Machine Learning Models for Inpatient Glucose Prediction

Inpatient Hypoglycemic Rate Reduction Through the Implementation of Prescriber Targeted Decision Support Tools

PURPOSE OF REVIEW

Hypoglycemia has been shown to increase mortality and length of hospital stay and is now reportable to the Centers for Medicare and Medicaid Services as a quality measure. The purpose of this article is to review clinical decision support (CDS) tools designed to reduce inpatient hypoglycemic events.

RECENT FINDINGS

CDS tools such as order set development, medication alerts, and data visibility have all been shown to be valuable tools in improving glycemic performance. This is especially true for hyperglycemic events with mixed results in hypoglycemia prevention. CDS solutions may be targeted directly to healthcare professionals or to specialty diabetes management teams to reduce hypoglycemia. Not all organizations have the financial resources to develop a diabetes management team so non-interruptive alerts may serve as an important tool to alert health care professionals of individuals with additional risk factors for the development of hypoglycemia. CDS can provide a mechanism to reduce the risk of hypoglycemia in hospitalized individuals. Although new research is promising, more studies are needed to determine future directions including the impact and feasibility of continuous glucose monitoring and predictive models to improve overall glycemic performance.

16. Diabetes Care in the Hospital: Standards of Care in Diabetes-2025

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.

Riemannian manifold-based geometric clustering of continuous glucose monitoring to improve personalized diabetes management

BACKGROUND

Continuous Glucose Monitoring (CGM) provides a detailed representation of glucose fluctuations in individuals, offering a rich dataset for understanding glycemic control in diabetes management. This study explores the potential of Riemannian manifold-based geometric clustering to analyze and interpret CGM data for individuals with Type 1 Diabetes (T1D) and healthy controls (HC), aiming to enhance diabetes management and treatment personalization.

METHODS

We utilized CGM data from publicly accessible datasets, covering both T1D individuals on insulin and HC. Data were segmented into daily intervals, from which 27 distinct glycemic features were extracted. Uniform Manifold Approximation and Projection (UMAP) was then applied to reduce dimensionality and visualize the data, with model performance validated through correlation analysis between Silhouette Score (SS) against HC cluster and HbA1c levels.

RESULTS

UMAP effectively distinguished between T1D on daily insulin and HC groups, with data points clustering according to glycemic profiles. Moderate inverse correlations were observed between SS against HC cluster and HbA1c levels, supporting the clinical relevance of the UMAP-derived metric.

CONCLUSIONS

This study demonstrates the utility of UMAP in enhancing the analysis of CGM data for diabetes management. We revealed distinct clustering of glycemic profiles between healthy individuals and diabetics on daily insulin indicating that in most instances insulin does not restore a normal glycemic phenotype. In addition, the SS quantifies day by day the degree of this continued dysglycemia and therefore potentially offers a novel approach for personalized diabetes care.

A Clinician's Guide to Understanding Bias in Critical Clinical Prediction Models

This narrative review focuses on the role of clinical prediction models in supporting informed decision-making in critical care, emphasizing their 2 forms: traditional scores and artificial intelligence (AI)-based models. Acknowledging the potential for both types to embed biases, the authors underscore the importance of critical appraisal to increase our trust in models. The authors outline recommendations and critical care examples to manage risk of bias in AI models. The authors advocate for enhanced interdisciplinary training for clinicians, who are encouraged to explore various resources (books, journals, news Web sites, and social media) and events (Datathons) to deepen their understanding of risk of bias.

Predicting hypoglycemia in ICU patients: a machine learning approach

BACKGROUND

The current study sets out to develop and validate a robust machine-learning model utilizing electronic health records (EHR) to forecast the risk of hypoglycemia among ICU patients in Jordan.

RESEARCH DESIGN AND METHODS

The present study drew upon a substantial cohort of 13,567 patients admitted 26,248 times to the intensive care unit (ICU) over 10 years from July 2012 to July 2022. The primary outcome of interest was the occurrence of any hypoglycemic episode during the patient's ICU stay. Developing and testing predictor models was conducted using Python machine-learning libraries.

RESULTS

A total of 1,896 were eligible to participate in the study, 206 experienced at least one hypoglycemic episode. Eight machine-learning models were trained to predict hypoglycemia. All models showed predicting power with a range of 74.53-99.69 for AUROC. Except for Naive Bayes, the six remaining models performed distinctly better than the basic logistic regression usually used for prediction in epidemiological studies. CatBoost model was consistently the best performer with the highest AUROC (0.99), accuracy and precision, sensitivity and specificity, and recall.

CONCLUSIONS

We used machine learning to anticipate the likelihood of hypoglycemia, which can significantly decrease hypoglycemia incidents and enhance patient outcomes.

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

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

Glu-Ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients

Diabetes is a chronic metabolic disorder characterized by elevated blood glucose levels, posing significant health risks such as cardiovascular disease, and nerve, kidney, and eye damage. Effective management of blood glucose is essential for individuals with diabetes to mitigate these risks. This study introduces the Glu-Ensemble, a deep learning framework designed for precise blood glucose forecasting in patients with type 2 diabetes. Unlike other predictive models, Glu-Ensemble addresses challenges related to small sample sizes, data quality issues, reliance on strict statistical assumptions, and the complexity of models. It enhances prediction accuracy and model generalizability by utilizing larger datasets and reduces bias inherent in many predictive models. The framework's unified approach, as opposed to patient-specific models, eliminates the need for initial calibration time, facilitating immediate blood glucose predictions for new patients. The obtained results indicate that Glu-Ensemble surpasses traditional methods in accuracy, as measured by root mean square error, mean absolute error, and error grid analysis. The Glu-Ensemble framework emerges as a promising tool for blood glucose level prediction in type 2 diabetes patients, warranting further investigation in clinical settings for its practical application.

Development and Validation of Inpatient Hypoglycemia Models Centered Around the Insulin Ordering Process

BACKGROUND

The insulin ordering process is an opportunity to provide clinicians with hypoglycemia risk predictions, but few hypoglycemia models centered around the insulin ordering process exist.

METHODS

We used data on adult patients, admitted in 2019 to non-ICU floors of a large teaching hospital, who had orders for subcutaneous insulin. Our outcome was hypoglycemia, defined as a blood glucose (BG) <70 mg/dL within 24 hours after ordering insulin. We trained and evaluated models to predict hypoglycemia at the time of placing an insulin order, using logistic regression, random forest, and extreme gradient boosting (XGBoost). We compared performance using area under the receiver operating characteristic curve (AUCs) and precision-recall curves. We determined recall at our goal precision of 0.30.

RESULTS

Of 21 052 included insulin orders, 1839 (9%) were followed by a hypoglycemic event within 24 hours. Logistic regression, random forest, and XGBoost models had AUCs of 0.81, 0.80, and 0.79, and recall of 0.44, 0.49, and 0.32, respectively. The most significant predictor was the lowest BG value in the 24 hours preceding the order. Predictors related to the insulin order being placed at the time of the prediction were useful to the model but less important than the patient's history of BG values over time.

CONCLUSIONS

Hypoglycemia within the next 24 hours can be predicted at the time an insulin order is placed, providing an opportunity to integrate decision support into the medication ordering process to make insulin therapy safer.

Heterogeneous temporal representation for diabetic blood glucose prediction

Background and aims: Blood glucose prediction (BGP) has increasingly been adopted for personalized monitoring of blood glucose levels in diabetic patients, providing valuable support for physicians in diagnosis and treatment planning. Despite the remarkable success achieved, applying BGP in multi-patient scenarios remains problematic, largely due to the inherent heterogeneity and uncertain nature of continuous glucose monitoring (CGM) data obtained from diverse patient profiles. Methodology: This study proposes the first graph-based Heterogeneous Temporal Representation (HETER) network for multi-patient Blood Glucose Prediction (BGP). Specifically, HETER employs a flexible subsequence repetition method (SSR) to align the heterogeneous input samples, in contrast to the traditional padding or truncation methods. Then, the relationships between multiple samples are constructed as a graph and learned by HETER to capture global temporal characteristics. Moreover, to address the limitations of conventional graph neural networks in capturing local temporal dependencies and providing linear representations, HETER incorporates both a temporally-enhanced mechanism and a linear residual fusion into its architecture. Results: Comprehensive experiments were conducted to validate the proposed method using real-world data from 112 patients in two hospitals, comparing it with five well-known baseline methods. The experimental results verify the robustness and accuracy of the proposed HETER, which achieves the maximal improvement of 31.42%, 27.18%, and 34.85% in terms of MAE, MAPE, and RMSE, respectively, over the second-best comparable method. Discussions: HETER integrates global and local temporal information from multi-patient samples to alleviate the impact of heterogeneity and uncertainty. This method can also be extended to other clinical tasks, thereby facilitating efficient and accurate capture of crucial pattern information in structured medical data.

Point of care blood glucose devices in the hospital setting

Dysglycemia is common among hospitalized patients. Accurate point-of-care (POC) glucose monitoring is necessary for the safe administration of insulin. Unfortunately, POC glucose meters are not all created equal. Interfering factors such as abnormal hematocrit, abnormal oxygen tension, and oxidizing/reducing substances can lead to inaccurate glucose measurements and result in inappropriate insulin dosing. The introduction of autocorrecting glucose meters has changed the POC testing landscape. Autocorrecting glucose meters provide more accurate measurements and have been associated with improved glycemic control in hospitalized patients. Continuous glucose monitoring has also created interest in using these platforms in at-risk inpatient populations. Future glucose monitoring technologies such as artificial intelligence/machine learning, wearable smart devices, and closed-loop insulin management systems are poised to transform glycemic management. The goal of this review is to provide an overview of glucose monitoring technology, summarize the clinical impact of glucose monitoring accuracy, and highlight emerging and future POC glucose monitoring technologies.

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.