Large Language Model-Generated Messages to Improve Guideline-Directed Medical Therapy in Heart Failure
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 入组人数
- 500
- 试验地点
- 1
- 主要终点
- Any GDMT optimization within 30 days of index visit
研究概览
简要总结
This study is an investigator-initiated, cluster-randomized implementation trial evaluating a large language model (LLM)-based clinical decision support (CDS) tool designed to improve guideline-directed medical therapy (GDMT) for adult patients with heart failure seen in outpatient cardiology clinics at Mass General Brigham.
For eligible heart failure encounters, the CDS tool reviews existing electronic health record (EHR) data, including diagnoses, medications, vital signs, laboratory results, and recent notes, and generates brief, clinician-facing messages suggesting opportunities to initiate or optimize GDMT and highlighting relevant safety considerations. Messages are delivered to cardiology providers via Epic InBasket and/or institutional email prior to scheduled visits. The tool is advisory only and cannot place orders or change medications automatically; all treatment decisions remain at the discretion of the treating clinician and patient.
Cardiology providers are assigned at the provider/clinic level to early implementation of the CDS tool versus usual care (no messages) during the initial phase. The primary outcome is GDMT optimization within 30 days of an index visit. Secondary outcomes include feasibility of CDS generation and delivery and a 30-day safety composite (e.g., heart failure hospitalization, acute kidney injury, hyperkalemia, hypotension or bradyarrhythmia plausibly related to GDMT).
详细描述
Overview and Rationale Guideline-directed medical therapy (GDMT) for heart failure reduces hospitalizations and mortality, yet substantial underuse and suboptimal titration persist in routine practice, even in specialty cardiology clinics. Barriers include limited visit time, complex comorbidities, fragmented information across notes and structured data, and uncertainty about contraindications or prior intolerance. Electronic clinical decision support (CDS) tools that synthesize key patient information and highlight GDMT opportunities at the point of care may help close these gaps.
Large language models (LLMs) can read both structured EHR data (e.g., diagnoses, medications, vital signs, laboratory results) and unstructured narrative notes to generate nuanced, patient-specific recommendations. We developed an LLM-based CDS tool that reviews an adult heart failure patient's EHR and produces a brief, free-text message to the treating cardiology provider summarizing heart failure status, suggesting potential GDMT changes consistent with contemporary guidelines, and flagging relevant safety issues (e.g., low blood pressure, bradycardia, renal dysfunction, hyperkalemia, prior documented intolerance). In retrospective testing, the tool's recommendations were generally concordant with expert clinician judgment.
Study Design
This is an interventional, cluster-randomized, provider-level trial conducted in adult outpatient cardiology clinics at Mass General Brigham. The intervention is a software-only, investigational clinical decision support device ("LLM-GDMT Clinical Decision Support Tool"). Eligible cardiology attendings and advanced practice providers are assigned at the provider/clinic level to one of two parallel arms during the initial phase:
Early Implementation - LLM-GDMT CDS: Providers in this arm receive LLM-generated, clinician-facing messages for eligible heart failure encounters. For scheduled visits that meet predefined inclusion criteria, the tool reviews existing EHR data and generates a brief advisory message that is delivered via Epic InBasket and/or institutional email within the week prior to the visit.
研究设计
- 研究类型
- Interventional
- 分配方式
- Randomized
- 干预模型
- Parallel
- 主要目的
- Health Services Research
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 85 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Age ≥18 years
- •Scheduled outpatient visit with a participating cardiology provider in an MGB outpatient cardiology clinic
- •At least one prior cardiology clinic visit in the MGB system within the past 2 years
- •Diagnosis of heart failure by ICD code within the past 2 years
- •Heart failure diagnosis supported by at least one of the following:
- •Current or recent use of a loop diuretic
- •Left ventricular ejection fraction ≤40% on the most recent echocardiogram
- •Explicit documentation of heart failure diagnosis or heart failure signs/symptoms in a prior cardiology note
排除标准
- •Systolic blood pressure <90 mmHg on the most recent recorded measurement
- •Heart rate <50 beats per minute on the most recent recorded measurement
- •eGFR <20 mL/min/1.73 m² on the most recent laboratory assessment
- •Known cardiac amyloidosis or hypertrophic cardiomyopathy
- •History of heart transplant or presence of a left ventricular assist device
- •Severe aortic stenosis, severe aortic insufficiency, or severe mitral stenosis on the most recent echocardiogram
- •Encounter occurs in an adult congenital heart disease clinic
研究组 & 干预措施
Usual Care (Delayed Implementation)
Providers in this arm continue usual care and do not receive LLM-GDMT CDS messages during the initial evaluation phase. Eligible outpatient heart failure encounters are managed according to routine clinical practice without additional CDS messages. EHR data from these encounters are used to compute GDMT utilization and safety outcomes for comparison with the early-implementation arm. After the initial evaluation phase is complete, the LLM-GDMT CDS tool may be expanded to providers in this arm as part of routine care.
Early Implementation
Providers in this arm receive a large language model-based clinical decision support (LLM-GDMT CDS) intervention. For eligible outpatient heart failure encounters, the CDS tool reviews existing EHR data (diagnoses, medications, vitals, labs, recent notes) and generates a brief, clinician-facing message summarizing HF status, suggesting opportunities to initiate or optimize guideline-directed medical therapy (GDMT), and highlighting safety considerations. Messages are delivered via Epic InBasket and/or institutional email in advance of the visit. The tool is advisory only and cannot place orders or directly change medications; all treatment decisions remain at the discretion of the treating clinician and patient.
干预措施: LLM-GDMT Clinical Decision Support Tool (Device)
结局指标
主要结局
Any GDMT optimization within 30 days of index visit
时间窗: 30 days
Among eligible HF encounters, the proportion with initiation of at least one new GDMT class not previously prescribed and/or uptitration of at least one existing GDMT medication during or within 30 days after the index visit, comparing early-implementation vs usual care arms.
次要结局
- Operational Feasibility(30 days)
- Short-Term Safety Composite (30 days)(30 days)
研究者
Jonathan Cunningham MD MPH
Assistant Professor of Medicine
Brigham and Women's Hospital