Machine-learning prediction of heart damage from anthracycline or HER2 cancer therapies

Machine Learning Score Prediction of Cardiotoxicity in Cancer Patients Receiving Anthracycline Chemotherapy or HER-2-Targeted Therapies

University Hospital, Caen · NCT07191730

We will see if a machine-learning score can predict which adults starting anthracycline or HER2-targeted cancer therapies will develop heart damage within one year.

Quick facts

Study typeObservational
Enrollment600 (estimated)
Ages18 Years and up
SexAll
SponsorUniversity Hospital, Caen (other)
Locations1 site (Caen)
Trial IDNCT07191730 on ClinicalTrials.gov

What this trial studies

This is a prospective, multicenter observational cohort in 15 French centers enrolling 600 patients treated with anthracyclines or HER2-targeted agents in cardio-oncology clinics. Patients receive a baseline pre-treatment evaluation and standardized data collection via a dedicated software platform that supports integration of AI tools. Machine learning methods will be used to develop a one-year prediction score for cancer therapy-related cardiotoxicity with the primary endpoint defined according to 2022 ESC criteria. Participants will be followed for 12 months to train and validate models and identify clinical and treatment-related predictors of cardiotoxicity.

Who should consider this trial

Good fit: Adults (≥18) who are starting or planning anthracycline and/or HER2-targeted therapy and who will have baseline pre-treatment follow-up in a participating French cardio-oncology clinic are ideal candidates.

Not a fit: People not receiving anthracyclines or HER2-targeted therapies, those without French national health insurance, or patients whose 12-month follow-up will occur outside the enrolling center are unlikely to benefit from this study.

Why it matters

Potential benefit: If successful, the score could help clinicians identify patients at high risk of therapy-related heart damage so monitoring and preventive care can be personalized.

How similar studies have performed: Machine-learning approaches to predict cardiotoxicity are emerging but currently have limited and mixed evidence, so this application remains relatively novel.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Age ≥ 18 years
* Planned follow-up in cardio-oncology clinic as part of a baseline pre-treatment evaluation before a sequence of anthracycline and/or HER2-targeted therapy, according to the 2022 ESC recommendations
* Inclusion regardless of prior exposure to potentially cardiotoxic anticancer therapies or thoracic radiotherapy

Exclusion Criteria:

* Patients not covered by the French national health insurance system (Sécurité Sociale)
* Patients for whom 12-month follow-up is planned outside the center performing the baseline pre-treatment evaluation

Where this trial is running

Caen

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.

View on ClinicalTrials.gov →

Conditions: Cardiotoxicity, Heart Failure, Neoplasms, Breast Neoplasms, Cancer Therapy-Related Cardiac Dysfunction, Anthracyclines, HER2-targeted Therapy, Cardio-Oncology

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.