The 2nd Digital Diabetes Management Conference Successfully Held: Focusing on the New Paradigm of “Digital Glucose Control and Integrated Innovation”

With the global prevalence of diabetes on the rise, achieving precise and efficient glycemic management has become a critical public health challenge. The rapid development of digital medical technologies—including continuous glucose monitoring (CGM), intelligent algorithms, and remote follow-up platforms—has introduced new solutions for comprehensive diabetes care.

On June 7, 2025, the 2nd Digital Diabetes Management Conference, themed “Digital Glucose Control and Integrated Innovation,” was successfully held in Chengdu, Sichuan Province. The event was co-hosted by the Institute of Active Health Strategy and Development of Shanghai Jiao Tong University and the Beijing Association for Chronic Disease Prevention and Health Education, with academic guidance from the Lifestyle Medicine Branch of the China Health Management Association and the Chinese Journal of Diabetes.

Empowering Diabetes Care with Digital Health: A New Vision for Smart Management

Professor Jia Weiping

Professor Jia Weiping from Shanghai Sixth People’s Hospital emphasized the transformation of clinical services from hospital-centered care to comprehensive lifecycle health management, encompassing prevention, screening, diagnosis, treatment, and rehabilitation. She stressed that only through “people-centered integrated care” can we enhance the quality and efficiency of diabetes management. Digital medicine and artificial intelligence are critical enablers of this transition^[1].

AI-Driven Precision: Building an Intelligent Diabetes Prevention and Treatment System

Professor Yang Zhenglin

Professor Yang Zhenglin from Sichuan Provincial People’s Hospital highlighted key challenges in diabetes care in China, where adult prevalence has reached 11.9%. These include insufficient early screening and limited personalized treatment.

AI technologies are widely used in diabetes applications—for instance: GWAS + AI models can predict gestational diabetes mellitus (GDM) before 20 weeks of pregnancy; Machine learning combined with single-cell multi-omics can reveal genetic regulatory mechanisms of type 2 diabetes (T2D); CGM combined with AI can identify metabolic subtypes^[4–6].

The team of Professor Jia Weiping developed DeepDR Plus, a deep learning system predicting 5-year progression of diabetic retinopathy (DR) based on fundus images^[7]. Professor Yang’s team constructed 657 machine learning models using large-scale patient data, including 14 focused on diabetes, some of which have reached advanced clinical application levels. AI is poised to further accelerate precision medicine and full-course diabetes care.

A Global Outlook: Breakthroughs in Digital Diabetes Management

Professor Marc Breton

Professor Marc Breton from the University of Virginia shared international insights into digital diabetes care, focusing on medical digital twin systems and AI-powered fully closed-loop artificial pancreas systems (FCL AID). These technologies enable real-time physiological updates and automated insulin dose adjustments, helping clinicians formulate personalized treatment strategies. The integration of digital twin systems with AI signifies a leap toward automated, individualized diabetes care.

Professor Juliana CN CHAN (陳重娥)

Professor Juliana Chen from the Chinese University of Hong Kong discussed how CGM influences emotions and behavior. To overcome the “knowledge-action gap” in diabetes management, she advocated combining CGM with full-course management to enable data-driven personalized care, emotional support, and self-management—ultimately improving glycemic control and reducing complications.

Expanding to Primary Care: AI-Enabling Diabetes Prevention and Control

Professor Zhou Zhiguang

Professor Zhou Zhiguang from the Second Xiangya Hospital of Central South University emphasized that China faces a “triple challenge” in diabetes control: high prevalence but low awareness, treatment, and control rates. The solution lies in shifting the focus to prevention and primary care.

The National Diabetes Standardized Prevention and Control Center (DPCC) initiative integrates 5G, AI, and IoT to support patient-centered, tiered care and collaborative management. Pilots in Hunan Province (Pingjiang, Yuetang, Yongzhou) have been scaled province-wide, and the model has expanded to Shenzhen, Shanxi, and Henan.

Dr. Zheng Jiyun

Dr. Zheng Jiyun, Vice GM and Board Secretary of Sinocare, noted that despite being based on massive datasets, large AI models in healthcare face challenges including outdated knowledge and passive data collection. To address this, she proposed a model combining dynamic knowledge updating, integrated data, and the framework of “large model + memory + planning + tools” to build intelligent agents for diabetes.

Sinocare Intelligent Diabetes Management System

The Sinocare Intelligent Diabetes Management System integrates BGM, CGM, CSII, PEP, and chronic disease management functions, using AI to assist doctors in accurate data analysis, treatment optimization, and efficient patient management.

Multidisciplinary Collaboration: CGM + AI Reshaping Glucose Management

In a panel led by Professor Guo Lixin of Beijing Hospital, experts including Professors Yang Xiaokang, Fu Junfen, Li Yingchuan, and Li Guisen discussed key clinical needs in glucose management:

lPediatric diabetes: Hormonal fluctuations during puberty cause unpredictable insulin demands, while painful finger pricks lower adherence.

lCritical care: 30–50% of ICU patients risk life-threatening glucose excursions due to intermittent testing.

lChronic kidney disease: HbA1c becomes less reliable due to impaired renal function, increasing the risk of undetected hypoglycemia.

CGM offers a breakthrough by providing continuous glucose trend data, real-time alerts, and Ambulatory Glucose Profiles (AGP), supporting personalized treatment planning. These advances mark a shift from simple glucose control to quality-controlled, full-course diabetes management.

Hospital-Wide Collaboration: Building an Intelligent Glucose Management Ecosystem

Studies show that 38% of hospitalized patients in China have diabetes, with over 80% of them treated outside endocrinology departments. Nearly one-third have poor glycemic control, highlighting gaps in clinical knowledge and response times [4].

Professor Cai Mengyin

Professor Cai Mengyin from the Third Affiliated Hospital of Sun Yat-sen University explained the 2025 Expert Consensus on Smart Glucose Management in Hospital Virtual Wards. This model, led by endocrinology departments, allows for centralized monitoring, automated alerts, and closed-loop management—especially for high-risk patients such as those undergoing surgery or pregnancy ^[4].

Professor Liu Shiwei

Professor Liu Shiwei from Bethune Hospital, Shanxi, shared their system integrating BGM, CGM, CSII, and PEP. The combination of smart hardware (meters and patch pumps) and software ensures data synchronization, broad applicability, and safety, enabling precise insulin adjustments and reduced complications.

Professor Lu Jingyi

Professor Lu Jingyi of Shanghai Sixth People’s Hospital noted that CGM, recommended by ADA in 2024^[5], is crucial for outpatient management and has shown added value during COVID-19 by reducing staff workload and infection risk^[6].

Professor Zheng Xueying

Professor Zheng Xueying introduced the 3C Therapy—a full-disposable combination of insulin pump, CGM, and diabetes management software. Compared to traditional pumps, this approach improves accuracy, reduces time to glucose targets, and is cost-effective for hospital-wide deployment^{[7–10, 13–14]}.

Professor Shen Jie

Professor Shen Jie emphasized that standardized, dynamic inpatient glucose management can improve control rates and reduce complications while enabling smooth transitions from acute inpatient care to stable outpatient follow-up, aligning with China’s tiered healthcare policy.

Endocrine Challenges and Innovations

Professor Liao Yu

Professor Liao Yu from Sinocare's Diabetes Remission Center noted that remission efforts are hindered by limited awareness, mindset shifts, and multidisciplinary execution. To address this, the center implemented the MIT method (Multidisciplinary, Individualized, Traceable) to manage multiple indicators and achieve collaborative reversal outcomes.

Professor Zhang Dongming

Professor Zhang Dongming of the Second Affiliated Hospital of Zhengzhou University presented a case of Insulin Autoimmune Syndrome (IAS)—characterized by blood glucose fluctuations and coexisting autoimmune diseases. Early identification and standardized intervention are vital \[15].

Professor Gao Ling

Professor Gao Ling from Wuhan University introduced DeepSeek, a multimodal AI tool that uses RAG technology to build a local knowledge base for high-speed, customized medical reference searches. It supports medical training with 91.7% accuracy on Chinese diabetes tests, though improvements are needed in summarization and stability.

Debate: Can CGM Replace HbA1c as the New Standard?

In a spirited debate, Professors Li Jun and Zhao Yongcai argued that CGM could replace HbA1c as the new standard, while Professors Yang Yang and Zhao Yu opposed the motion.

While HbA1c remains the “gold standard” for assessing long-term glycemic control and complications, CGM offers real-time data and better responsiveness, with strong correlation to HbA1c—showing great promise for future standardization.

Outstanding Cases in Digital Diabetes Management

Among numerous clinical cases submitted, ten were recognized as Outstanding Digital Diabetes Management Cases after expert review. These cases showcased innovations in CGM-based intervention models and the deep integration of digital tools and clinical expertise.

Closing

The 2nd Digital Diabetes Management Conference concluded successfully. With the continued advancement of CGM, AI, and digital twin technologies, along with the development of grassroots medical networks, the innovative paradigm of “digital glucose control” is poised to accelerate, ushering in a new era of precision, intelligence, and integration in diabetes prevention and treatment.

*This article is intended for healthcare professionals only.

References:

[1] https://dtxalliance.org/wp-content/uploads/2021/01/DTA_DTx-Definition-and-Core-Principles.pdf

[2] 第11版国际糖尿病联盟（IDF）糖尿病地图，https://diabetesatlas.org/

[3] 中华医学会糖尿病学分会.中国糖尿病防治指南(2024版)[J].中华糖尿病杂志, 2025, 17(01):16-139.

[4] Gu Y, et al. Genetic architecture and risk prediction of gestational diabetes mellitus in Chinese pregnancies. Nat Commun. 2025 May 5;16(1):4178.

[5] Wang G, et al. Integrating genetics with single-cell multiomic measurements across disease states identifies mechanisms of beta cell dysfunction in type 2 diabetes. Nat Genet. 2023 Jun;55(6):984-994.

[6] Metwally AA, et al. Prediction of metabolic subphenotypes of type 2 diabetes via continuous glucose monitoring and machine learning. Nat Biomed Eng. 2024 Dec 23.

[7] Dai L, et al. A deep learning system for predicting time to progression of diabetic retinopathy. Nat Med. 2024 Feb;30(2):584-594.

[8] Khunti K, et al. Glycaemic control is still central in the hierarchy of priorities in type 2 diabetes management. Diabetologia. 2025 Jan;68(1):17-28.

[9] Bitew ZW, et al. Prevalence of Glycemic Control and Factors Associated With Poor Glycemic Control: A Systematic Review and Meta-analysis. Inquiry. 2023 Jan-Dec;60:469580231155716.

[10] 《医院内虚拟病区智慧化血糖综合管理专家共识》制订专家组. 医院内虚拟病区智慧化血糖综合管理专家共识（2025版）[J]. 中华糖尿病杂志,2025,17(3):299-310.

[11] American Diabetes Association Professional Practice Committee; 7. Diabetes Technology: Standards of Care in Diabetes—2024. Diabetes Care 1 January 2024; 47 (Supplement_1): S126–S144.

[12] Gómez AM, et al. Continuous Glucose Monitoring Versus Capillary Point-of-Care Testing for Inpatient Glycemic Control in Type 2 Diabetes Patients Hospitalized in the General Ward and Treated With a Basal Bolus Insulin Regimen. J Diabetes Sci Technol. 2015 Aug 31;10(2):325-9.

[13] 中华医学会内分泌学分会. 中国胰岛素泵治疗指南(2021年版). 中华内分泌代谢杂志，2021，37(08):679-701.

[14] Natale P, et al. Patient experiences of continuous glucose monitoring and sensor-augmented insulin pump therapy for diabetes: A systematic review of qualitative studies. J Diabetes. 2023 Dec;15(12):1048-1069.

[15] Bergenstal RM, et al. Effectiveness of sensor-augmented insulin-pump therapy in type 1 diabetes. N Engl J Med. 2010 Jul 22;363(4):311-20.

[16] Gu W, et al. Multicentre randomized controlled trial with sensor-augmented pump vs multiple daily injections in hospitalized patients with type 2 diabetes in China: Time to reach target glucose. Diabetes Metab. 2017 Sep;43(4):359-363.

[17] American Diabetes Association Professional Practice Committee; 7. Diabetes Technology: Standards of Care in Diabetes—2025. Diabetes Care 1 January 2025; 48 (Supplement_1): S146–S166.

[18] Grunberger G, et al. American Association of Clinical Endocrinology Clinical Practice Guideline: The Use of Advanced Technology in the Management of Persons With Diabetes Mellitus. Endocr Pract. 2021 Jun;27(6):505-537.

[19] Wang H, et al. Predictors of Long-Term Glycemic Remission After 2-Week Intensive Insulin Treatment in Newly Diagnosed Type 2 Diabetes. J Clin Endocrinol Metab. 2019 Jun 1;104(6):2153-2162.

[20] Liu L, et al. Intense simplified strategy for newly diagnosed type 2 diabetes in patients with severe hyperglycaemia: multicentre, open label, randomised trial. BMJ. 2024 Oct 15;387:e080122.

[21]  《胰岛素自身免疫综合征诊治专家共识（2024版）》编写委员会. 胰岛素自身免疫综合征诊治专家共识（2024版）[J]. 中华糖尿病杂志,2024,16(12):1346-1360.