LLM-CoManage: Large Language Model-Enabled Co-Management of Hypertension, Diabetes, and Dyslipidemia

NCT07350486 | Not Yet Recruiting DMC

• 1 other identifier: CMU-HyperMindRCT-2025
• Study Type: interventional
• Target: 6,800
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to evaluate the effectiveness of a large language model (LLM)-supported, community-based integrated management model in improving cardiometabolic multimorbidity control among adults with hypertension and coexisting diabetes or dyslipidemia. Adopting an interventional study design, eligible patients will be recruited to compare the disease control indicators between LLM-assisted management and conventional management, so as to verify the effectiveness and safety of the former.

Conditions

Hypertension; Diabetes; Dyslipidemia

Keywords

Large Language Model; Co-Management

Outcome Measures

Primary Outcomes (1)

• The between-group difference in the proportion of participants achieving simultaneous control of hypertension and either diabetes or dyslipidemia.

  Simultaneous control is defined as BP \< 130/80 mmHg and at least one of the following: HbA1c \< 7.0% or LDL-C \< 2.6 mmol/L (100 mg/dL), with a stricter threshold of \< 1.8 mmol/L (70 mg/dL) for participants with cardiovascular disease(CVD).

  6 months after baseline

Secondary Outcomes (17)

• Net changes in estimated 10-year risk for atherosclerotic CVD.

  6 months after baseline

• Proportion of participants achieving control of individual risk factors: BP < 130/80 mmHg (or < 140/90 mmHg); HbA1c < 7.0%; and LDL-C < 2.6 mmol/L (100 mg/dL) or < 1.8 mmol/L (70 mg/dL) for those with CVD.

  6 months after baseline

• Mean systolic blood pressure changes.

  6 months after baseline

• Mean diastolic blood pressure changes.

  6 months after baseline.

• Mean HbA1c changes.

  6 months after baseline.

Study Arms (2)

LLM-Enabled Intervention Group

ACTIVE COMPARATOR

LLM-enabled community physicians delivered integrated, guideline-based management

Other: LLM-Enabled Co-management

Usual Care Control Group

NO INTERVENTION

Community physicians provided routine care according to local primary health service standards

Interventions

LLM-Enabled Co-management OTHER

The intervention is a LLM-enabled, community-based integrated management strategy for cardiometabolic multimorbidity. The LLM system functions as the central intelligence layer, integrating multi-condition clinical information, delivering real-time decision support, coordinating care workflows, and facilitating continuous patient engagement. Within this LLM-enabled framework, community physicians-after standardized training-serve as the core executors of care, delivering guideline-based pharmacologic treatment, lifestyle counseling, and structured monitoring of coexisting cardiometabolic conditions. Policy-aligned performance incentives are used to support physician engagement and implementation fidelity, without altering medication access or underlying clinical protocols. The LLM-enabled intervention is implemented through the HyperMind system, an integrated platform that simultaneously supports clinicians, patients, and health-system oversight.

LLM-Enabled Intervention Group

Eligibility Criteria

• Age: 40 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Participating communities must meet all of the following criteria:
• Have a designated community physician responsible for primary care who is capable of using a smartphone with stable internet access for clinical communication and LLM-assisted management;
• No plan for administrative merger or restructuring within the next three years;
• Located at least 2 kilometers away from adjacent participating communities (to minimize contamination between clusters).
• Eligible participants must fulfill all of the following conditions:
• Aged 40 years or older;
• Uncontrolled hypertension, defined as systolic blood pressure (SBP) ≥140 mmHg or diastolic blood pressure (DBP) ≥ 90 mmHg;
• Coexisting diabetes (HbA1c ≥ 7.0%) or coexisting dyslipidemia (LDL-C ≥ 3.4 mmol/L\[130 mg/dL\]);
• Able to use a smartphone independently or with assistance from family members;
• Has resided in the participating community for at least 6 months;
• Has no plan to relocate in the next 3 years;
• Enrolled in basic medical insurance for urban and rural residents, employee medical insurance, or the New Rural Cooperative Medical Scheme;
• Not currently pregnant or planning pregnancy during the study period;
• Free from malignant tumors and deemed to have a life expectancy of at least 3 years, as judged by study physicians;
• Willing and able to provide written informed consent.

Sponsors & Collaborators

• First Hospital of China Medical University: lead
• Beijing Chao Yang Hospital: collaborator
• Zhejiang University: collaborator
• Shandong Provincial Hospital: collaborator
• Cangzhou Central Hospital: collaborator

Study Sites (1)

The First Hospital of China Medical University

Shenyang, Liaoning, 110001, China

Location

MeSH Terms

Conditions

Hypertension; Diabetes Mellitus; Dyslipidemias

Condition Hierarchy (Ancestors)

Vascular Diseases; Cardiovascular Diseases; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Endocrine System Diseases; Lipid Metabolism Disorders

Study Officials

• Yingxian Sun, MD, PhD

  First Hospital of China Medical University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Xiaofan Guo, PhD

CONTACT

+86 13842078178; guoxiaofan1986@hotmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Outcome Assessment Committee members will be blinded to outcome assignment.
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Chief of Department of Cardiology in First Hospital of China Medical University

Study Record Dates

• First Submitted: December 25, 2025
• First Posted: January 20, 2026
• Study Start: June 15, 2026
• Primary Completion (Estimated): June 30, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: May 13, 2026

Record last verified: 2026-05

Locations

CN (1)