Multimodal AI-Driven Out-of-Hospital Management for Hypertension and Cardiometabolic Risk (no acronym)
Effects of Multimodal Artificial Intelligence-Driven Out-of-Hospital Management on Patients With Hypertension and Cardiometabolic Risk Factors
High blood pressure often occurs together with abnormal blood glucose, abnormal blood lipids, or abdominal obesity. Managing these conditions outside the hospital can be difficult. This study will test whether a digital health program that combines artificial intelligence (AI) with review and support by doctors and nurses improves health outcomes compared with standard out-of-hospital guidance.
The study will enroll 150 adults aged 18 to 70 years who have hypertension and at least one additional cardiometabolic risk factor that is not at target. Participants will be randomly assigned in a 1:1 ratio to either the hybrid AI-assisted management group or the standard-guidance group. The intervention group will use a patient mini-program and connected devices to monitor blood pressure, glucose, and lifestyle information. The AI system will propose personalized medication, diet, exercise, and monitoring plans, which the healthcare team will review and confirm before delivery. The control group will receive routine printed health education and usual clinical follow-up.
All participants will be followed for 6 months. The main outcome is the proportion of participants achieving blood pressure control together with control of at least one glycemic or lipid indicator. Other assessments include treatment adherence, cardiovascular events, hospitalizations, medical costs, quality of life, and system usability.
調査の概要
状態
詳細な説明
This single-center, prospective, randomized, open-label, parallel-group controlled trial evaluates a multimodal AI-driven, human-AI collaborative out-of-hospital health management system for adults with hypertension and cardiometabolic risk factors. A central randomization system will allocate 150 participants in a 1:1 ratio to hybrid AI-assisted management or standard out-of-hospital guidance. Follow-up lasts 6 months.
The intervention integrates clinical data, patient-generated data, and device data from Huawei wearable bands/watches, blood pressure monitors, and glucose meters. An AI agent informed by the COM-B and Fogg behavior models generates personalized recommendations, monitoring tasks, reminders, adherence support, and risk alerts. Healthcare professionals review, modify, and approve key recommendations, respond to medical questions, and manage alerts. The control group receives a printed health education booklet, instructions on medication use and follow-up, and usual clinical care without the study digital system or additional proactive follow-up.
Study visits occur at screening, baseline, Month 3, and Month 6, with additional telephone follow-up. Blood pressure is measured using a HUAWEI WATCH D2. Laboratory assessments include glucose, lipids, insulin, HbA1c, and free fatty acids after an 8-hour fast. The primary endpoint is a participant-level composite of blood pressure target attainment and target attainment for at least one glycemic or lipid indicator at Month 6. Secondary and exploratory assessments cover multidimensional adherence, major adverse cardiovascular events, all-cause hospitalization, medical costs related to hypertension, hyperlipidemia, hyperglycemia, and hyperuricemia, SF-36 quality of life, and System Usability Scale ratings.
The planned analysis uses intention-to-treat principles, with chi-square tests and logistic regression for the primary endpoint, analysis of covariance for continuous changes, Kaplan-Meier methods for cardiovascular events, and multiple imputation for missing primary and secondary outcome data.
研究の種類
入学 (推定)
段階
- 適用できない
連絡先と場所
研究連絡先
- 名前：Yifan Wu, master
- 電話番号：01088398069
- メール：wuyifan1127@126.com
参加基準
適格基準
就学可能な年齢
健康ボランティアの受け入れ
受講資格のある性別
説明
Inclusion Criteria:
- Aged 18-70 years.
- Confirmed hypertension plus at least one of dyslipidemia, hyperglycemia, or abdominal obesity, with at least one condition not at target. Hypertension: BP ≥130/85 mmHg and/or diagnosed hypertension under treatment. Hyperglycemia: fasting glucose ≥6.1 mmol/L or 2-hour post-load glucose ≥7.8 mmol/L and/or diagnosed diabetes under treatment. Abdominal obesity: waist circumference ≥90 cm in men or ≥85 cm in women. Dyslipidemia: fasting triglycerides ≥1.7 mmol/L, LDL-C ≥4.1 mmol/L in the general population, or failure to meet the ASCVD risk-stratified LDL-C target (<2.6 mmol/L for general low-risk adults; <1.8 mmol/L for specified higher-risk groups; <1.4 mmol/L for specified very-high-risk ASCVD groups).
- Able to use a smartphone and smart wearable devices.
- Relatively stable work/life circumstances and residence for the next 6 months.
- Voluntary participation and signed informed consent.
Exclusion Criteria:
- Secondary hypertension, acute hypertension, subacute hypertension, or hypertensive encephalopathy.
- Severe primary hypertension (SBP ≥180 mmHg and/or DBP ≥110 mmHg) or poorly controlled primary hypertension.
- Acute myocardial infarction, unstable angina, or coronary revascularization (PCI or CABG) within 6 months.
- Cerebral infarction or cerebral hemorrhage within 6 months.
- Severe heart failure (NYHA class III-IV).
- Uncontrolled severe arrhythmia, such as symptomatic ventricular tachycardia or high-grade atrioventricular block.
- Chronic kidney disease.
- Severe psychiatric illness preventing cooperation.
- Life expectancy <12 months.
- ALT or AST ≥3 × ULN; for patients receiving lipid-lowering therapy, ALT or AST ≥2 × ULN that does not normalize after drug discontinuation.
- Other severe conditions preventing digital management, including severe visual/hearing impairment or cognitive dysfunction.
- Any other condition considered by the investigator to make participation unsuitable.
- Participation in another clinical study within 3 months.
- Refusal to sign informed consent.
研究計画
研究はどのように設計されていますか？
デザインの詳細
- 主な目的：処理
- 割り当て：ランダム化
- 介入モデル：並列代入
- マスキング：なし（オープンラベル）
武器と介入
参加者グループ / アーム |
介入・治療 |
|---|---|
|
実験的：Hybrid AI-Assisted Out-of-Hospital Management
Participants use a patient mini-program with automatically synchronized wearable-device, blood pressure, and glucose data plus manual lifestyle entries. An AI agent generates personalized medication reminders, dietary advice, exercise plans, monitoring tasks, education, and risk alerts. Healthcare professionals review, modify, and approve recommendations and manage medical questions and alerts for 6 months. |
A 6-month personalized digital health intervention integrating multimodal clinical, patient-generated, and device data. AI informed by COM-B and Fogg behavior models provides lifestyle and medication-adherence support, monitoring tasks, reminders, and risk alerts; healthcare professionals review and confirm key recommendations and provide clinical oversight. |
|
アクティブコンパレータ：Control
Participants receive routine discharge health education and a printed booklet, with instructions to take medications as prescribed and attend regular follow-up visits. They do not receive the study digital system or additional proactive follow-up beyond usual clinical care. Follow-up lasts 6 months. |
Routine health education at discharge, including a printed booklet and advice on medication adherence and regular follow-up, with usual clinical follow-up for 6 months and no study digital system or additional proactive follow-up. |
この研究は何を測定していますか？
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Proportion of Participants Achieving Blood Pressure Control and Control of at Least One Glycemic or Lipid Indicator
時間枠：At 6 months after randomization
|
Proportion of participants achieving both: (1) blood pressure <140/90 mmHg for general hypertension, or <130/80 mmHg for participants with metabolic syndrome; and (2) at least one glycemic or lipid target. Glycemic target: fasting plasma glucose <7.0 mmol/L and HbA1c <7.0%. LDL-C target: <2.6 mmol/L for intermediate ASCVD risk or <1.8 mmol/L for high/very high ASCVD risk. |
At 6 months after randomization
|
|
Composite Treatment and Health-Management Adherence
時間枠：At 6 months after randomization
|
Composite adherence assessed using MMAS-8 (score ≥6 indicates good medication adherence) and system data. Good monitoring adherence: ≥4 valid blood pressure measurements/week. Good home-monitoring adherence: ≥80% of AI-recommended tasks completed/week. Dietary/physical-activity adherence is defined in the protocol using achievement of at least 4 of 5 domains (medication, monitoring, diet, physical activity, follow-up), with >80% of participants meeting this threshold. |
At 6 months after randomization
|
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Incidence of Major Adverse Cardiovascular Events (MACE)
時間枠：From randomization through 6 months
|
Composite of cardiovascular death, nonfatal myocardial infarction, and nonfatal stroke. |
From randomization through 6 months
|
|
Health-Related Quality of Life (SF-36 Score)
時間枠：Baseline and 6 months after randomization
|
Assessed using the 36-Item Short Form Health Survey (SF-36). |
Baseline and 6 months after randomization
|
|
System Satisfaction and Usability (System Usability Scale Score)
時間枠：At 6 months after randomization
|
Patient and healthcare-professional satisfaction and usability assessed using the System Usability Scale (SUS). |
At 6 months after randomization
|
協力者と研究者
研究記録日
主要日程の研究
研究開始 (推定)
一次修了 (推定)
研究の完了 (推定)
試験登録日
最初に提出
QC基準を満たした最初の提出物
最初の投稿 (実際)
学習記録の更新
投稿された最後の更新 (実際)
QC基準を満たした最後の更新が送信されました
最終確認日
詳しくは
この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。