Heart Failure With Preserved Ejection FractionMeG-HFpEFNCT06486649
Application of Multimodal Large Language Model in HFpEF
An observational study of Heart Failure With Preserved Ejection Fraction, run by Peking University Third Hospital at 1 site in China.
Trial summary
This study will validate the effectiveness of a multimodal large language model to screen for heart failure with preserved ejection fraction (HFpEF), comparing it with the traditional clinical standardized assessment process. Read more about this study
- Who is it for?
- Ages 18 to 80 years
- Conditions the study is for
- Heart Failure With Preserved Ejection Fraction
- What is being tested?
- Multimodal Large Language Model Diagnosis and Routine diagnostic and therapeutic procedure
- How many people
- 80 participants
- Where
- 1 siteChina
- Study dates
- 20 Dec 2023to 20 Dec 2024
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 80 years
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: Subjects will be recruited from patients routinely hospitalized in the cardiology department who also met the needs of this trial and are not recruited separately.
Who may be able to join
- Age 18-80 years, male or female;
- Cardiology inpatients with suspected heart failure with preserved ejection fraction (cardiac ultrasound suggestive of LVEF ≥50% with at least 1 of the following: 1, left ventricular hypertrophy and/or left atrial enlargement; and 2, abnormal diastolic cardiac function);
- Current or previous at least one symptom of heart failure, including dyspnea (including exertional dyspnea, nocturnal paroxysmal dyspnea, and telangiectasia), malaise, nausea, and bilateral lower extremity edema;
- Voluntary participation and signed informed consent.
Who cannot join
- Acute heart failure or acute worsening of chronic heart failure;
- Severe coronary stenosis (≥75% stenosis) without revascularization;
- Patients who are unable to perform exercise stress echocardiography or have contraindications to the test;
- are participating in other clinical trials;
- Those with severe organic pathologies of the liver, kidney, or hematologic system or those with chronic diseases;
- Those who are unable to follow the trial procedures;
- Those who refuse to sign the informed consent.
Trial locations and contacts
1 site in 1 country.
China1 site, 1 recruiting
- Recruiting
Peking UniversityThird Hospital
Beijing, Beijing Municipality
About this study
Official title: Application of a Multimodal Large Language Model to Assist Diagnosis for Heart Failure With Preserved Ejection Fraction
This study will validate the effectiveness of a multimodal large language model to screen for heart failure with preserved ejection fraction (HFpEF), comparing it with the traditional clinical standardized assessment process.
Read the detailed description
Heart failure is a major complication of various heart diseases and is the leading lethal cause of cardiovascular death worldwide. Based on the left ventricular ejection fraction (LVEF), heart failure can be divided into heart failure with reduced ejection fraction (HFrEF), heart failure with preserved ejection fraction (HFpEF) and heart failure with mildly reduced ejection fraction (HFmrEF). Heart failure rehospitalization rates and in-hospital complications did not differ between HFrEF and HFpEF. However, over the past two decades, the survival rate of HFrEF has improved significantly, whereas HFpEF has remained stagnant. One of the major reasons for this is that the diagnostic process of HFpEF is complicated, and it is easy to cause missed diagnosis in the clinic, resulting in delayed treatment.
Multimodal large language models are capable of integrating and analyzing medical data from different sources, including textual data (e.g., medical records, medical literature), image data (e.g., electrocardiograms, CT scan images), and audio data (e.g., symptoms narrated by patients). This multimodal data integration capability is crucial for understanding complex medical scenarios, as it provides a more comprehensive view of the condition than a single data source.
The diagnosis of HFpEF faces many challenges and requires clinicians to make judgments on multi-dimensional data, which can easily lead to the underdiagnosis and misdiagnosis of the disease. As a generative artificial intelligence tool, a large language model is able to integrate and analyze data from different sources and has the ability to learn and evolve from existing clinical evidence. Based on this, this study intends to evaluate the effectiveness of multimodal large language model for screening for heart failure with preserved ejection fraction (HFpEF), comparing it with the traditional clinical standard assessment process.
- Being tested
- Multimodal Large Language Model Diagnosis, Routine diagnostic and therapeutic procedure
- Keywords
- Heart failure with preserved ejection fraction, large language model, diagnosis
- Medical subject headings
- Disease
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Multimodal Large Language Model DiagnosisDiagnostic test
Diagnosis for heart failure with preserved ejection fraction (HFpEF) using the multimodal large language model MedGuide-72B.
Routine diagnostic and therapeutic procedureDiagnostic test
Routine diagnostic and therapeutic procedure
| Study group | Role | What they receive |
|---|---|---|
| single group | The routine consultation process was performed first: according to the process recommended by the 2023 edition of the Chinese Expert Consensus on the Diagnosis and Treatment of Heart Failure with Preserved Ejection Fraction, the attending cardiologist completed the subject's clinical criteria assessment and performed the HFpEF diagnosis (yes/no).
During the attending physician's checkup visit, the multimodal large language model screening system (MedGuide-72B) collected routine visit data, recorded relevant data and indicators during the patient's communication with MedGuide-72B and made the diagnosis. Receives: Diagnostic Test: Multimodal Large Language Model Diagnosis; Diagnostic Test: Routine diagnostic and therapeutic procedure |
What is being measured
The primary outcome is the main question the study is designed to answer.
dignostic specificity
dianostic specificity comparison between routine diagnosis and therapy and large language model diagnosis
Measured: through study completion, an average of 8 months
dignostic sensitivity
dianostic sensitivity comparison between routine diagnosis and therapy and large language model diagnosis
Measured: through study completion, an average of 8 months
Secondary outcomes (7)
consistency rate
consistency rate between routine diagnosis and therapy and large language model diagnosis
Measured: through study completion, an average of 8 months
time spent on diagnosis
comparison of time spent on diagnosis between routine diagnosis and therapy and large language model diagnosis
Measured: through study completion, an average of 8 months
patient satisfaction
comparison of patient satisfaction between routine diagnosis and therapy and large language model diagnosis by questionnaire
Measured: through study completion, an average of 8 months
economic cost analysis
comparison of economic cost between routine diagnosis and therapy and large language model diagnosis by the total cost of treatment
Measured: through study completion, an average of 8 months
false discovery rate
comparison of false discovery rate between routine diagnosis and therapy and large language model diagnosis
Measured: through study completion, an average of 8 months
physician workload assessment
comparison of physician workload between routine diagnosis and therapy and large language model diagnosis according to counting the number of participants with treatment-related
Measured: through study completion, an average of 8 months
diagnosis efficiency
The probability of accuracy compared to the final diagnosis of the patient's visit
Measured: through study completion, an average of 8 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted3 Jul 2024
- Study start20 Dec 2023
- Primary completion20 Dec 2024 (estimated)
- Study completion20 Dec 2024 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (9)Papers the sponsor has linked to this study.
- Other trials for Heart Failure With Preserved Ejection FractionStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Case crossover
- Time perspective
- Prospective
- Enrolment
- 80 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Peking University Third Hospital
- Sponsor type
- University, hospital or other
- Collaborators
- Tianjin Medical University General Hospital, The First Hospital of Hebei Medical University, Qianfoshan Hospital, Qingdao Municipal Hospital
- Responsible party
- Principal investigator, Tang Yida, Peking University Third Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT06486649
- Sponsor's protocol ID
- M2023830
- Acronym
- MeG-HFpEF
- Status last verified
- Jun 2024
- First submitted
- 22 Dec 2023
- Last updated
- 3 Jul 2024
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Kittleson MM, Panjrath GS, Amancherla K, Davis LL, Deswal A, Dixon DL, Januzzi JL Jr, Yancy CW. 2023 ACC Expert Consensus Decision Pathway on Management of Heart Failure With Preserved Ejection Fraction: A Report of the American College of Cardiology Solution Set Oversight Committee. J Am Coll Cardiol. 2023 May 9;81(18):1835-1878. doi: 10.1016/j.jacc.2023.03.393. Epub 2023 Apr 19. No abstract available.
PubMed 37137593Wang X, Cunningham JW. Restoring balance in heart failure with preserved ejection fraction. Eur J Heart Fail. 2022 Aug;24(8):1415-1417. doi: 10.1002/ejhf.2599. Epub 2022 Jul 18. No abstract available.
PubMed 35789069Sicari R. Phenotyping heart failure with preserved ejection fraction with exercise stress echocardiography. Eur Heart J Cardiovasc Imaging. 2022 Jul 21;23(8):1053-1054. doi: 10.1093/ehjci/jeac053. No abstract available.
PubMed 35262693Omote K, Verbrugge FH, Borlaug BA. Heart Failure with Preserved Ejection Fraction: Mechanisms and Treatment Strategies. Annu Rev Med. 2022 Jan 27;73:321-337. doi: 10.1146/annurev-med-042220-022745. Epub 2021 Aug 11.
PubMed 34379445Margulies KB. DELIVERing Progress in Heart Failure with Preserved Ejection Fraction. N Engl J Med. 2022 Sep 22;387(12):1138-1140. doi: 10.1056/NEJMe2210177. Epub 2022 Aug 27. No abstract available.
PubMed 36027566Ventura HO, Lavie CJ, Mehra MR. Heart Failure With Preserved Ejection Fraction: Separating the Wheat From the Chaff. J Am Coll Cardiol. 2020 Jan 28;75(3):255-257. doi: 10.1016/j.jacc.2019.11.027. No abstract available.
PubMed 31976862Reddy YNV, Borlaug BA. Heart Failure With Preserved Ejection Fraction: Where Do We Stand? Mayo Clin Proc. 2020 Apr;95(4):629-631. doi: 10.1016/j.mayocp.2020.02.015. No abstract available.
PubMed 32247333Donal E, L'official G, Kosmala W. Heart Failure With Preserved Ejection Fraction: Defining Phenotypes. J Card Fail. 2020 Nov;26(11):929-931. doi: 10.1016/j.cardfail.2020.09.013. Epub 2020 Sep 19. No abstract available.
PubMed 32956811Ahmad T, Desai NR, Januzzi JL. Heart Failure With Preserved Ejection Fraction: Many Emperors With Many Clothes. JACC Heart Fail. 2020 Mar;8(3):185-187. doi: 10.1016/j.jchf.2019.11.004. Epub 2020 Jan 8. No abstract available.
PubMed 31926855
Study at a glance
From the registry record, last updated by the sponsor on 3 Jul 2024. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Application of a Multimodal Large Language Model to Assist Diagnosis for Heart Failure With Preserved Ejection Fraction
- ClinicalTrials.gov ID
- NCT06486649
- Acronym / sponsor ID
- MeG-HFpEF / M2023830
- Keywords
- Heart failure with preserved ejection fraction, large language model, diagnosis
- Study type
- Observational
- Recruitment status
- Unknown status
- Enrolment
- 80 participants (estimated)
- Lead sponsor
- Peking University Third HospitalUniversity, hospital or other
- Collaborators
- Tianjin Medical University General Hospital, The First Hospital of Hebei Medical University, Qianfoshan Hospital, Qingdao Municipal Hospital
- Study start
- 20 Dec 2023 (actual)
- Primary completion
- 20 Dec 2024 (estimated)
- Study completion
- 20 Dec 2024 (estimated)
- First posted
- 3 Jul 2024 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This study will validate the effectiveness of a multimodal large language model to screen for heart failure with preserved ejection fraction (HFpEF), comparing it with the traditional clinical standardized assessment process.
Detailed description
Heart failure is a major complication of various heart diseases and is the leading lethal cause of cardiovascular death worldwide. Based on the left ventricular ejection fraction (LVEF), heart failure can be divided into heart failure with reduced ejection fraction (HFrEF), heart failure with preserved ejection fraction (HFpEF) and heart failure with mildly reduced ejection fraction (HFmrEF). Heart failure rehospitalization rates and in-hospital complications did not differ between HFrEF and HFpEF. However, over the past two decades, the survival rate of HFrEF has improved significantly, whereas HFpEF has remained stagnant. One of the major reasons for this is that the diagnostic process of HFpEF is complicated, and it is easy to cause missed diagnosis in the clinic, resulting in delayed treatment.
Multimodal large language models are capable of integrating and analyzing medical data from different sources, including textual data (e.g., medical records, medical literature), image data (e.g., electrocardiograms, CT scan images), and audio data (e.g., symptoms narrated by patients). This multimodal data integration capability is crucial for understanding complex medical scenarios, as it provides a more comprehensive view of the condition than a single data source.
The diagnosis of HFpEF faces many challenges and requires clinicians to make judgments on multi-dimensional data, which can easily lead to the underdiagnosis and misdiagnosis of the disease. As a generative artificial intelligence tool, a large language model is able to integrate and analyze data from different sources and has the ability to learn and evolve from existing clinical evidence. Based on this, this study intends to evaluate the effectiveness of multimodal large language model for screening for heart failure with preserved ejection fraction (HFpEF), comparing it with the traditional clinical standard assessment process.
Study design
- Observational model
- Case crossover
- Time perspective
- Prospective
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| single group | – | Diagnostic Test: Multimodal Large Language Model Diagnosis, Diagnostic Test: Routine diagnostic and therapeutic procedureThe routine consultation process was performed first: according to the process recommended by the 2023 edition of the Chinese Expert Consensus on the Diagnosis and Treatment of Heart Failure with Preserved Ejection Fraction, the attending cardiologist completed the subject's clinical criteria assessment and performed the HFpEF diagnosis (yes/no). During the attending physician's checkup visit, the multimodal large language model screening system (MedGuide-72B) collected routine visit data, recorded relevant data and indicators during the patient's communication with MedGuide-72B and made the diagnosis. |
Who may qualify
- Ages
- 18 to 80 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Subjects will be recruited from patients routinely hospitalized in the cardiology department who also met the needs of this trial and are not recruited separately.
Key inclusion criteria (4 listed)
- Age 18-80 years, male or female;
- Cardiology inpatients with suspected heart failure with preserved ejection fraction (cardiac ultrasound suggestive of LVEF ≥50% with at least 1 of the following: 1, left ventricular hypertrophy and/or left atrial enlargement; and 2, abnormal diastolic cardiac function);
- Current or previous at least one symptom of heart failure, including dyspnea (including exertional dyspnea, nocturnal paroxysmal dyspnea, and telangiectasia), malaise, nausea, and bilateral lower extremity edema;
- Voluntary participation and signed informed consent.
Key exclusion criteria (7 listed)
- Acute heart failure or acute worsening of chronic heart failure;
- Severe coronary stenosis (≥75% stenosis) without revascularization;
- Patients who are unable to perform exercise stress echocardiography or have contraindications to the test;
- are participating in other clinical trials;
- Those with severe organic pathologies of the liver, kidney, or hematologic system or those with chronic diseases;
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Multimodal Large Language Model DiagnosisDiagnosis for heart failure with preserved ejection fraction (HFpEF) using the multimodal large language model MedGuide-72B. | Diagnostic test | single group |
| Routine diagnostic and therapeutic procedureRoutine diagnostic and therapeutic procedure | Diagnostic test | single group |
Primary outcome
dignostic specificity
Time frame: through study completion, an average of 8 months
dianostic specificity comparison between routine diagnosis and therapy and large language model diagnosis
dignostic sensitivity
Time frame: through study completion, an average of 8 months
dianostic sensitivity comparison between routine diagnosis and therapy and large language model diagnosis
7 secondary outcomes
consistency rate
Time frame: through study completion, an average of 8 months
time spent on diagnosis
Time frame: through study completion, an average of 8 months
patient satisfaction
Time frame: through study completion, an average of 8 months
economic cost analysis
Time frame: through study completion, an average of 8 months
false discovery rate
Time frame: through study completion, an average of 8 months
physician workload assessment
Time frame: through study completion, an average of 8 months
diagnosis efficiency
Time frame: through study completion, an average of 8 months
Results and safety
Results are not available in the source record.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 3 Jul 2024.
- Background: PubMed 37137593Kittleson MM, Panjrath GS, Amancherla K, Davis LL, Deswal A, Dixon DL, Januzzi JL Jr, Yancy CW. 2023 ACC Expert Consensus Decision Pathway on Management of Heart Failure With Preserved Ejection Fraction: A Report of the American College of Cardiology Solution Set Oversight Committee. J Am Coll Cardiol. 2023 May 9;81(18):1835-1878. doi: 10.1016/j.jacc.2023.03.393. Epub 2023 Apr 19. No abstract available.
- Background: PubMed 35789069Wang X, Cunningham JW. Restoring balance in heart failure with preserved ejection fraction. Eur J Heart Fail. 2022 Aug;24(8):1415-1417. doi: 10.1002/ejhf.2599. Epub 2022 Jul 18. No abstract available.
- Background: PubMed 35262693Sicari R. Phenotyping heart failure with preserved ejection fraction with exercise stress echocardiography. Eur Heart J Cardiovasc Imaging. 2022 Jul 21;23(8):1053-1054. doi: 10.1093/ehjci/jeac053. No abstract available.
- Background: PubMed 34379445Omote K, Verbrugge FH, Borlaug BA. Heart Failure with Preserved Ejection Fraction: Mechanisms and Treatment Strategies. Annu Rev Med. 2022 Jan 27;73:321-337. doi: 10.1146/annurev-med-042220-022745. Epub 2021 Aug 11.
- Background: PubMed 36027566Margulies KB. DELIVERing Progress in Heart Failure with Preserved Ejection Fraction. N Engl J Med. 2022 Sep 22;387(12):1138-1140. doi: 10.1056/NEJMe2210177. Epub 2022 Aug 27. No abstract available.
- Background: PubMed 31976862Ventura HO, Lavie CJ, Mehra MR. Heart Failure With Preserved Ejection Fraction: Separating the Wheat From the Chaff. J Am Coll Cardiol. 2020 Jan 28;75(3):255-257. doi: 10.1016/j.jacc.2019.11.027. No abstract available.
- Background: PubMed 32247333Reddy YNV, Borlaug BA. Heart Failure With Preserved Ejection Fraction: Where Do We Stand? Mayo Clin Proc. 2020 Apr;95(4):629-631. doi: 10.1016/j.mayocp.2020.02.015. No abstract available.
- Background: PubMed 32956811Donal E, L'official G, Kosmala W. Heart Failure With Preserved Ejection Fraction: Defining Phenotypes. J Card Fail. 2020 Nov;26(11):929-931. doi: 10.1016/j.cardfail.2020.09.013. Epub 2020 Sep 19. No abstract available.
- Background: PubMed 31926855Ahmad T, Desai NR, Januzzi JL. Heart Failure With Preserved Ejection Fraction: Many Emperors With Many Clothes. JACC Heart Fail. 2020 Mar;8(3):185-187. doi: 10.1016/j.jchf.2019.11.004. Epub 2020 Jan 8. No abstract available.
- Individual participant dataSharing planned: No
Related trials for Heart Failure With Preserved Ejection Fraction
RecruitingPhase 1/2
HS235 Study in Overweight and Obese Participants With Combined Pre and Post-Capillary Pulmonary Hypertension Due to Heart Failure With Preserved Ejection Fraction
Pulmonary Hypertension, Heart Failure With Preserved Ejection Fraction
RecruitingPhase 2
The Clinical Trial of Tamibarotene for Patients With HFpEF (RELIEF Trial)
HFpEF - Heart Failure With Preserved Ejection Fraction
RecruitingPhase 3
Maridebart Cafraglutide in Heart Failure With Preserved or Mildly Reduced Ejection Fraction and Obesity
Heart Failure With Preserved Ejection Fraction, Heart Failure With Mildly Reduced Ejection Fraction
Recruiting
PrEcision Pacing in HFpEF: the PEP-HFpEF Trial
Heart Failure and Preserved Ejection Fraction, Heart Failure New York Heart Association Class III
Active, not recruiting
Fast Induced Remodeling in Heart Failure With Preserved Ejection Fraction
Heart Failure With Preserved Ejection Fraction, Concentric Hypertrophy
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Heart Failure With Preserved Ejection Fraction, run by Peking University Third Hospital at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 4 inclusion and 7 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: status not confirmed, as of the sponsor's last update on 3 Jul 2024. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Results are not available in the source record.
How can a doctor refer a patient or contact the research team?
Contact Xiangbin Meng (17600220171, 15896850171@163.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
dignostic specificity (time frame: through study completion, an average of 8 months). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT06486649, which also lists 9 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 3 Jul 2024.