Quantifying Input Behaviors That Influence Clinical Outcomes in Diabetes and Other Chronic Illnesses

Lewis, Dana

doi:10.1177/19322968211068445

Cited by 4 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are high rates of EPI in diabetes, and many people go undiagnosed for long periods, as is true with other common gastrointestinal conditions that are frequently present in people with diabetes. This is yet another indicator that glycemic outcomes may be influenced by variables outside of an individual’s control 5 and ability to self-manage (eg someone with EPI can’t make more enzymes), and points to the need for further study of many of these GI-related conditions and their impact on glycemic outcomes and GV. The use of AID and CGM should be funded and encouraged for studies in such related gastrointestinal conditions to fill the knowledge gaps about glycemic impacts of medications such as those used in PERT.…”

Section: Discussionmentioning

confidence: 99%

“…4 With the advent of new diabetes technologies including continuous glucose monitors (CGM), connected insulin pumps and insulin pens, and automated insulin delivery (AID) systems, it is now possible to answer questions that have previously been left as gaps in the medical research. 5 PERT, in particular, may be well suited to study with an assessment of changes in post-meal glycemic variability (GV) in people with insulin-requiring diabetes. Alongside analyzing diabetes data and meal intake records from an individual with an open-source AID for a period of time both before and after using PERT, this article proposes a method for assessing GV and other related changes following the onset of new medication such as PERT.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Glycemic Variability Assessment in Newly Treated Exocrine Pancreatic Insufficiency With Type 1 Diabetes

Lewis¹,

Shahid

2022

J Diabetes Sci Technol

Self Cite

View full text Add to dashboard Cite

Background: Thirty-nine percent of people with type 1 diabetes may have lowered pancreatic elastase levels, correlated with exocrine pancreatic insufficiency (EPI or PEI). EPI is treated with oral supplementation of pancreatic enzymes. Little is known about the glycemic impact of pancreatic enzyme replacement therapy (PERT) in people with diabetes. This article demonstrates a method of assessing glycemic variability (GV), glycemic outcomes, and other changes in an individual with type 1 diabetes using open-source automated insulin delivery (AID). Method: Macronutrient, PERT intake, and EPI-related symptoms were self-tracked; diabetes data were collected automatically via an open-source AID system. Diabetes data were uploaded via Nightscout to Open Humans and downloaded for analysis alongside self-tracked data (food, PERT). Glycemic outcomes, macronutrients, PERT dosing, and a variety of GV metrics following meals were evaluated for one month before and one month after PERT commencement. Breakfast was assessed independently across both time periods. Results: In an n = 1 individual using an open-source AID, time in range was already above goal and improved further after PERT commencement. Glucose rate of change and excursions >180 mg/dL were reduced; mean high blood glucose index was reduced overall and more so specifically at breakfast following PERT commencement. Conclusions: GV can aid in assessing response to new-onset medications, as was demonstrated in this article for n = 1 individual with type 1 diabetes (using an open-source AID) after commencing PERT for newly identified EPI. GV may be useful for evaluating the efficacy of new-onset medications for people with insulin-requiring diabetes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Glycemic Variability Assessment in Newly Treated Exocrine Pancreatic Insufficiency With Type 1 Diabetes

Lewis¹,

Shahid

2022

J Diabetes Sci Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Insulin pumps and CGM can be combined as part of an automated insulin delivery (AID) system, where data from each device flows through an algorithm to determine insulin-delivery rates and automatically adjust them to keep glucose values in a specific range, requiring less work from people with diabetes and also improving quality of life outcomes [ 1 ]. AID systems further generate rich data regarding the conditions (such as sensor glucose values, user-entered information such as targets or carbohydrates, and current and previous insulin delivery) in which it operates [ 2 ]. Exploring these rich data sources unveils opportunities for scientific discoveries to understand individual glucose outcomes better and improve diabetes technology.…”

Section: Introductionmentioning

confidence: 99%

Long-Term Glucose Forecasting for Open-Source Automated Insulin Delivery Systems: A Machine Learning Study with Real-World Variability Analysis

Zafar

Lewis²,

Shahid

2023

Healthcare

Self Cite

View full text Add to dashboard Cite

Glucose forecasting serves as a backbone for several healthcare applications, including real-time insulin dosing in people with diabetes and physical activity optimization. This paper presents a study on the use of machine learning (ML) and deep learning (DL) methods for predicting glucose variability (GV) in individuals with open-source automated insulin delivery systems (AID). A three-stage experimental framework is employed in this work to systematically implement and evaluate ML/DL methods on a large-scale diabetes dataset collected from individuals with open-source AID. The first stage involves data collection, the second stage involves data preparation and exploratory analysis, and the third stage involves developing, fine-tuning, and evaluating ML/DL models. The performance and resource costs of the models are evaluated alongside relative and proportional errors for 17 GV metrics. Evaluation of fine-tuned ML/DL models shows considerable accuracy in glucose forecasting and variability analysis up to 48 h in advance. The average MAE ranges from 2.50 mg/dL for long short-term memory models (LSTM) to 4.94 mg/dL for autoregressive integrated moving average (ARIMA) models, and the RMSE ranges from 3.7 mg/dL for LSTM to 7.67 mg/dL for ARIMA. Model execution time is proportional to the amount of data used for training, with long short-term memory models having the lowest execution time but the highest memory consumption compared to other models. This work successfully incorporates the use of appropriate programming frameworks, concurrency-enhancing tools, and resource and storage cost estimators to encourage the sustainable use of ML/DL in real-world AID systems.

show abstract

“…With increasing access to diabetes technology, we will increasingly move from guessing to choosing what manual behaviors a person with diabetes wants to do to achieve their goal outcomes, whether those be clinical outcomes, reducing effort, improving quality of life, or all three. 4 It is especially important to acknowledge the disparities, too, in who has access to tools that enable them to achieve their desired diabetes outcomes 5 and ensure that any individuals who do not have access to diabetes technology are not also stigmatized for that.…”

mentioning

confidence: 99%

Language Matters in Diabetes and in Diabetes Science and Research

Lewis¹

2022

J Diabetes Sci Technol

Self Cite

View full text Add to dashboard Cite

Quantifying Input Behaviors That Influence Clinical Outcomes in Diabetes and Other Chronic Illnesses

Cited by 4 publications

References 6 publications

Glycemic Variability Assessment in Newly Treated Exocrine Pancreatic Insufficiency With Type 1 Diabetes

Glycemic Variability Assessment in Newly Treated Exocrine Pancreatic Insufficiency With Type 1 Diabetes

Long-Term Glucose Forecasting for Open-Source Automated Insulin Delivery Systems: A Machine Learning Study with Real-World Variability Analysis

Language Matters in Diabetes and in Diabetes Science and Research

Contact Info

Product

Resources

About