Heart failure with preserved ejection fraction (HFpEF) is a complex pathology that has undergone a paradigm shift in the last few years. As technology develops and diagnosis algorithms become more refined, early diagnosis leads to prompt medical management. This management has also changed in recent years. Moreover, HFpEF phenotyping attempts further nuance the management of patients with this disease. Whereas guidelines are not so firm on the medical classes of drugs that should be employed in HFpEF compared to HFrEF, new trials are on the way to change this. This literature review focuses on the evolution of diagnosis criteria for HFpEF, the clinical scores proposed by current guidelines, and also on the medical management of this pathology, focusing on medical management and how it has changed recently, by highlighting landmark trials that have been published on the topic or that are going to be published on the topic.
Background: Digital transformation in cardiology is reshaping diagnosis, monitoring, and therapy through connected devices, digital biomarkers, telemedicine, and artificial intelligence. This paper synthesizes recent advances and emphasizes the shift from episodic assessment to continuous surveillance and personalized predictive care. Methods: The article included 81 studies published between 2015 and 2026, identified in PubMed, Google Scholar, and ScienceDirect, encompassing clinical trials, meta- analyses, observational studies, and reviews focused upon continuous cardiovascular monitoring, remote care, and AI-supported analysis. According to the selection criteria, studies with weak methodology or limited clinical relevance were removed. Results: Continuous monitoring enables early detection of physiological changes, individualized prevention, reduces hospitalizations, and supports cost efficiency and the expansion of remote services. Artificial intelligence and multimodal analytics facilitate dynamic risk stratification, clinical decision support, and the development of cardiovascular digital twin models for precision medicine. Implementation remains constrained by requirements for robust validation, potential algorithmic bias, data protection and cybersecurity concerns, and regulatory or acceptance barriers. Conclusions: Digital cardiology enables anticipatory, patient- centered healthcare based on continuous monitoring and AI as core clinical tools, promoting integrated patient–hospital–home ecosystems, real-time therapeutic guidance, and sustained cardiovascular prevention. The priorities defined by these directions are subjects for further research and healthcare development worldwide in the next decades. improves
(1) Introduction: Artificial intelligence (AI) is transforming healthcare and has particular relevance in military medicine, where austere environments, uncertainty, and time-critical decisions are common; (2) Methods: A literature review was conducted in PubMed/MEDLINE, Scopus, and Web of Science, covering studies published between 2000 and 2026. Relevant articles on AI in military medicine were identified and grouped into three domains: clinical, operational, and educational; (3) Results: Forty-one studies were included. In the clinical domain, AI supports decision-making, trauma care, medical imaging, and mental health, including early detection of post-traumatic stress disorder (PTSD). Operational applications include physiological monitoring, triage optimization, and medical evacuation. In education, AI enhances medical simulation and adaptive learning. Key limitations include poor data quality and availability, algorithmic bias, and limited validation in real operational settings; (4) Conclusions: AI can substantially improve military medical practice by increasing diagnostic accuracy, supporting rapid decisions, and improving operational efficiency. However, implementation requires rigorous clinical validation, transparent and reliable systems, and careful attention to ethical and organizational issues. AI should be used as a complementary tool that supports, rather than replaces, clinical judgment.
