Dataset Information

Evolutionary algorithm for the optimization of meal intake and insulin administration in patients with type 2 diabetes.

ABSTRACT: The optimal management of type 2 diabetes (T2DM) is complex and involves an appropriate combination of diet, exercise, and different pharmacological treatments. Artificial intelligence-based tools have been shown to be very useful for the diagnosis and treatment of diverse pathologies, including diabetes. In the present study, we present a proof of concept of the potential of an evolutionary algorithm to optimize the meal size, timing and insulin dose for the control of glycemia. We found that an appropriate distribution of food intake throughout the day permits a reduction in the insulin dose required to maintain glycemia within the range recommended by the American Diabetes Association for patients with T2DM of a range of severities. Furthermore, the effects of restrictions to both the timing and amount of food ingested were assessed, and we found that an increase in the amount of insulin was required to control glycemia as dietary intake became more restricted. In the near future, the use of these computational tools should permit patients with T2DM to optimize their personal meal schedule and insulin dose, according to the severity of their diabetes.

SUBMITTER: Gonzalez-Flo E

PROVIDER: S-EPMC10115945 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evolutionary algorithm for the optimization of meal intake and insulin administration in patients with type 2 diabetes.

Gonzalez-Flo Eva E Kheirabadi Elaheh E Rodriguez-Caso Carlos C Macía Javier J

Frontiers in physiology 20230406

The optimal management of type 2 diabetes (T2DM) is complex and involves an appropriate combination of diet, exercise, and different pharmacological treatments. Artificial intelligence-based tools have been shown to be very useful for the diagnosis and treatment of diverse pathologies, including diabetes. In the present study, we present a proof of concept of the potential of an evolutionary algorithm to optimize the meal size, timing and insulin dose for the control of glycemia. We found that a ...[more]

PMID: 37089422

Similar Datasets

Project description:BackgroundSelf-monitoring of blood glucose (SMBG) using web-based diabetes management platforms has demonstrated promise in managing type 2 diabetes (T2D). However, the effectiveness of such systems incorporating algorithm-guided insulin titration has not been extensively studied in Asian populations.ObjectiveThis study evaluates the efficacy and safety of the ALRT telehealth solution-a US Food and Drug Administration-cleared, web-based platform that integrates SMBG with algorithm-driven insulin dose adjustments-in improving glycemia in insulin-treated T2D.MethodsThis 24-week, pre-post intervention study enrolled 25 adults with T2D (mean age 58.9, SD 7.0 y; n=14, 56% male) on twice-daily premixed insulin. Inclusion criteria included a baseline hemoglobin A1c (HbA1c) level between 7.5% to 9.9% (58-86 mmol/mol), a BMI ≤40 kg/m², and experience with SMBG. Participants uploaded twice-daily SMBG data weekly via a mobile app, which generated insulin titration recommendations based on a predefined algorithm. Physicians reviewed and approved the recommendations, which were then communicated back to participants via the app. The primary outcome was the change in HbA1c level from baseline to 24 weeks. Secondary outcomes included changes in fasting plasma glucose, insulin dose, hypoglycemia incidence, and SMBG adherence.ResultsParticipants achieved significant reductions in HbA1c level from 8.6% (70 mmol/mol) at baseline to 7.4% (57 mmol/mol) at 24 weeks (P<.001), with reductions of 0.8% and 0.4% in the first and second 12 weeks, respectively. Fasting plasma glucose decreased from 8.7 (SD 2.0) mmol/L to 7.1 (SD 1.4) mmol/L (P<.001). Mean total daily insulin dose increased modestly from 0.73 (SD 0.31) units/kg/day to 0.79 (SD 0.34) units/kg/day (P=.007). Participants demonstrated high adherence, completing 97.3% (327/336) of prescribed SMBG measurements. During the study, 48% (12/25) of participants experienced at least 1 hypoglycemia episode, predominantly mild hypoglycemia (85/96, 88.5%; glucose 3.0-3.9 mmol/L). Hypoglycemia episodes increased from 24 during weeks 0-12 to 72 during weeks 13-24. There were no episodes of severe hypoglycemia requiring external assistance. BMI increased slightly from 29.0 (SD 3.6) kg/m² to 29.5 (SD 3.6) kg/m² (P=.03), reflecting a modest weight gain associated with improved glycemia.ConclusionsIn conclusion, patients with insulin-treated T2D initiated on a web-based glucose monitoring system with algorithm-guided dosing recommendations showed significant improvement in glycemic control compared to baseline. High adherence rates underscore the feasibility of integrating algorithm-guided insulin titration into routine care. While hypoglycemia incidence rose slightly, episodes were predominantly mild, and no severe events occurred. This intervention shows promise for broader adoption in T2D management, particularly in resource-constrained settings.

Project description:The current inverse planning methods for intensity modulated radiation therapy (IMRT) are limited because they are not designed to explore the trade-offs between the competing objectives of tumor and normal tissues. The goal was to develop an efficient multiobjective optimization algorithm that was flexible enough to handle any form of objective function and that resulted in a set of Pareto optimal plans.A hierarchical evolutionary multiobjective algorithm designed to quickly generate a small diverse Pareto optimal set of IMRT plans that meet all clinical constraints and reflect the optimal trade-offs in any radiation therapy plan was developed. The top level of the hierarchical algorithm is a multiobjective evolutionary algorithm (MOEA). The genes of the individuals generated in the MOEA are the parameters that define the penalty function minimized during an accelerated deterministic IMRT optimization that represents the bottom level of the hierarchy. The MOEA incorporates clinical criteria to restrict the search space through protocol objectives and then uses Pareto optimality among the fitness objectives to select individuals. The population size is not fixed, but a specialized niche effect, domination advantage, is used to control the population and plan diversity. The number of fitness objectives is kept to a minimum for greater selective pressure, but the number of genes is expanded for flexibility that allows a better approximation of the Pareto front.The MOEA improvements were evaluated for two example prostate cases with one target and two organs at risk (OARs). The population of plans generated by the modified MOEA was closer to the Pareto front than populations of plans generated using a standard genetic algorithm package. Statistical significance of the method was established by compiling the results of 25 multiobjective optimizations using each method. From these sets of 12-15 plans, any random plan selected from a MOEA population had a 11.3% +/- 0.7% chance of dominating any random plan selected by a standard genetic package with 0.04% +/- 0.02% chance of domination in reverse. By implementing domination advantage and protocol objectives, small and diverse populations of clinically acceptable plans that approximated the Pareto front could be generated in a fraction of 1 h. Acceleration techniques implemented on both levels of the hierarchical algorithm resulted in short, practical runtimes for multiobjective optimizations.The MOEA produces a diverse Pareto optimal set of plans that meet all dosimetric protocol criteria in a feasible amount of time. The final goal is to improve practical aspects of the algorithm and integrate it with a decision analysis tool or human interface for selection of the IMRT plan with the best possible balance of successful treatment of the target with low OAR dose and low risk of complication for any specific patient situation.

Dataset Information

Evolutionary algorithm for the optimization of meal intake and insulin administration in patients with type 2 diabetes.

Publications

Evolutionary algorithm for the optimization of meal intake and insulin administration in patients with type 2 diabetes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets