Chronic Heart FailurePREDICT-CVDNCT07369141
PREcision meDICine in Treatment in CardioVascular Disease
A study testing ASSIST-HF AI- algorithm in people with Chronic Heart Failure and Acute Decompensated Heart Failure, run by Maastricht University Medical Center at 4 sites in Netherlands.
Trial summary
The main goal of PREDICT-CVS is to demonstrate that a personalized, AI-derived biomarker-guided medication treatment algorithm that provides advice to the treating professional is superior to prevent clinical events and improve quality of life (QoL) when compared to patients receiving standard treatment of care. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Chronic Heart Failure, Acute Decompensated Heart Failure
- What is being tested?
- ASSIST-HF AI- algorithm
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 0 participants
- Where
- 4 sitesNetherlands
- Study dates
- Feb 2026to Jun 2028
- Phase
- Interventional
- 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 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Provide written and dated informed consent for participation prior to trial admission,
- Age ≥18 years, female or male
- Diagnosis of heart failure* either before discharge of a heart failure hospital admission or in the outpatient setting,
- Symptomatic, defined as NYHA class II - IV,
- LVEF < 50% measured in the last 12 months (using any modality), with no occurrence of HF event(s) since that measurement) and
- Those not previously treated with evidence-based therapies or sub-optimally treated with GDMT defined as; • Not treated with one of the foundational four** HF medication unless absolute contraindication or documented intolerance
- Definition of heart failure according to the most recent Heart Failure Guidelines of the European Society of Cardiology
- Foundational four heart failure medication: BBs, ARNi, MRAs and SGLT2i. NB. This does not include ACE and ARBs these are permitted.
Who cannot join
- Inability to understand and sign informed consent,
- Scheduled or on renal replacement therapy,
- Clearly documented intolerance to BBs, ARNI, SGLT2i or MRAs
- Diagnosis of acute myocarditis or (non)obstructive hypertrophic cardiomyopathy,
- The presence of a mechanical assist device,
- Scheduled for mechanical assist device or heart transplant,
Show all 12Show fewer
- Acute coronary syndrome (ACS) in the past 3 months or current angina pectoris ≥class III,
- Requiring valvular surgery or revascularization in the upcoming 3 months or revascularization within the past 3 months,
- Anticipated need for surgery or any cardiovascular intervention, except implantable cardioverter defibrillator and/or cardiac resynchronization therapy, within 4 weeks,
- Other non-cardiac conditions with limited life expectancy (≤ duration of the trial/ 1 year),
- Participation in another (intervention) clinical trial (registry studies not included) until the onsite EoS visit (V5) at 9 months has been completed.
- Women who are pregnant, breastfeeding or may be considering pregnancy during the study duration.
Trial locations and contacts
4 sites in 1 country.
Netherlands4 sites
University Medical Center Groningen
Groningen
Leiden University Medical Center
Leiden
Maastricht University Medical Center
Maastricht
Erasmus Medical Center
Rotterdam
About this study
The main goal of PREDICT-CVS is to demonstrate that a personalized, AI-derived biomarker-guided medication treatment algorithm that provides advice to the treating professional is superior to prevent clinical events and improve quality of life (QoL) when compared to patients receiving standard treatment of care.
Participants will be randomized into two groups
Read more
- Group 1 - Standard treatment Participant will receive the usual treatment for heart failure, based on current medical guidelines.
- Group 2 - AI-supported treatment The professional will receive a personalized treatment plan generated by the AI program. This plan is based on medical information and biomarkers. The professional can choose whether or not to follow the AI's advice, reasons for not following the AI-based advice will be collected.
Participants will visit the outpatient clinic at 1, 2, 3 and 9 months after being randomized.
Read the detailed description
The PREDICT-CVD is a prospective, randomized controlled, open label, multinational trial, in which patients with HF will be randomized to either the control arm or the intervention arm. The control arm is the standard of care and the intervention arm is where an AI-derived biomarker-guided treatment algorithm will be applied, to assist the treating professional in treatment decision. Assessment of the primary endpoint will be at the 9 month onsite follow-up visit, further long-term outcomes will be collected via telephone visits every 6 months until the last subject has completed the 9 month onsite follow-up.
The main objective is to demonstrate that a personalized, AI-derived biomarker-guided medication treatment algorithm that provides advice to the treating HF professional is superior to prevent clinical events and improve quality of life (QoL) when compared to patients receiving standard treatment of care.
The primary outcome of the trial is a clinical benefit, defined as a hierarchical composite of death from any cause, number of heart failure events and or a greater difference in change from baseline in the Kansas City Cardiomyopathy Questionnaire Total Symptom Score at 9 months, as assessed using a win ratio.
The expected duration for patients will be between 9 and max 24 months from the moment of enrollment. From 9 months onwards patients will be contacted by phone every 6 months and information regarding (HF) events and concomitant medication will be collected.
- Being tested
- ASSIST-HF AI- algorithm, Standard of Care (Investigator Choice)
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
ASSIST-HF AI- algorithmOther
AI-derived biomarker-guided treatment algorithm to assist the treating HF professional in treatment decision
Standard of Care (Investigator Choice)Other
Standard treatment of care for HF
| Study group | Role | What they receive |
|---|---|---|
| Standard of Care | Active comparator | Standard treatment for HF Receives: Other: Standard of Care (Investigator Choice) |
| Intervention | Experimental | AI algorithm to assist the treating HF professional in treatment decision Receives: Other: ASSIST-HF AI- algorithm |
What is being measured
The primary outcome is the main question the study is designed to answer.
Clinical benefit
Hierarchical composite of death from any cause, number of heart failure events and or a greater difference in change from baseline in the Kansas City Cardiomyopathy Questionnaire Total Symptom Score, as assessed using a win ratio
Measured: 9 months
Secondary outcomes (9)
Time to death from any cause
time to the first (re)hospitalization due to disease progression
Measured: 9 months (the number of days/months from randomization to the date of death)
Time to first (re)-hospitalization due to heart failure
Time to first (re)-hospitalization due to heart failure
Measured: 9 months (the number of days/months from randomization to the date of first (re)-hospitalization due to heart failure)
Time to all-cause hospitalization
Time to all-cause hospitalization
Measured: 9 months (the number of days/months from randomization to the date of all cause hospitalization).
Time to cardiovascular (CV) mortality
Time to cardiovascular (CV) mortality
Measured: 9 months (the number of days/months from randomization to the date of CV death)
Change in QoL
Change in QoL according to the KCCQ-TSS (change from baseline in KCCQ-TSS score, measured in points, with higher scores indicating better health status.)
Measured: 9 months
Change in NT-proBNP
Change in NT-proBNP (pg/mL)
Measured: 9 months
Change in clinical congestion score
Change in clinical congestion score (CCS). The higher the score the worst congestion is
Measured: 9 months
Change in eGFR
Change in eGFR (mL/min/1.73 m²)
Measured: 9 months
GDMT at 9 month
Guideline directed Medical Therapy
Measured: 9 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted27 Jan 2026
- Study startFeb 2026 (estimated)
- Primary completionMar 2028 (estimated)
- Study completionJun 2028 (estimated)
Why it stopped: Despite extensive modelling, it was not possible to develop a model that had sufficient accuracy and could be readily applied in a clinical trial.
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Chronic Heart FailureStudies of the same condition, open and under way.
- More trials run by Maastricht University Medical CenterThe sponsor's other registered studies.
- 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
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Proof of concept trial
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 0 participants (actual)
Sponsor and investigators
- Lead sponsor
- Maastricht University Medical Center
- Sponsor type
- University, hospital or other
- Collaborators
- University Medical Center Groningen, Maastricht University
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07369141
- Sponsor's protocol ID
- PREDICT-CVD
- Other IDs
- No 101112022, No 10088702, NL 009912
- Acronym
- PREDICT-CVD
- Status last verified
- Apr 2026
- First submitted
- 31 Dec 2025
- Last updated
- 17 Apr 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Undecided: not decided at this time yet
Study at a glance
From the registry record, last updated by the sponsor on 17 Apr 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- PREcision meDICine in Treatment in CardioVascular Disease
- ClinicalTrials.gov ID
- NCT07369141
- Acronym / sponsor ID
- PREDICT-CVD / PREDICT-CVD
- Study type
- Interventional
- Recruitment status
- WithdrawnReason stopped: Despite extensive modelling, it was not possible to develop a model that had sufficient accuracy and could be readily applied in a clinical trial.
- Enrolment
- 0 participants (actual)
- Lead sponsor
- Maastricht University Medical CenterUniversity, hospital or other
- Collaborators
- University Medical Center Groningen, Maastricht University
- Study start
- Feb 2026 (estimated)
- Primary completion
- Mar 2028 (estimated)
- Study completion
- Jun 2028 (estimated)
- First posted
- 27 Jan 2026 (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.
The main goal of PREDICT-CVS is to demonstrate that a personalized, AI-derived biomarker-guided medication treatment algorithm that provides advice to the treating professional is superior to prevent clinical events and improve quality of life (QoL) when compared to patients receiving standard treatment of care.
Participants will be randomized into two groups
- Group 1 - Standard treatment Participant will receive the usual treatment for heart failure, based on current medical guidelines.
- Group 2 - AI-supported treatment The professional will receive a personalized treatment plan generated by the AI program. This plan is based on medical information and biomarkers. The professional can choose whether or not to follow the AI's advice, reasons for not following the AI-based advice will be collected.
Participants will visit the outpatient clinic at 1, 2, 3 and 9 months after being randomized.
Detailed description
The PREDICT-CVD is a prospective, randomized controlled, open label, multinational trial, in which patients with HF will be randomized to either the control arm or the intervention arm. The control arm is the standard of care and the intervention arm is where an AI-derived biomarker-guided treatment algorithm will be applied, to assist the treating professional in treatment decision. Assessment of the primary endpoint will be at the 9 month onsite follow-up visit, further long-term outcomes will be collected via telephone visits every 6 months until the last subject has completed the 9 month onsite follow-up.
The main objective is to demonstrate that a personalized, AI-derived biomarker-guided medication treatment algorithm that provides advice to the treating HF professional is superior to prevent clinical events and improve quality of life (QoL) when compared to patients receiving standard treatment of care.
The primary outcome of the trial is a clinical benefit, defined as a hierarchical composite of death from any cause, number of heart failure events and or a greater difference in change from baseline in the Kansas City Cardiomyopathy Questionnaire Total Symptom Score at 9 months, as assessed using a win ratio.
The expected duration for patients will be between 9 and max 24 months from the moment of enrollment. From 9 months onwards patients will be contacted by phone every 6 months and information regarding (HF) events and concomitant medication will be collected.
Study design
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (outcomes assessor)
- Number of arms
- 2
- Model description
- Proof of concept trial
| Arm | Type | Receives |
|---|---|---|
| Standard of Care | Active comparator | Other: Standard of Care (Investigator Choice)Standard treatment for HF |
| Intervention | Experimental | Other: ASSIST-HF AI- algorithmAI algorithm to assist the treating HF professional in treatment decision |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (8 listed)
- Provide written and dated informed consent for participation prior to trial admission,
- Age ≥18 years, female or male
- Diagnosis of heart failure* either before discharge of a heart failure hospital admission or in the outpatient setting,
- Symptomatic, defined as NYHA class II - IV,
- LVEF < 50% measured in the last 12 months (using any modality), with no occurrence of HF event(s) since that measurement) and
Key exclusion criteria (12 listed)
- Inability to understand and sign informed consent,
- Scheduled or on renal replacement therapy,
- Clearly documented intolerance to BBs, ARNI, SGLT2i or MRAs
- Diagnosis of acute myocarditis or (non)obstructive hypertrophic cardiomyopathy,
- The presence of a mechanical assist device,
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 |
|---|---|---|
| ASSIST-HF AI- algorithmAI-derived biomarker-guided treatment algorithm to assist the treating HF professional in treatment decision | Other | Intervention |
| Standard of Care (Investigator Choice)Standard treatment of care for HF | Other | Standard of Care |
Primary outcome
Clinical benefit
Time frame: 9 months
Hierarchical composite of death from any cause, number of heart failure events and or a greater difference in change from baseline in the Kansas City Cardiomyopathy Questionnaire Total Symptom Score, as assessed using a win ratio
9 secondary outcomes
Time to death from any cause
Time frame: 9 months (the number of days/months from randomization to the date of death)
Time to first (re)-hospitalization due to heart failure
Time frame: 9 months (the number of days/months from randomization to the date of first (re)-hospitalization due to heart failure)
Time to all-cause hospitalization
Time frame: 9 months (the number of days/months from randomization to the date of all cause hospitalization).
Time to cardiovascular (CV) mortality
Time frame: 9 months (the number of days/months from randomization to the date of CV death)
Change in QoL
Time frame: 9 months
Change in NT-proBNP
Time frame: 9 months
Change in clinical congestion score
Time frame: 9 months
Change in eGFR
Time frame: 9 months
GDMT at 9 month
Time frame: 9 months
Results and safety
The study was withdrawn before enrolling participants, so there are no results.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 17 Apr 2026.
- Individual participant dataSharing planned: Undecided. not decided at this time yet
Related trials for Chronic Heart Failure
Not yet recruiting
RELIEVE-HFrEF TRIAL: REducing Lung congestIon Symptoms Using the v-wavE Shunt in adVancEd Heart Failure With Reduced EF
Heart Failure and Reduced Ejection Fraction, Heart Failure Chronic
Not yet recruiting
Community Health Worker Nutrition Self-Management Support for Cardio-Kidney-Metabolic Health
Hypertension (HTN), CKD - Chronic Kidney Disease
RecruitingPhase 4
The Effects of Low-Dose Versus High-Dose Intravenous IRON Therapy With Ferric DerisomaltOSE in Patients With Chronic Heart Failure and Iron Deficiency
Heart Failure, Iron Deficiency
Recruiting
WIN Ratio Analysis to Determine a Strategy of Non- Invasive SUpport for Respiratory Failure in the EmeRgency Department
Acute Hypoxic Respiratory Failure, Acute Respiratory Distress Syndrome (ARDS)
RecruitingObservational study
Norepinephrine in the Management of General Anesthesia-Induced Arterial Hypotension in Chronic Heart Failure Patients
Hypotension
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.
The record lists no contact. Use the official record to reach the sponsor.
4 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing ASSIST-HF AI- algorithm in people with Chronic Heart Failure and Acute Decompensated Heart Failure, run by Maastricht University Medical Center at 4 sites in Netherlands.
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 8 inclusion and 12 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: withdrawn, as of the sponsor's last update on 17 Apr 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 4 sites in Netherlands. 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?
The study was withdrawn before enrolling participants, so there are no results.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Clinical benefit (time frame: 9 months). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
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 17 Apr 2026; AzTrials last refreshed its copy on 7 Nov 2026.