Fatemeh Sarani Rad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fatemeh Sarani Rad has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Juan Li
Computer Science Department, North Dakota State University, 1320 Albrecht Blvd, Fargo, ND, 58105, United States, 1 7012319662
7 shared publications Ehsan Bitaraf
4 shared publicationsMaryam Jafarpour
4 shared publicationsVajiheh Jami
Center for Statistics and Information Technology, Ministry of Health and Medical Education
3 shared publicationsEbrahim Keshavarz Safari
Center for Statistics & Information Technology, Ministry of Health and Medical Education, Tehran, Iran
2 shared publications- Ehsan Bitaraf
Center for Technology and Innovation in Cardiovascular Informatics, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
2 shared publications
Latest Publications
- Open Access
- 18 June 2026
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 11 (1) , e83059
Digital Twin Applications in Diabetes Management: Scoping Review
Background: Digital twin (DT) systems have emerged as a promising approach in health care, enabling real-time, patient-specific virtual modeling and personalized interventions. In diabetes care, DTs offer the potential to revolutionize glucose management, decision support, and therapy personalization through integration of real-time and longitudinal patient data. Objective: This scoping review mapped the current landscape of DT applications in diabetes and synthesized evidence across 13 research questions organized into 7 thematic domains: system design, target conditions, data sources, personalization strategies, intelligence and adaptability, validation methods, and implementation considerations. Methods: This scoping review was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) and JBI methodological guidance for scoping reviews. A literature search was performed in PubMed, IEEE Xplore, Scopus, and Web of Science for studies published up to April 2025; all databases were last searched on June 23, 2025. Eligible studies were original empirical articles in English that described patient-specific DT systems or closely related individualized virtual models applied to diabetes diagnosis, monitoring, management, treatment, or complication-related care. Reviews, editorials, commentaries, theoretical papers without original data, and studies not focused on diabetes were excluded. Furthermore, FSR, MJ, and KK independently screened records and assessed full texts, with disagreements resolved through discussion and, when needed, by EB. Data were charted using a structured framework based on 13 predefined research questions, and were synthesized descriptively and thematically. Results: Of 208 records identified, 123 underwent title and abstract screening, 39 full texts were assessed for eligibility, and 28 studies were included. Most studies focused on type 1 or type 2 diabetes and used data-driven, hybrid, or simulation-based DT approaches. Common clinical applications included therapeutic control, glucose prediction, decision support, and disease management. Lifestyle data, wearables, continuous glucose monitoring, and electronic health records were the dominant inputs, while personalization relied on adaptive feedback, insulin optimization, and behavior-driven tools. Intelligent features, such as adaptive learning, explainable artificial intelligence, and real-time synchronization, enhanced adaptability, although human oversight was rare. Validation was mainly retrospective or simulation-based, with few clinical trials; reported outcomes included improved hemoglobin A 1c , time-in-range, and reduced hypoglycemia. Ethical discussions focused on data privacy, while implementation barriers centered on validation gaps, data quality, and workflow integration. Conclusions: DT research in diabetes is expanding and shows strong potential for personalized and data-driven care; however, the evidence base remains heterogeneous, inconsistently reported, and limited in prospective clinical validation. Key gaps include standardized definitions, robust real-world evaluation, fairness and governance considerations, and integration into clinical workflows. Future work should prioritize clinically grounded validation, regulatory readiness, and interoperable architectures to support safe, equitable, and scalable implementation.
- 18 June 2026
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 11 (1) , e83059
Open AccessDigital Twin Applications in Diabetes Management: Scoping Review
Background: Digital twin (DT) systems have emerged as a promising approach in health care, enabling real-time, patient-specific virtual modeling and personalized interventions. In diabetes care, DTs offer the potential to revolutionize glucose management, decision support, and therapy personalization through integration of real-time and longitudinal patient data. Objective: This scoping review mapped the current landscape of DT applications in diabetes and synthesized evidence across 13 research questions organized into 7 thematic domains: system design, target conditions, data sources, personalization strategies, intelligence and adaptability, validation methods, and implementation considerations. Methods: This scoping review was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) and JBI methodological guidance for scoping reviews. A literature search was performed in PubMed, IEEE Xplore, Scopus, and Web of Science for studies published up to April 2025; all databases were last searched on June 23, 2025. Eligible studies were original empirical articles in English that described patient-specific DT systems or closely related individualized virtual models applied to diabetes diagnosis, monitoring, management, treatment, or complication-related care. Reviews, editorials, commentaries, theoretical papers without original data, and studies not focused on diabetes were excluded. Furthermore, FSR, MJ, and KK independently screened records and assessed full texts, with disagreements resolved through discussion and, when needed, by EB. Data were charted using a structured framework based on 13 predefined research questions, and were synthesized descriptively and thematically. Results: Of 208 records identified, 123 underwent title and abstract screening, 39 full texts were assessed for eligibility, and 28 studies were included. Most studies focused on type 1 or type 2 diabetes and used data-driven, hybrid, or simulation-based DT approaches. Common clinical applications included therapeutic control, glucose prediction, decision support, and disease management. Lifestyle data, wearables, continuous glucose monitoring, and electronic health records were the dominant inputs, while personalization relied on adaptive feedback, insulin optimization, and behavior-driven tools. Intelligent features, such as adaptive learning, explainable artificial intelligence, and real-time synchronization, enhanced adaptability, although human oversight was rare. Validation was mainly retrospective or simulation-based, with few clinical trials; reported outcomes included improved hemoglobin A 1c , time-in-range, and reduced hypoglycemia. Ethical discussions focused on data privacy, while implementation barriers centered on validation gaps, data quality, and workflow integration. Conclusions: DT research in diabetes is expanding and shows strong potential for personalized and data-driven care; however, the evidence base remains heterogeneous, inconsistently reported, and limited in prospective clinical validation. Key gaps include standardized definitions, robust real-world evaluation, fairness and governance considerations, and integration into clinical workflows. Future work should prioritize clinically grounded validation, regulatory readiness, and interoperable architectures to support safe, equitable, and scalable implementation.
- Top Cited PapersOpen Access
- 8 January 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10 (1) , e78499
Technologies, Clinical Applications, and Implementation Barriers of Digital Twins in Precision Cardiology: Systematic Review
Background: Digital twin systems are emerging as promising tools in precision cardiology, enabling dynamic, patient-specific simulations to support diagnosis, risk assessment, and treatment planning. However, the current landscape of cardiovascular digital twin development, validation, and implementation remains fragmented, with substantial variability in modeling approaches, data use, and reporting practices. Objective: This systematic review aims to synthesize the current state of cardiovascular digital twin research by addressing 11 research questions spanning modeling technologies, data infrastructure, clinical applications, clinical impact, implementation barriers, and ethical considerations. Methods: We systematically searched 5 databases (PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar) and screened 330 records. Forty-two original studies met the predefined eligibility criteria and were included. Data extraction was guided by 11 thematic research questions. Mechanistic and artificial intelligence (AI) or machine learning (ML) modeling strategies, data modalities, visualization formats, clinical use cases, reported impacts, limitations, and ethical or legal issues were coded and summarized. Risk of bias was evaluated using a custom checklist for modeling studies, the Prediction Model Risk of Bias Assessment Tool (PROBAST) for prediction models, and the Risk of Bias in Non-Randomized Studies - of Interventions (ROBINS-I) for observational studies. Results: Most digital twins (29/42, 69%) relied on mechanistic models, while hybrid mechanistic–data-driven approaches and purely data-driven designs were less frequent (13/42, 31%). Only 18 studies explicitly described ML or AI, most often deep learning, Bayesian methods, or optimization algorithms. Personalization depended primarily on imaging (32/42, 76%) and electrocardiography or other electrical signals (18/42, 43%). Visualization was dominated (41/42, 98%) by static figures and anatomical snapshots. Clinically, digital twins were most commonly applied to therapy planning, risk prediction, and monitoring. Reported benefits focused on improved decision-making and therapy-related impacts, with occasional (8/42, 19%) reports of increased accuracy or faster diagnosis, but there was limited evidence for downstream improvements in patient outcomes. Key barriers included strong model assumptions and simplifications; high computational cost; data quality and availability constraints; limited external validation; and challenges in real-time performance, workflow integration, and usability. Explicit discussion of ethical, legal, or governance issues was rare (7/42, 17%). Conclusions: Cardiovascular digital twins show substantial potential to advance precision cardiology by linking personalized physiological models with clinical decision support, particularly for therapy planning and risk prediction in arrhythmia and heart failure. However, real-world implementation is constrained by methodological heterogeneity, restricted data and validation practices, limited openness of code and models, and sparse engagement with ethical and governance questions. Future research should prioritize standardized evaluation frameworks, robust clinical validation, interoperable and user-centered system design, and ethically grounded, patient-centered development to realize the full clinical value of digital twin systems.
- 8 January 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10 (1) , e78499
Top Cited PapersOpen AccessTechnologies, Clinical Applications, and Implementation Barriers of Digital Twins in Precision Cardiology: Systematic Review
Background: Digital twin systems are emerging as promising tools in precision cardiology, enabling dynamic, patient-specific simulations to support diagnosis, risk assessment, and treatment planning. However, the current landscape of cardiovascular digital twin development, validation, and implementation remains fragmented, with substantial variability in modeling approaches, data use, and reporting practices. Objective: This systematic review aims to synthesize the current state of cardiovascular digital twin research by addressing 11 research questions spanning modeling technologies, data infrastructure, clinical applications, clinical impact, implementation barriers, and ethical considerations. Methods: We systematically searched 5 databases (PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar) and screened 330 records. Forty-two original studies met the predefined eligibility criteria and were included. Data extraction was guided by 11 thematic research questions. Mechanistic and artificial intelligence (AI) or machine learning (ML) modeling strategies, data modalities, visualization formats, clinical use cases, reported impacts, limitations, and ethical or legal issues were coded and summarized. Risk of bias was evaluated using a custom checklist for modeling studies, the Prediction Model Risk of Bias Assessment Tool (PROBAST) for prediction models, and the Risk of Bias in Non-Randomized Studies - of Interventions (ROBINS-I) for observational studies. Results: Most digital twins (29/42, 69%) relied on mechanistic models, while hybrid mechanistic–data-driven approaches and purely data-driven designs were less frequent (13/42, 31%). Only 18 studies explicitly described ML or AI, most often deep learning, Bayesian methods, or optimization algorithms. Personalization depended primarily on imaging (32/42, 76%) and electrocardiography or other electrical signals (18/42, 43%). Visualization was dominated (41/42, 98%) by static figures and anatomical snapshots. Clinically, digital twins were most commonly applied to therapy planning, risk prediction, and monitoring. Reported benefits focused on improved decision-making and therapy-related impacts, with occasional (8/42, 19%) reports of increased accuracy or faster diagnosis, but there was limited evidence for downstream improvements in patient outcomes. Key barriers included strong model assumptions and simplifications; high computational cost; data quality and availability constraints; limited external validation; and challenges in real-time performance, workflow integration, and usability. Explicit discussion of ethical, legal, or governance issues was rare (7/42, 17%). Conclusions: Cardiovascular digital twins show substantial potential to advance precision cardiology by linking personalized physiological models with clinical decision support, particularly for therapy planning and risk prediction in arrhythmia and heart failure. However, real-world implementation is constrained by methodological heterogeneity, restricted data and validation practices, limited openness of code and models, and sparse engagement with ethical and governance questions. Future research should prioritize standardized evaluation frameworks, robust clinical validation, interoperable and user-centered system design, and ethically grounded, patient-centered development to realize the full clinical value of digital twin systems.
- Open Access
- 4 July 2025
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 10 (1) , e72874
Privacy-Preserving Glycemic Management in Type 1 Diabetes: Development and Validation of a Multiobjective Federated Reinforcement Learning Framework
Background: Effective diabetes management requires precise glycemic control to prevent both hypoglycemia and hyperglycemia, yet existing machine learning (ML) and reinforcement learning (RL) approaches often fail to balance competing objectives. Traditional RL-based glucose regulation systems primarily focus on single-objective optimization, overlooking factors such as minimizing insulin overuse, reducing glycemic variability, and ensuring patient safety. Furthermore, these approaches typically rely on centralized data processing, which raises privacy concerns due to the sensitive nature of health care data. There is a critical need for a decentralized, privacy-preserving framework that can personalize blood glucose regulation while addressing the multiobjective nature of diabetes management. Objective: This study aimed to develop and validate PRIMO-FRL (Privacy-Preserving Reinforcement Learning for Individualized Multi-Objective Glycemic Management Using Federated Reinforcement Learning), a novel framework that optimizes clinical objectives—maximizing time in range (TIR), reducing hypoglycemia and hyperglycemia, and minimizing glycemic risk—while preserving patient privacy. Methods: We developed PRIMO-FRL, integrating multiobjective reward shaping to dynamically balance glucose stability, insulin efficiency, and risk reduction. The model was trained and tested using simulated data from 30 simulated patients (10 children, 10 adolescents, and 10 adults) generated with the Food and Drug Administration (FDA)–approved UVA/Padova simulator. A comparative analysis was conducted against state-of-the-art RL and ML models, evaluating performance using metrics such as TIR, hypoglycemia (180 mg/dL), and glycemic risk scores. Results: The PRIMO-FRL model achieved a robust overall TIR of 76.54%, with adults demonstrating the highest TIR at 81.48%, followed by children at 77.78% and adolescents at 70.37%. Importantly, the approach eliminated hypoglycemia, with 0.0% spent below 70 mg/dL across all cohorts, significantly outperforming existing methods. Mild hyperglycemia (180-250 mg/dL) was observed in adolescents (29.63%), children (22.22%), and adults (18.52%), with adults exhibiting the best control. Furthermore, the PRIMO-FRL approach consistently reduced glycemic risk scores, demonstrating improved safety and long-term stability in glucose regulation.. Conclusions: Our findings highlight the potential of PRIMO-FRL as a transformative, privacy-preserving approach to personalized glycemic management. By integrating federated RL, this framework eliminates hypoglycemia, improves TIR, and preserves data privacy by decentralizing model training. Unlike traditional centralized approaches that require sharing sensitive health data, PRIMO-FRL leverages federated learning to keep patient data local, significantly reducing privacy risks while enabling adaptive and personalized glucose control. This multiobjective optimization strategy offers a scalable, secure, and clinically viable solution for real-world diabetes care. The ability to train personalized models across diverse populations without exposing raw data makes PRIMO-FRL well-suited for deployment in privacy-sensitive health care environments. These results pave the way for future clinical adoption, demonstrating the potential of privacy-preserving artificial intelligence in optimizing glycemic regulation while maintaining security, adaptability, and personalization.
- 4 July 2025
- Published by JMIR Publications Inc. in JMIR Diabetes
- Vol. 10 (1) , e72874
Open AccessPrivacy-Preserving Glycemic Management in Type 1 Diabetes: Development and Validation of a Multiobjective Federated Reinforcement Learning Framework
Background: Effective diabetes management requires precise glycemic control to prevent both hypoglycemia and hyperglycemia, yet existing machine learning (ML) and reinforcement learning (RL) approaches often fail to balance competing objectives. Traditional RL-based glucose regulation systems primarily focus on single-objective optimization, overlooking factors such as minimizing insulin overuse, reducing glycemic variability, and ensuring patient safety. Furthermore, these approaches typically rely on centralized data processing, which raises privacy concerns due to the sensitive nature of health care data. There is a critical need for a decentralized, privacy-preserving framework that can personalize blood glucose regulation while addressing the multiobjective nature of diabetes management. Objective: This study aimed to develop and validate PRIMO-FRL (Privacy-Preserving Reinforcement Learning for Individualized Multi-Objective Glycemic Management Using Federated Reinforcement Learning), a novel framework that optimizes clinical objectives—maximizing time in range (TIR), reducing hypoglycemia and hyperglycemia, and minimizing glycemic risk—while preserving patient privacy. Methods: We developed PRIMO-FRL, integrating multiobjective reward shaping to dynamically balance glucose stability, insulin efficiency, and risk reduction. The model was trained and tested using simulated data from 30 simulated patients (10 children, 10 adolescents, and 10 adults) generated with the Food and Drug Administration (FDA)–approved UVA/Padova simulator. A comparative analysis was conducted against state-of-the-art RL and ML models, evaluating performance using metrics such as TIR, hypoglycemia (180 mg/dL), and glycemic risk scores. Results: The PRIMO-FRL model achieved a robust overall TIR of 76.54%, with adults demonstrating the highest TIR at 81.48%, followed by children at 77.78% and adolescents at 70.37%. Importantly, the approach eliminated hypoglycemia, with 0.0% spent below 70 mg/dL across all cohorts, significantly outperforming existing methods. Mild hyperglycemia (180-250 mg/dL) was observed in adolescents (29.63%), children (22.22%), and adults (18.52%), with adults exhibiting the best control. Furthermore, the PRIMO-FRL approach consistently reduced glycemic risk scores, demonstrating improved safety and long-term stability in glucose regulation.. Conclusions: Our findings highlight the potential of PRIMO-FRL as a transformative, privacy-preserving approach to personalized glycemic management. By integrating federated RL, this framework eliminates hypoglycemia, improves TIR, and preserves data privacy by decentralizing model training. Unlike traditional centralized approaches that require sharing sensitive health data, PRIMO-FRL leverages federated learning to keep patient data local, significantly reducing privacy risks while enabling adaptive and personalized glucose control. This multiobjective optimization strategy offers a scalable, secure, and clinically viable solution for real-world diabetes care. The ability to train personalized models across diverse populations without exposing raw data makes PRIMO-FRL well-suited for deployment in privacy-sensitive health care environments. These results pave the way for future clinical adoption, demonstrating the potential of privacy-preserving artificial intelligence in optimizing glycemic regulation while maintaining security, adaptability, and personalization.
- Open Access
Optimizing Nutritional Decisions: A Particle Swarm Optimization–Simulated Annealing-Enhanced Analytic Hierarchy Process Approach for Personalized Meal Planning
Background/Objective: Nutritionists play a crucial role in guiding individuals toward healthier lifestyles through personalized meal planning; however, this task involves navigating a complex web of factors, including health conditions, dietary restrictions, cultural preferences, and socioeconomic constraints. The Analytic Hierarchy Process (AHP) offers a valuable framework for structuring these multi-faceted decisions but inconsistencies can hinder its effectiveness in pairwise comparisons. Methods: This paper proposes a novel hybrid Particle Swarm Optimization–Simulated Annealing (PSO-SA) algorithm to refine inconsistent AHP weight matrices, ensuring a consistent and accurate representation of the nutritionist’s expertise and client preferences. Our approach merges PSO’s global search capabilities with SA’s local search precision, striking an optimal balance between exploration and exploitation. Results: We demonstrate the practical utility of our algorithm through real-world use cases involving personalized meal planning for individuals with specific dietary needs and preferences. Results showcase the algorithm’s efficiency in achieving consistency and surpassing standard PSO accuracy. Conclusion: By integrating the PSO-SA algorithm into a mobile app, we empower nutritionists with an advanced decision-making tool for creating tailored meal plans that promote healthier dietary choices and improved client outcomes. This research represents a significant advancement in multi-criteria decision-making for nutrition, offering a robust solution to the inconsistency challenge in AHP and paving the way for more effective and personalized dietary interventions.
Open AccessOptimizing Nutritional Decisions: A Particle Swarm Optimization–Simulated Annealing-Enhanced Analytic Hierarchy Process Approach for Personalized Meal Planning
Background/Objective: Nutritionists play a crucial role in guiding individuals toward healthier lifestyles through personalized meal planning; however, this task involves navigating a complex web of factors, including health conditions, dietary restrictions, cultural preferences, and socioeconomic constraints. The Analytic Hierarchy Process (AHP) offers a valuable framework for structuring these multi-faceted decisions but inconsistencies can hinder its effectiveness in pairwise comparisons. Methods: This paper proposes a novel hybrid Particle Swarm Optimization–Simulated Annealing (PSO-SA) algorithm to refine inconsistent AHP weight matrices, ensuring a consistent and accurate representation of the nutritionist’s expertise and client preferences. Our approach merges PSO’s global search capabilities with SA’s local search precision, striking an optimal balance between exploration and exploitation. Results: We demonstrate the practical utility of our algorithm through real-world use cases involving personalized meal planning for individuals with specific dietary needs and preferences. Results showcase the algorithm’s efficiency in achieving consistency and surpassing standard PSO accuracy. Conclusion: By integrating the PSO-SA algorithm into a mobile app, we empower nutritionists with an advanced decision-making tool for creating tailored meal plans that promote healthier dietary choices and improved client outcomes. This research represents a significant advancement in multi-criteria decision-making for nutrition, offering a robust solution to the inconsistency challenge in AHP and paving the way for more effective and personalized dietary interventions.
- Open Access
- 28 March 2024
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 14 (4) , 359
Personalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach
Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and personal health knowledge graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange while ensuring high levels of accuracy in data representation and health insights. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it, enhancing the precision and accuracy of the care provided. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As a proof of concept, we have demonstrated the versatility of our digital twins by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.
- 28 March 2024
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 14 (4) , 359
Open AccessPersonalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach
Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and personal health knowledge graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange while ensuring high levels of accuracy in data representation and health insights. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it, enhancing the precision and accuracy of the care provided. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As a proof of concept, we have demonstrated the versatility of our digital twins by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.
- Open Access
- 15 March 2024
- Published by MDPI AG in Preprints.org
Personalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach
Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and Personal Health Knowledge Graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As proof of concept, we have demonstrated the versatility of our digital twin by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.
- 15 March 2024
- Published by MDPI AG in Preprints.org
Open AccessPersonalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach
Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and Personal Health Knowledge Graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As proof of concept, we have demonstrated the versatility of our digital twin by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.
- Open Access
Delighting Palates with AI: Reinforcement Learning’s Triumph in Crafting Personalized Meal Plans with High User Acceptance
Eating, central to human existence, is influenced by a myriad of factors, including nutrition, health, personal taste, cultural background, and flavor preferences. The challenge of devising personalized meal plans that effectively encompass these dimensions is formidable. A crucial shortfall in many existing meal-planning systems is poor user adherence, often stemming from a disconnect between the plan and the user’s lifestyle, preferences, or unseen eating patterns. Our study introduces a pioneering algorithm, CFRL, which melds reinforcement learning (RL) with collaborative filtering (CF) in a unique synergy. This algorithm not only addresses nutritional and health considerations but also dynamically adapts to and uncovers latent user eating habits, thereby significantly enhancing user acceptance and adherence. CFRL utilizes Markov decision processes (MDPs) for interactive meal recommendations and incorporates a CF-based MDP framework to align with broader user preferences, translated into a shared latent vector space. Central to CFRL is its innovative reward-shaping mechanism, rooted in multi-criteria decision-making that includes user ratings, preferences, and nutritional data. This results in versatile, user-specific meal plans. Our comparative analysis with four baseline methods showcases CFRL’s superior performance in key metrics like user satisfaction and nutritional adequacy. This research underscores the effectiveness of combining RL and CF in personalized meal planning, marking a substantial advancement over traditional approaches.
Open AccessDelighting Palates with AI: Reinforcement Learning’s Triumph in Crafting Personalized Meal Plans with High User Acceptance
Eating, central to human existence, is influenced by a myriad of factors, including nutrition, health, personal taste, cultural background, and flavor preferences. The challenge of devising personalized meal plans that effectively encompass these dimensions is formidable. A crucial shortfall in many existing meal-planning systems is poor user adherence, often stemming from a disconnect between the plan and the user’s lifestyle, preferences, or unseen eating patterns. Our study introduces a pioneering algorithm, CFRL, which melds reinforcement learning (RL) with collaborative filtering (CF) in a unique synergy. This algorithm not only addresses nutritional and health considerations but also dynamically adapts to and uncovers latent user eating habits, thereby significantly enhancing user acceptance and adherence. CFRL utilizes Markov decision processes (MDPs) for interactive meal recommendations and incorporates a CF-based MDP framework to align with broader user preferences, translated into a shared latent vector space. Central to CFRL is its innovative reward-shaping mechanism, rooted in multi-criteria decision-making that includes user ratings, preferences, and nutritional data. This results in versatile, user-specific meal plans. Our comparative analysis with four baseline methods showcases CFRL’s superior performance in key metrics like user satisfaction and nutritional adequacy. This research underscores the effectiveness of combining RL and CF in personalized meal planning, marking a substantial advancement over traditional approaches.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 342-347
Optimizing Blood Glucose Control through Reward Shaping in Reinforcement Learning
Achieving optimal blood glucose control is a complex challenge for individuals with diabetes, necessitating a delicate balance among insulin dosage, food consumption, physical activity, and stress management. This paper introduces an innovative approach utilizing reinforcement learning (RL) to develop personalized and effective strategies for blood glucose regulation. Specifically, we employ the state-of-the-art soft actorcritic (SAC) RL algorithm, which concurrently maximizes anticipated rewards and policy entropy. We devise an entropydriven reward function to incentivize diverse action exploration while ensuring a secure and consistent blood glucose profile. This reward function considers both the policy's entropy and the deviation of the blood glucose level from the target range, thus optimizing blood glucose control and minimizing the risk of complications. Our methodology is applied, trained, and assessed using a sophisticated blood glucose dynamics simulator based on the UVA/Padova model. The results demonstrate that our proposed method, SAC with entropy-based reward shaping (SAC+RS), outperforms a comparative approach, SAC with Magni's risk-based reward function (SAC+MRS), in terms of risk scores, glucose levels, insulin levels, and reward values.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 342-347
Optimizing Blood Glucose Control through Reward Shaping in Reinforcement Learning
Achieving optimal blood glucose control is a complex challenge for individuals with diabetes, necessitating a delicate balance among insulin dosage, food consumption, physical activity, and stress management. This paper introduces an innovative approach utilizing reinforcement learning (RL) to develop personalized and effective strategies for blood glucose regulation. Specifically, we employ the state-of-the-art soft actorcritic (SAC) RL algorithm, which concurrently maximizes anticipated rewards and policy entropy. We devise an entropydriven reward function to incentivize diverse action exploration while ensuring a secure and consistent blood glucose profile. This reward function considers both the policy's entropy and the deviation of the blood glucose level from the target range, thus optimizing blood glucose control and minimizing the risk of complications. Our methodology is applied, trained, and assessed using a sophisticated blood glucose dynamics simulator based on the UVA/Padova model. The results demonstrate that our proposed method, SAC with entropy-based reward shaping (SAC+RS), outperforms a comparative approach, SAC with Magni's risk-based reward function (SAC+MRS), in terms of risk scores, glucose levels, insulin levels, and reward values.
- Open Access
- 27 May 2021
- Published by IOS Press
- Vol. 281, 654-658
The Iranian Integrated Care Electronic Health Record
E-health plays a crucial role in E-government by proposing healthcare services based on information technology. However, the way to administer these services by using E-health solutions is one of the challenging issues. One of these significant challenges is how one integrates heterogeneous healthcare information of the different point of care systems. This paper introduces the Iranian integrated care electronic health record using the information gathered from several point-of-care systems in healthcare enterprises in Iran. This service-oriented architecture has a remarkable characteristic – its accessibility to medical knowledge and medical concepts through archetypes and ontology, respectively. The Ministry of Health and Medical Education of the Islamic Republic of Iran has designed and implemented this national architecture.
- 27 May 2021
- Published by IOS Press
- Vol. 281, 654-658
Open AccessThe Iranian Integrated Care Electronic Health Record
E-health plays a crucial role in E-government by proposing healthcare services based on information technology. However, the way to administer these services by using E-health solutions is one of the challenging issues. One of these significant challenges is how one integrates heterogeneous healthcare information of the different point of care systems. This paper introduces the Iranian integrated care electronic health record using the information gathered from several point-of-care systems in healthcare enterprises in Iran. This service-oriented architecture has a remarkable characteristic – its accessibility to medical knowledge and medical concepts through archetypes and ontology, respectively. The Ministry of Health and Medical Education of the Islamic Republic of Iran has designed and implemented this national architecture.