich information can be formidable. The power of CGMS-derived data lies in its characterization of glycemic variability. In contrast, many standard glycemic measures like hemoglobin A1c (HbA1c) and self-monitored blood glucose inadequately describe glycemic variability and run the risk of bias toward overreporting hyperglycemia. Methods that adjust for this bias are often overlooked in clinical research due to difficulty of computation and lack of accessible analysis tools.

METHODS

In response, we have developed a new R package rGV, which calculates a suite of 16 glycemic variability metrics when provided a single individual's CGM data. rGV is versatile and robust; it is capable of handling data of many formats from many sensor types. We also created a companion R Shiny web app that provides these glycemic variability analysis tools without prior knowledge of R coding. We analyzed the statistical reliability of all the glycemic variability metrics included in rGV and illustrate the clinical utility of rGV by analyzing CGM data from three studies.

RESULTS

In subjects without diabetes, greater glycemic variability was associated with higher HbA1c values. In patients with type 2 diabetes mellitus (T2DM), we found that high glucose is the primary driver of glycemic variability. In patients with type 1 diabetes (T1DM), we found that naltrexone use may potentially reduce glycemic variability.

CONCLUSIONS

We present a new R package and accompanying web app to facilitate quick and easy computation of a suite of glycemic variability metrics.

Prediction models of diabetes complications: a scoping review

BACKGROUND

Diabetes often places a large burden on people with diabetes (hereafter 'patients') and the society, that is, in part attributable to its complications. However, evidence from models predicting diabetes complications in patients remains unclear. With the collaboration of patient partners, we aimed to describe existing prediction models of physical and mental health complications of diabetes.

METHODS

Building on existing frameworks, we systematically searched for studies in Ovid-Medline and Embase. We included studies describing prognostic prediction models that used data from patients with pre-diabetes or any type of diabetes, published between 2000 and 2020. Independent reviewers screened articles, extracted data and narratively synthesised findings using established reporting standards.

RESULTS

Overall, 78 studies reported 260 risk prediction models of cardiovascular complications (n=42 studies), mortality (n=16), kidney complications (n=14), eye complications (n=10), hypoglycaemia (n=8), nerve complications (n=3), cancer (n=2), fracture (n=2) and dementia (n=1). Prevalent complications deemed important by patients such as amputation and mental health were poorly or not at all represented. Studies primarily analysed data from older people with type 2 diabetes (n=54), with little focus on pre-diabetes (n=0), type 1 diabetes (n=8), younger (n=1) and racialised people (n=10). Per complication, predictors vary substantially between models. Studies with details of calibration and discrimination mostly exhibited good model performance.

CONCLUSION

This rigorous knowledge synthesis provides evidence of gaps in the landscape of diabetes complication prediction models. Future studies should address unmet needs for analyses of complications n> and among patient groups currently under-represented in the literature and should consistently report relevant statistics. SCOPING REVIEW REGISTRATION: https://osf.io/fjubt/.

Identifying patients at increased risk of hypoglycaemia in primary care: Development of a machine learning-based screening tool

INTRODUCTION

In primary care, identifying patients with type 2 diabetes (T2D) who are at increased risk of hypoglycaemia is important for the prevention of hypoglycaemic events. We aimed to develop a screening tool based on machine learning to identify such patients using routinely available demographic and medication data.

METHODS

We used a cohort study design and the Groningen Initiative to ANalyse Type 2 diabetes Treatment (GIANTT) medical record database to develop models for hypoglycaemia risk. The first hypoglycaemic event in the observation period (2007-2013) was the outcome. Demographic and medication data were used as predictor variables to train machine learning models. The performance of the models was compared with a model using additional clinical data using fivefold cross validation with the area under the receiver operator characteristic curve (AUC) as a metric.

RESULTS

We included 13,876 T2D patients. The best performing model including only demographic and medication data was logistic regression with least absolute shrinkage and selection operator, with an AUC of 0.71. Ten variables were included (odds ratio): male gender (0.997), age (0.990), total drug count (1.012), glucose-lowering drug count (1.039), sulfonylurea use (1.62), insulin use (1.769), pre-mixed insulin use (1.109), insulin count (1.827), insulin duration (1.193), and antidepressant use (1.05). The proposed model obtained a similar performance to the model using additional clinical data.

CONCLUSION

Using demographic and medication data, a model for identifying patients at increased risk of hypoglycaemia was developed using machine learning. This model can be used as a tool in primary care to screen for patients with T2D who may need additional attention to prevent or reduce hypoglycaemic events.

Effective Treatment Recommendations for Type 2 Diabetes Management Using Reinforcement Learning: Treatment Recommendation Model Development and Validation

Background

Type 2 diabetes mellitus (T2DM) and its related complications represent a growing economic burden for many countries and health systems. Diabetes complications can be prevented through better disease control, but there is a large gap between the recommended treatment and the treatment that patients actually receive. The treatment of T2DM can be challenging because of different comprehensive therapeutic targets and individual variability of the patients, leading to the need for precise, personalized treatment.

Objective

The aim of this study was to develop treatment recommendation models for T2DM based on deep reinforcement learning. A retrospective analysis was then performed to evaluate the reliability and effectiveness of the models.

Methods

The data used in our study were collected from the Singapore Health Services Diabetes Registry, encompassing 189,520 patients with T2DM, including 6,407,958 outpatient visits from 2013 to 2018. The treatment recommendation model was built based on 80% of the dataset and its effectiveness was evaluated with the remaining 20% of data. Three treatment recommendation models were developed for antiglycemic, antihypertensive, and lipid-lowering treatments by combining a knowledge-driven model and a data-driven model. The knowledge-driven model, based on clinical guidelines and expert experiences, was first applied to select the candidate medications. The data-driven model, based on deep reinforcement learning, was used to rank the candidates according to the expected clinical outcomes. To evaluate the models, short-term outcomes were compared between the model-concordant treatments and the model-nonconcordant treatments with confounder adjustment by stratification, propensity score weighting, and multivariate regression. For long-term outcomes, model-concordant rates were included as independent variables to evaluate if the combined antiglycemic, antihypertensive, and lipid-lowering treatments had a positive impact on reduction of long-term complication occurrence or death at the patient level via multivariate logistic regression.

Results

The test data consisted of 36,993 patients for evaluating the effectiveness of the three treatment recommendation models. In 43.3% of patient visits, the antiglycemic medications recommended by the model were concordant with the actual prescriptions of the physicians. The concordant rates for antihypertensive medications and lipid-lowering medications were 51.3% and 58.9%, respectively. The evaluation results also showed that model-concordant treatments were associated with better glycemic control (odds ratio [OR] 1.73, 95% CI 1.69-1.76), blood pressure control (OR 1.26, 95% CI, 1.23-1.29), and blood lipids control (OR 1.28, 95% CI 1.22-1.35). We also found that patients with more model-concordant treatments were associated with a lower risk of diabetes complications (including 3 macrovascular and 2 microvascular complications) and death, suggesting that the models have the potential of achieving better outcomes in the long term.

Conclusions

Comprehensive management by combining knowledge-driven and data-driven models has good potential to help physicians improve the clinical outcomes of patients with T2DM; achieving good control on blood glucose, blood pressure, and blood lipids; and reducing the risk of diabetes complications in the long term.

Effectiveness of premixed insulin to achieve glycaemic control in type 2 diabetes: A retrospective UK cohort study

AIM

To investigate the effectiveness of premixed insulin for achieving glycaemic outcomes in clinical practice in the UK.

MATERIALS AND METHODS

Electronic medical record data from The Health Improvement Network database were captured for adults with type 2 diabetes (T2D) uncontrolled (HbA1c ≥9%) on two or more oral antihyperglycaemic drugs (OADs) initiating premixed insulin. Effectiveness of premixed insulin was assessed by the probability and incidence of achieving glycaemic outcomes (target HbA1c <7.5% [<58 mmol/mol] and a ≥1% or ≥2% HbA1c reduction) over 24 months.

RESULTS

Data from 974 participants (mean age 62 years; 56% male; 52% obese or extremely obese; mean HbA1c 11.3% [100 mmol/mol]; hypertension 64%, dyslipidaemia 23% and nephropathy 21%) were analysed. The probability of achieving HbA1c  <7.5% was highest during months 3-6 (18.2%), while the cumulative probability of achieving this target plateaued between months 15-24 (15.7%-16.0%). Incidence of achieving all glycaemic outcomes plateaued after 12 months and differed by baseline HbA1c, but not OAD use. Factors affecting some glycaemic outcomes included a body mass index >40 kg/m2 and co-morbidities including nephropathy and stroke.

CONCLUSIONS

In people with uncontrolled T2D (HbA1c ≥9%), glycaemic outcome achievement on premixed insulin was low at 6 months with little additional clinical benefit beyond 12 months, suggesting a high unmet need for early, timely treatment changes with more effective, simpler therapies.

Development of a hypoglycaemia risk score to identify high-risk individuals with advanced type 2 diabetes in DEVOTE

AIMS

The ability to differentiate patient populations with type 2 diabetes at high risk of severe hypoglycaemia could impact clinical decision making. The aim of this study was to develop a risk score, using patient characteristics, that could differentiate between populations with higher and lower 2-year risk of severe hypoglycaemia among individuals at increased risk of cardiovascular disease.

MATERIALS AND METHODS

Two models were developed for the risk score based on data from the DEVOTE cardiovascular outcomes trials. The first, a data-driven machine-learning model, used stepwise regression with bidirectional elimination to identify risk factors for severe hypoglycaemia. The second, a risk score based on known clinical risk factors accessible in clinical practice identified from the data-driven model, included: insulin treatment regimen; diabetes duration; sex; age; and glycated haemoglobin, all at baseline. Both the data-driven model and simple risk score were evaluated for discrimination, calibration and generalizability using data from DEVOTE, and were validated against the external LEADER cardiovascular outcomes trial dataset.

RESULTS

Both the data-driven model and the simple risk score discriminated between patients at higher and lower hypoglycaemia risk, and performed similarly well based on the time-dependent area under the curve index (0.63 and 0.66, respectively) over a 2-year time horizon.

CONCLUSIONS

Both the data-driven model and the simple hypoglycaemia risk score were able to discriminate between patients at higher and lower risk of severe hypoglycaemia, the latter doing so using easily accessible clinical data. The implementation of such a tool (http://www.hyporiskscore.com/) may facilitate improved recognition of, and education about, severe hypoglycaemia risk, potentially improving patient care.

Use of Antihyperglycemic Medications in U.S. Adults: An Analysis of the National Health and Nutrition Examination Survey

OBJECTIVE

1) To examine trends in the use of diabetes medications and 2) to determine whether physicians individualize diabetes treatment as recommended by the American Diabetes Association (ADA).

RESEARCH DESIGN AND METHODS

We conducted a retrospective, cross-sectional analysis of 2003-2016 National Health and Nutrition Examination Survey (NHANES) data. We included people ≥18 years who had ever been told they had diabetes, had an HbA_1c >6.4%, or had a fasting plasma glucose >125 mg/dL. Pregnant women and patients aged <20 years receiving only insulin were excluded. We assessed trends in use of ADA's seven preferred classes from 2003-2004 to 2015-2016. We also examined use by hypoglycemia risk (sulfonylureas, insulin, and meglitinides), weight effect (sulfonylureas, thiazolidinediones [TZDs], insulin, and meglitinides), cardiovascular benefit (canagliflozin, empagliflozin, and liraglutide), and cost (brand-name medications and insulin analogs).

RESULTS

The final sample included 6,323 patients. The proportion taking any medication increased from 58% in 2003-2004 to 67% in 2015-2016 (P < 0.001). Use of metformin and insulin analogs increased, while use of sulfonylureas, TZDs, and human insulin decreased. Following the 2012 ADA recommendation, the choice of drug did not vary significantly by older age, weight, or presence of cardiovascular disease. Patients with low HbA_1c, or HbA_1c <6%, and age ≥65 years were less likely to receive hypoglycemia-inducing medications, while older patients with comorbidities were more likely. Insurance, but not income, was associated with the use of higher-cost medications.

CONCLUSIONS

Following ADA recommendations, the use of metformin increased, but physicians generally did not individualize treatment according to patients' characteristics. Substantial opportunities exist to improve pharmacologic management of diabetes.

Multiple predictively equivalent risk models for handling missing data at time of prediction: With an application in severe hypoglycemia risk prediction for type 2 diabetes

The presence of missing data at the time of prediction limits the application of risk models in clinical and research settings. Common ways of handling missing data at the time of prediction include measuring the missing value and employing statistical methods. Measuring missing value incurs additional cost, whereas previously reported statistical methods results in reduced performance compared to when all variables are measured. To tackle these challenges, we introduce a new strategy, the MMTOP algorithm (Multiple models for Missing values at Time Of Prediction), which does not require measuring additional data elements or data imputation. Specifically, at model construction time, the MMTOP constructs multiple predictively equivalent risk models utilizing different risk factor sets. The collection of models are stored and to be queried at prediction time. To predict an individual's risk in the presence of incomplete data, the MMTOP selects the risk model based on measurement availability for that individual from the collection of predictively equivalent models and makes the risk prediction with the selected model. We illustrate the MMTOP with severe hypoglycemia (SH) risk prediction based on data from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study. We identified 77 predictively equivalent models for SH with cross-validated c-index of 0.77 ± 0.03. These models are based on 77 distinct risk factor sets containing 12-17 risk factors. In terms of handling missing data at the time of prediction, the MMTOP outperforms all four tested competitor methods and maintains consistent performance as the number of missing variables increase.

Development and Validation of a Hypoglycemia Risk Model for Intensive Insulin Therapy in Patients with Type 2 Diabetes

AIMS

To develop a simple hypoglycemic prediction model to evaluate the risk of hypoglycemia during hospitalization in patients with type 2 diabetes treated with intensive insulin therapy.

METHODS

We performed a cross-sectional chart review study utilizing the electronic database of the Third Affiliated Hospital of Sun Yat-sen University, and included 257 patients with type 2 diabetes undergoing intensive insulin therapy in the Department of Endocrinology and Metabolism. Logistic regression analysis was used to derive the clinical prediction rule with hypoglycemia (blood glucose ≤ 3.9 mmol/L) as the main result, and internal verification was performed.

RESULTS

In the derivation cohort, the incidence of hypoglycemia was 51%. The final model selected included three variables: fasting insulin, fasting blood glucose, and total treatment time. The area under the curve (AUC) of this model was 0.666 (95% CI: 0.594-0.738, P < 0.001).

CONCLUSIONS

The model's hypoglycemia prediction and the actual occurrence are in good agreement. The variable data was easy to obtain and the evaluation method was simple, which could provide a reference for the prevention and treatment of hypoglycemia and screen patients with a high risk of hypoglycemia.

Approaches to Risk Assessment Among Older Patients With Diabetes

PURPOSE OF REVIEW

A patient's prognosis and risk of adverse drug effects are important considerations for individualizing care of older patients with diabetes. This review summarizes the evidence for risk assessment and proposes approaches for clinicians in the context of current clinical guidelines.

RECENT FINDINGS

Diabetes guidelines vary in their recommendations for how life expectancy should be estimated and used to inform the selection of glycemic targets. Readily available prognostic tools may improve estimation of life expectancy but require validation among patients with diabetes. Treatment decisions based on prognosis are difficult for clinicians to communicate and for patients to understand. Determining hypoglycemia risk involves assessing major risk factors; models to synthesize these factors have been developed. Applying risk assessment to individualize diabetes care is complex and currently relies heavily on clinician judgment. More research is need to validate structured approaches to risk assessment and determine how to incorporate them into patient-centered diabetes care.

Artificial Pancreas Systems for People With Type 2 Diabetes: Conception and Design of the European CLOSE Project

In the last 10 years tremendous progress has been made in the development of artificial pancreas (AP) systems for people with type 1 diabetes (T1D). The pan-European consortium CLOSE (Automated Glu cose Contro l at H ome for People with Chronic Disea se) is aiming to develop integrated AP solutions (APplus) tailored to the needs of people with type 2 diabetes (T2D). APplus comprises a product and service package complementing the AP system by obligatory training as well as home visits and telemedical consultations on demand. Outcome predictors and performance indicators shall help to identify people who could benefit most from AP usage and facilitate the measurement of AP impact in diabetes care. In a first step CLOSE will establish a scalable APplus model case working at the interface between patients, homecare service providers, and payers in France. CLOSE will then scale up APplus by pursuing geographic distribution, targeting additional audiences, and enhancing AP functionalities and interconnectedness. By being part of the European Institute of Innovation and Technology (EIT) Health public-private partnership, CLOSE is committed to the EIT "knowledge triangle" pursuing the integrated advancement of technology, education, and business creation. Putting stakeholders, education, and impact into the center of APplus advancement is considered key for achieving wide AP use in T2D care.