Introduction
In today's world, numerous diets are promoted, each with its unique combination of macronutrient compositions and fasting schedules. However, a lack of consensus exists regarding the impact of these diets due to the variability in study designs, measured variables, and populations studied. This fragmented approach hinders the integration of insights into a comprehensive understanding. Digital twin technology presents a promising solution, offering a personalized computer model that describes the underlying physiology of an individual, enabling the simulation of responses to different diets and fasting schedules.
The Need for Integrated Insights
Fasting and diet are crucial components of cardiovascular disease prevention. The absence of consensus on optimal diet schemes is partly due to the disconnected knowledge derived from various clinical studies. Mathematical models describing meal responses could potentially integrate these insights, but current models lack critical mechanisms such as protein metabolism and dynamic glycogen regulation.
Digital Twins: A Potential Solution
Digital twins, personalized computer models that describe the underlying physiology of a specific person, can address the lack of consensus by incorporating specific aspects of each study into the appropriate parts of the model. These twins can be updated with data from various studies, allowing for a more comprehensive understanding of metabolic responses.
Developing a New Digital Twin Tool
To address the shortcomings of existing models, a new and significantly extended model has been developed and trained using data from four different clinical studies. This model can predict new situations and variables, personalized responses, and data from a new study involving fasting and oral protein tolerance tests (OPTT).
The new model incorporates several new features, including:
Read also: Evaluating Weight Loss Programs
- Intracellular metabolism in the liver
- Long-term energy regulation via liver and kidney glycogen
- Protein metabolism
- Hepatic interconversion between glucose and amino acids
These additions allow the model to incorporate data and insights from a wide variety of studies measuring fasting, glycogen, gluconeogenesis, and both hepatic and kidney endogenous glucose production.
Qualitative Improvements of the New Model
The new digital twin tool demonstrates significant qualitative improvements compared to previous models, particularly in its ability to simulate OPTTs before and after fasting. Unlike previous glucose-centric models, the new tool includes a biochemical description, conversion in the liver followed by endogenous glucose production (EGP), and exhibits a negligible glucose response in fed conditions but a clear response in fasting conditions.
Validation of the New Model
The reliability of the new model has been tested both quantitatively and qualitatively using new data that has not been used for parameter estimation. Both estimation and validation data include various aspects of a new protein metabolism and fasting-oriented study designed to generate new responses not present in any of the other data.
The new model has also been fitted to the original data used to develop the 'Dalla Man model,' demonstrating that it has not lost any critical ability compared to its predecessors.
Metabolic Flexibility and Digital Twins
Metabolic flexibility, the ability to switch fuel utilization between glucose and fat, is a key indicator of metabolic health. Optimizing metabolic health with digital twins that model an individual's metabolic flexibility profile can gamify the process of health optimization and predict long-term health outcomes.
Read also: Weight Loss Guide Andalusia, AL
A metabolic flexibility-based digital twin model can drive adherence to lifestyle changes, enable personalized health management, and facilitate the early detection of subclinical metabolic decline.
Gamification Module for Monitoring Fuel Switching
One key module of the proposed digital twin is the gamification module, which monitors fuel switching and promotes adherence to healthy behaviors. This module uses glucose and ketone body (KB) measurements and details of a fixed health regimen to identify the occurrence of fuel switching within a preset period. A Metabolic Flexibility Score (MFS) is then computed based on the fuel-switching speed.
AI-Powered Module for Predicting Long-Term Health Outcomes
Another critical feature integrated into the digital twin is predictive analytics for evaluating long-term health outcomes resulting from sustained fuel switching. This AI-powered module links health regimens with long-term health outcomes by integrating health regimen adherence, baseline and post-intervention health data collection, and metabolic flexibility assessment.
Digital Twins in Diabetes Management
Digital twin technology has shown promise in diabetes management. By creating a digital twin for each patient that simulates their metabolic status, dietary intake, blood glucose levels, and lifestyle habits, personalized dietary and lifestyle recommendations can be offered to minimize postprandial glucose response (PPGRs) and improve overall glycemic control.
Digital Twins in Cardiovascular Medicine
Digital twin technology also has the potential to transform cardiovascular medicine by enhancing disease phenotyping, enriching diagnostic workflows, and optimizing procedural planning. Cardiac replicas can be created to simulate different blood pressure and diuretic drugs, comparing them to other patients with similar profiles.
Read also: Beef jerky: A high-protein option for shedding pounds?
Multi-Level Digital Twins for Insulin Resistance
To better understand the progression of insulin resistance, a method is needed that can combine different timescales and physiological levels. Digital twins, consisting of combined mechanistic mathematical models, offer such a method. An interconnected twin can correctly predict independent data from weight increase and weight loss studies, both for weight changes, fasting plasma insulin and glucose levels, and intracellular insulin signaling.
Digital Health Interventions and AI
Digital health interventions, particularly those leveraging AI, offer a promising alternative to traditional methods for managing and preventing metabolic diseases. AI approaches can alleviate the burden of continuous glucose monitoring (CGM) by enabling infrequent CGM use while still providing insights into blood sugar management.
A Flexible, AI-Supported Intervention
A flexible, AI-supported intervention ("January V2") has been designed to reduce the user burden of CGM while promoting better metabolic health outcomes. This system focuses on infrequent CGM use and personalized, adaptive feedback, making it more sustainable for long-term use and appealing to a broad population.
Results of a Retrospective Cohort Study
A retrospective cohort study involving 944 users who utilized the January V2 app over a 14-day period found significant improvements in time in range (TIR) among users with lower baseline values. The study also observed significant weight loss, particularly in the prediabetes cohort and among power users.
Impact of AI Recommendations on Glycemic Control
The introduction of AI recommendations contributed additional benefits to glycemic control beyond the initial effects of self-monitoring and logging, as evidenced by the significant improvement in TIR after the implementation of AI recommendations.
Changes in Calorie and Macronutrient Intake
The January V2 program aims to reduce carbohydrate and sugar intake while increasing protein and fiber intake per calorie. This goal was achieved across all groups, with notable dietary adjustments observed in the T2D group.
User Engagement and Improved Outcomes
The study found a clear correlation between highly engaged "power users" and improved outcomes in TIR and weight loss compared to less engaged users, highlighting the importance of user engagement in digital health interventions.