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 type | Observational |
|---|---|
| Enrollment | 600 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | University Hospital, Caen (other) |
| Locations | 1 site (Caen) |
| Trial ID | NCT07191730 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
- CHU de Caen — Caen, France (RECRUITING)
Study contacts
- Study coordinator: Damien Legallois, MD, PhD
- Email: damien.legallois@unicaen.fr
- Phone: 33231064418
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Cardiotoxicity, Heart Failure, Neoplasms, Breast Neoplasms, Cancer Therapy-Related Cardiac Dysfunction, Anthracyclines, HER2-targeted Therapy, Cardio-Oncology