Aim of the proposal is to create an interactive AI-based multicentre prospective database to provide information on how to improve the QoC for pts with HF.This will provide detailed information on pts characteristics,treatment practices, adherence to prescribed guideline-based optimal drug therapy,and outcomes.The database stems from a registry started two years ago,conceived to provide a contemporary snapshot on the adherence to the latest European GGLL for the therapeutic management of pts with HF.The database will be integrated with a specifically designed algorithm that provides an accurate feedback on whether patients are properly treated according to the ESC most recent recommendations.The expected outcomes are:-define non-adherence level to GGLL-based recommendations for treatment of HF;-provide information on initiation, adherence and persistence over time of the recommended treatment;-reduce medical inertia;produce practical implications to reduce morbidity and mortality

Heart Failure (HF) is a worldwide leading cause of death and continues to increase, with important implications for healthcare providers. International guidelines (GGLL) for patients with HF recommend a combination of drugs to reduce the risk of events and improve patient¿s symptoms. However, the current impact of guideline-directed medical therapies on mortality and morbidity remains limited because population of HF patients is very different from that enrolled in clinical trials, which is much older and therefore suffers multiple comorbidities, with the need of higher precision therapy based on their phenotype. Therefore, medical inertia is another lack of adherence factor and bad outcomes for HF patients. The aim of the proposal is to create an interactive multicentre prospective database initiated to provide information on how to improve the quality of care for patients (pts) with HF. The database will provide detailed information on pts characteristics, treatment practices, adherence to prescribed guideline, based optimal drug therapy and outcomes. Populations and Methods: The database stems from a registry that started two years ago. This registry was conceived to provide a contemporary snapshot adherence to the latest European guidelines for HF. The database will be integrated with a specifically designed artificial intelligence-based algorithm that provides an accurate feedback on whether patients are properly treated according to the European Society of Cardiology (ESC) most recent and updated recommendations for the treatment of patients with HF, suggesting the right therapy and target dosage based on patients¿ phenotype, clinical characteristic and comorbidities. According to HF drug major trials results, the algorithm will calculate the saved hospitalizations, urgent visits for decompensated HF and death for HF. Using an algorithm, created by inquiring about a recently started HF registry, this project will be able to produce practical implications to reduce morbidity and mortality in pts with HF, thanks to the increase of pts adherence to optimal treatments and physician¿s compliance to GGLL.

Inclusion Criteria:

• Both gender
• Age >18 years
• Signed informed consent for the study
• Known diagnosis of heart failure > 6 months
• Recent or ongoing hospitalization for heart failure exacerbation

Exclusion Criteria:

• Conditions that, in the investigator's judgment, may interfere with the study or contraindicate participation for safety reasons
• Concurrent diagnosis of neoplasia
• Advanced COPD (FEV1 <50%)
• Advanced valvular heart disease (severe mitral-aortic stenosis-insufficiency requiring cardiac surgery)

Patients with heart Failure