Toward Precision Cardiac Rehabilitation: Current Limitations and Future Opportunities of Omics and Artificial Intelligence.
Researchers
Amine Ghram, Javier Loureiro Diaz, Preeti Raghavan, Arto J Hautala, Rasha Kaddoura, Jari A Laukkanen, Setor K Kunutsor, Mohamed A Elrayess, Beat Knechtle, Katja Weiss, Thomas Rosemann, Salaheddin M Sharif, Amanda R Bonikowske, Thijs M H Eijsvogels, Linda S Pescatello, Leonard A Kaminsky, Abraham Samuel Babu, Giuseppe Biondi-Zoccai, Manuel Avelino Giráldez-García, Javaid Nauman, Giuseppe Lippi, Josef Niebauer, Francesco Perone, Karim Chamari, Hani Sabbour, Miguel Paniagua, Sara Omar, Karam I Turk-Adawi, Marta Supervia, Laila Hedaya, Omar Ibrahim, Mohamed Suliman, Praveen Jayaprabha Surendran, Daniel Martinez-Bussion, Manal S Al Shamari, Mohammed Alhashemi, Tagowg Agab, Rehab Ahmad, M S Ajimsha, Adam Staron, Adel Shabana, Amal Albatini, Abdulfattah S Alqahtani, Raghdah Aljehani, Aisha Aladab, Hisham A Sattar, Trine Moholdt, Øyvind Sandbakk, Carl J Lavie, Helmi Ben Saad
Abstract
Cardiovascular disease involves complex molecular, cellular, and physiological derangements that present challenges for traditional diagnostic and therapeutic approaches. Precision medicine is an evolving field that seeks to tailor interventions according to an individual's genetic, molecular, and physiological characteristics. By leveraging advanced omics approaches, including genomics, proteomics, metabolomics, and microbiomics, precision medicine may enable more comprehensive patient phenotyping and support the development of more individualized strategies. The emerging concept of precision cardiac rehabilitation (CR) could provide a more tailored approach to cardiac care by integrating artificial intelligence (AI) with multimodal data, including clinical, imaging, physiological, and omics information. In this context, AI has been explored as a tool to support risk assessment, exercise prescription, and monitoring during CR. However, current evidence remains limited and heterogeneous. Omics-based approaches are primarily confined to research and translational settings, and their role in guiding individualized exercise prescription or clinical decision making in CR remains unestablished. Similarly, while AI shows promise for improving adherence, remote monitoring, and data integration, its effectiveness for optimizing clinical outcomes in CR requires further validation. Overall, precision CR represents a promising but still evolving paradigm. Future progress will depend on well-designed clinical trials, real-world data integration, standardized methodologies, and interdisciplinary collaboration to determine whether these technologies can be safely and effectively integrated into routine clinical practice.