Obesity management based on multimodal artificial intelligence
1
Digital Health China Technologies Co. Ltd,, beijing, China
2
Department of Urology, First Affiliated Hospital, Kunming Medical University, Kunming, Yunnan, China
3
School of Population Medicine and Public Health,Peking Union Medical College, beijing, China
4
School of Biomedical Engineering, Guangdong Medical University, dongguan,guangdong, China
5
National Clinical Research Center for Aging and Medicine, Huashan Hospital, Fudan University, shanghai, China
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
INTRODUCTION:
The escalating prevalence of overweight and obesity in China presents a major public health concern1,2. Conventional obesity management approaches are frequently limited by fragmented assessments, delayed interventions, low patient engagement, and insufficient support in primary care settings3. Emerging advancements in artificial intelligence (AI), particularly multimodal large models, offer transformative potential to overcome these limitations by enabling comprehensive data integration, intelligent reasoning, and personalized intervention strategies4,5.
METHODS:
We developed a multimodal AI framework for obesity management, integrating a Digital Health Connector (DHC) for multimodal data standardization and a medical reasoning engine (DeepSeek) for intelligent decision-making. The framework supports structured data ingestion, algorithm deployment, and a collaborative doctor–patient interaction platform. It facilitates risk stratification, personalized intervention planning, and real-time monitoring throughout the entire care cycle, encompassing early screening, diagnosis, intervention, and follow-up.
RESULTS:
The implemented system enables closed-loop, life-cycle obesity care, incorporating AI-powered components such as voice-assisted pre-consultation, food image analysis, wearable device integration, and clinical decision support tools. A three-tier system—early screening, diagnosis, and intervention—was established alongside standardized toolkits for primary healthcare providers. Pilot deployments demonstrated enhanced diagnostic accuracy, improved patient adherence, and strengthened capabilities for community-level obesity prevention and management.
CONCLUSIONS:
This multimodal AI framework represents a scalable and intelligent approach to obesity management, leveraging multisource data and clinical reasoning to deliver personalized, equitable, and primary care–oriented interventions. It contributes to improved efficiency and equity in obesity care, aligning with the strategic objectives of the Healthy China 2030 initiative.
The escalating prevalence of overweight and obesity in China presents a major public health concern1,2. Conventional obesity management approaches are frequently limited by fragmented assessments, delayed interventions, low patient engagement, and insufficient support in primary care settings3. Emerging advancements in artificial intelligence (AI), particularly multimodal large models, offer transformative potential to overcome these limitations by enabling comprehensive data integration, intelligent reasoning, and personalized intervention strategies4,5.
METHODS:
We developed a multimodal AI framework for obesity management, integrating a Digital Health Connector (DHC) for multimodal data standardization and a medical reasoning engine (DeepSeek) for intelligent decision-making. The framework supports structured data ingestion, algorithm deployment, and a collaborative doctor–patient interaction platform. It facilitates risk stratification, personalized intervention planning, and real-time monitoring throughout the entire care cycle, encompassing early screening, diagnosis, intervention, and follow-up.
RESULTS:
The implemented system enables closed-loop, life-cycle obesity care, incorporating AI-powered components such as voice-assisted pre-consultation, food image analysis, wearable device integration, and clinical decision support tools. A three-tier system—early screening, diagnosis, and intervention—was established alongside standardized toolkits for primary healthcare providers. Pilot deployments demonstrated enhanced diagnostic accuracy, improved patient adherence, and strengthened capabilities for community-level obesity prevention and management.
CONCLUSIONS:
This multimodal AI framework represents a scalable and intelligent approach to obesity management, leveraging multisource data and clinical reasoning to deliver personalized, equitable, and primary care–oriented interventions. It contributes to improved efficiency and equity in obesity care, aligning with the strategic objectives of the Healthy China 2030 initiative.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
