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.

Artificial Intelligence for Predicting and Diagnosing Complications of Diabetes

Artificial intelligence can use real-world data to create models capable of making predictions and medical diagnosis for diabetes and its complications. The aim of this commentary article is to provide a general perspective and present recent advances on how artificial intelligence can be applied to improve the prediction and diagnosis of six significant complications of diabetes including (1) gestational diabetes, (2) hypoglycemia in the hospital, (3) diabetic retinopathy, (4) diabetic foot ulcers, (5) diabetic peripheral neuropathy, and (6) diabetic nephropathy.

Machine Learning Models for Inpatient Glucose Prediction

PURPOSE OF REVIEW

Glucose management in the hospital is difficult due to non-static factors such as antihyperglycemic and steroid doses, renal function, infection, surgical status, and diet. Given these complex and dynamic factors, machine learning approaches can be leveraged for prediction of glucose trends in the hospital to mitigate and prevent suboptimal hypoglycemic and hyperglycemic outcomes. Our aim was to review the clinical evidence for the role of machine learning-based models in predicting hospitalized patients' glucose trajectory.

RECENT FINDINGS

The published literature on machine learning algorithms has varied in terms of population studied, outcomes of interest, and validation methods. There have been tools developed that utilize data from both continuous glucose monitors and large electronic health records (EHRs). With increasing sample sizes, inclusion of a greater number of predictor variables, and use of more advanced machine learning algorithms, there has been a trend in recent years towards increasing predictive accuracy for glycemic outcomes in the hospital setting. While current models predicting glucose trajectory offer promising results, they have not been tested prospectively in the clinical setting. Accurate machine learning algorithms have been developed and validated for prediction of hypoglycemia and hyperglycemia in the hospital. Further work is needed in implementation/integration of machine learning models into EHR systems, with prospective studies to evaluate effectiveness and safety of such clinical decision support on glycemic and other clinical outcomes.

A Pharmacist-Driven Glycemic Control Protocol to Reduce the Rate of Severe Hypoglycemia in High-Risk Patients

Purpose: Hospital pharmacists contribute to patient safety and quality initiatives by overseeing the prescribing of antidiabetic medications. A pharmacist-driven glycemic control protocol was developed to reduce the rate of severe hypoglycemia events (SHE) in high-risk hospitalized patients. Methods: We retrospectively analyzed the rates of SHE (defined as blood glucose ≤40 mg/dL), before and after instituting a pharmacist-driven glycemic control protocol over a 4-year period. A hospital glucose management team that included a lead Certified Diabetes Educator Pharmacist (CDEP), 5 pharmacists trained in diabetes, a lead hospitalist, critical care and hospital providers established a process to first identify patients at risk for severe hypoglycemia and then implement our protocol. Criteria from the American Diabetes Association and the American Association of Clinical Endocrinologists was utilized to identify and treat patients at risk for SHE. We analyzed and compared the rate of SHE and physician acceptance rates before and after protocol initiation. Results: From January 2015 to March 2019, 18 297 patients met criteria for this study; 139 patients experienced a SHE and approximately 80% were considered high risk diabetes patients. Physician acceptance rates for the new protocol ranged from 77% to 81% from the year of initiation (2016) through 2018. The absolute risk reduction of SHE was 9 events per 1000 hospitalized diabetic patients and the relative risk reduction was 74% SHE from the start to the end of the protocol implementation. Linear regression analysis demonstrated that SHE decreased by 1.5 events per 1000 hospitalized diabetic patients (95% confidence interval, -1.54 to -1.48, P < .001) during the 2 years following the introduction of the protocol. This represents a 15% relative reduction of SHE per year. Conclusion: The pharmacist-driven glycemic control protocol was well accepted by our hospitalists and led to a significant reduction in SHE in high-risk diabetes patient groups at our hospital. It was cost effective and strengthened our physician-pharmacist relationship while improving diabetes care.

Development and validation of a machine learning model for classification of next glucose measurement in hospitalized patients

BACKGROUND

Inpatient glucose management can be challenging due to evolving factors that influence a patient's blood glucose (BG) throughout hospital admission. The purpose of our study was to predict the category of a patient's next BG measurement based on electronic medical record (EMR) data.

METHODS

EMR data from 184,361 admissions containing 4,538,418 BG measurements from five hospitals in the Johns Hopkins Health System were collected from patients who were discharged between January 1, 2015 and May 31, 2019. Index BGs used for prediction included the 5th to penultimate BG measurements (N = 2,740,539). The outcome was category of next BG measurement: hypoglycemic (BG  ≤  70 mg/dl), controlled (BG 71-180 mg/dl), or hyperglycemic (BG > 180 mg/dl). A random forest algorithm that included a broad range of clinical covariates predicted the outcome and was validated internally and externally.

FINDINGS

In our internal validation test set, 72·8%, 25·7%, and 1·5% of BG measurements occurring after the index BG were controlled, hyperglycemic, and hypoglycemic respectively. The sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·77/0·81, 0·77/0·89, and 0·73/0·91, respectively. On external validation in four hospitals, the ranges of sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·64-0·70/0·80-0·87, 0·75-0·80/0·82-0·84, and 0·76-0·78/0·87-0·90, respectively.

INTERPRETATION

A machine learning algorithm using EMR data can accurately predict the category of a hospitalized patient's next BG measurement. Further studies should determine the effectiveness of integration of this model into the EMR in reducing rates of hypoglycemia and hyperglycemia.

Digital interventions to improve safety and quality of inpatient diabetes management: A systematic review

IMPORTANCE

Diabetes is common amongst hospitalised patients and contributes to increased length of stay and poorer outcomes. Digital transformation, particularly the implementation of electronic medical records (EMRs), is rapidly occurring across the healthcare sector and provides an opportunity to improve the safety and quality of inpatient diabetes care. Alongside this revolution has been a considerable and ongoing evolution of digital interventions to optimise care of inpatients with diabetes including optimisation of EMRs, digital clinical decision support systems (CDSS) and solutions utilising data visibility to allow targeted patient review.

OBJECTIVE

To systematically appraise the recent literature to determine which digitally-enabled interventions including EMR, CDSS and data visibility solutions improve the safety and quality of non-critical care inpatient diabetes management.

METHODS

Pubmed, Embase and Cochrane databases were searched for suitable articles. Selected articles underwent quality assessment and analysis with results grouped by intervention type.

RESULTS

1202 articles were identified with 42 meeting inclusion criteria. Four key interventions were identified; computerised physician order entry (n = 4), clinician decision support systems (n = 21), EMR driven active case finding (data visibility solutions) and targeted patient review (n = 10) and multicomponent system interventions (n = 7). Studies reported on glucometric outcomes, evidence-based medication ordering including medication errors, and patient and user outcomes. An improvement in glucometric measures particularly mean blood glucose and proportion of target range blood glucose levels and rates of evidence-based insulin prescribing were consistently demonstrated.

CONCLUSION

Digitally-enabled interventions utilised to improve quality and safety of inpatient diabetes care were heterogenous in design. The majority of studies across all intervention types reported positive effects for evidence-based prescribing and glucometric outcomes. There was less evidence for digital interventions reducing diabetes medication administration errors or impacting patient outcomes (length of stay).

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.

Development and Validation of a Machine Learning Model to Predict Near-Term Risk of Iatrogenic Hypoglycemia in Hospitalized Patients

Importance

Accurate clinical decision support tools are needed to identify patients at risk for iatrogenic hypoglycemia, a potentially serious adverse event, throughout hospitalization.

Objective

To predict the risk of iatrogenic hypoglycemia within 24 hours after each blood glucose (BG) measurement during hospitalization using a machine learning model.

Design, Setting, and Participants

This retrospective cohort study, conducted at 5 hospitals within the Johns Hopkins Health System, included 54 978 admissions of 35 147 inpatients who had at least 4 BG measurements and received at least 1 U of insulin during hospitalization between December 1, 2014, and July 31, 2018. Data from the largest hospital were split into a 70% training set and 30% test set. A stochastic gradient boosting machine learning model was developed using the training set and validated on internal and external validation.

Exposures

A total of 43 clinical predictors of iatrogenic hypoglycemia were extracted from the electronic medical record, including demographic characteristics, diagnoses, procedures, laboratory data, medications, orders, anthropomorphometric data, and vital signs.

Main Outcomes and Measures

Iatrogenic hypoglycemia was defined as a BG measurement less than or equal to 70 mg/dL occurring within the pharmacologic duration of action of administered insulin, sulfonylurea, or meglitinide.

Results

This cohort study included 54 978 admissions (35 147 inpatients; median [interquartile range] age, 66.0 [56.0-75.0] years; 27 781 [50.5%] male; 30 429 [55.3%] White) from 5 hospitals. Of 1 612 425 index BG measurements, 50 354 (3.1%) were followed by iatrogenic hypoglycemia in the subsequent 24 hours. On internal validation, the model achieved a C statistic of 0.90 (95% CI, 0.89-0.90), a positive predictive value of 0.09 (95% CI, 0.08-0.09), a positive likelihood ratio of 4.67 (95% CI, 4.59-4.74), a negative predictive value of 1.00 (95% CI, 1.00-1.00), and a negative likelihood ratio of 0.22 (95% CI, 0.21-0.23). On external validation, the model achieved C statistics ranging from 0.86 to 0.88, positive predictive values ranging from 0.12 to 0.13, negative predictive values of 0.99, positive likelihood ratios ranging from 3.09 to 3.89, and negative likelihood ratios ranging from 0.23 to 0.25. Basal insulin dose, coefficient of variation of BG, and previous hypoglycemic episodes were the strongest predictors.

Conclusions and Relevance

These findings suggest that iatrogenic hypoglycemia can be predicted in a short-term prediction horizon after each BG measurement during hospitalization. Further studies are needed to translate this model into a real-time informatics alert and evaluate its effectiveness in reducing the incidence of inpatient iatrogenic hypoglycemia.

Predicting hypoglycemia in hospitalized patients with diabetes: A derivation and validation study

AIMS

Develop and validate a model for predicting hypoglycemia in inpatients.

METHODS

Derivation cohort: patients treated with hypoglycemic drugs and admitted to the departments of medicine of a university hospital during 2016.

VALIDATION

patients admitted to a community hospital, and patients admitted to a university hospital in the north of Israel, 2017-2018. Data available in the electronic patient record (EPR) during the first hours of hospital stay were used to develop a logistic model to predict the probability of hypoglycemia. The performance of the model was measured in the validation cohorts.

RESULTS

In the derivation cohort, hypoglycemia was measured in 474 out of 3605 patients, 13.1%. The logistic model to predict hypoglycemia included age, nasogastric or percutaneous gastrostomy tube, Charlson score, vomiting, chest pain, acute renal failure, insulin, hemoglobin and diastolic blood pressure. The area under the ROC curve (AUROC) was 0.71 (95% CI 0.69-0.73). In the highest probability group the percentage of hypoglycemia was 24.3% (258/1061). In the two validation groups hypoglycemia was measured in 269/2592 patients (11.1%); and 393/3635 (10.8%). AUROC was 0.72 (95% CI 0.68-0.76); and 0.71 (95% CI 0.68-0.74). In the highest probability groups hypoglycemia was measured in 28.1% (111/395); and 23.0% (211/909) of patients.

CONCLUSIONS

The derived model performed well in the validation cohorts. Assuming that most of the hypoglycemia episodes could be prevented we would need to invest efforts to avoid hypoglycemia in 4-5 patients to prevent one episode of hypoglycemia.

Practice-enhancing publications about the medication-use process in 2018

PURPOSE

This article identifies, prioritizes, and summarizes published literature on the medication-use process (MUP) from calendar year 2018 that can impact health-system pharmacy daily practice. The MUP is the foundational system that provides the framework for safe medication utilization within the healthcare environment. The MUP is defined in this article as having the following steps: prescribing/transcribing, dispensing, administration, and monitoring. Articles that evaluated one of the steps were gauged for their usefulness toward daily practice change.

SUMMARY

A PubMed search was conducted in February 2019 for articles published in calendar year 2018 using targeted Medical Subject Headings (MeSH) keywords, targeted non-MeSH keywords, and the table of contents of selected pharmacy journals, providing a total of 43,977 articles. A thorough review identified 62 potentially significant articles: 9 for prescribing/transcribing, 12 for dispensing, 13 for administration, and 28 for monitoring. Ranking of the articles for importance by peers led to the selection of key articles from each category. The highest-ranked articles are briefly summarized, with a mention of why they are important within health-system pharmacy. The other articles are listed for further review and evaluation.

CONCLUSION

It is important to routinely review the published literature and to incorporate significant findings into daily practice. This article assists in identifying and summarizing recent impactful contributions to the MUP literature. Health-system pharmacists have an active role in improving the MUP in their institution, and awareness of significant published studies can assist in changing practice at the institutional level.

Common inpatient hypoglycemia phenotypes identified from an automated electronic health record-based prediction model

PURPOSE

Common inpatient hypoglycemia risk factor patterns (phenotypes) from an electronic health record (EHR)-based prediction model and preventive strategies were identified.

METHODS

Patients admitted to 2 large academic medical centers who were in the top fifth percentile of a previously developed hypoglycemia risk score and developed hypoglycemia (blood glucose [BG] of <50mg/dL) were included in the study. Frequencies of all combinations of ≥4 risk factors contributing to the risk score among these patients were determined to identify common risk patterns. Clinical pharmacists developed clinical vignettes for each common pattern and formulated medication therapy management recommendations for hypoglycemia prevention.

RESULTS

A total of 401 admissions with a hypoglycemic event were identified among 1,875 admissions whose hypoglycemic risk was in the top fifth percentile among all admissions that received antihyperglycemic drugs and evaluated. Five distinct phenotypes emerged: (1) frail patients with history of hypoglycemia receiving insulin on hospital day 1, (2) a rapid downward trend in BG values in patients receiving an insulin infusion or with a history of hypoglycemia, (3) administration of insulin in the presence of an active nothing by mouth order in frail patients, (4) repeated low BG level in frail patients, and (5) inadequate night-time BG monitoring for patients on long-acting insulin. The 5 themes jointly described 53.0% of high-risk patients who experienced hypoglycemia.

CONCLUSION

Five distinct phenotypes that are prevalent in patients at greatest risk for inpatient hypoglycemia were identified.