Heart failure is the major pandemic of the 21st century. The number of patients and of Heart Failure-related deaths is progressively increasing. This means a devastating economic and health organization burden. In fact, chronic heart failure patients are at high risk of death, and the course of the disease is often insidious and uncertain with a progressive deterioration requiring the need for repeated and successive hospitalizations with an ominous prognosis: with each admission for acute heart failure there is a short-term improvement, a phase characterized by a degree of stability, and then a worsening phase follows until a new need for a new hospitalization. Moreover, with each subsequent hospitalization, myocardial function progressively declines, gradually worsening the patient's quality of life until the fatal event.

For these reasons, one of the major unmet needs is the identification of patients with a negative trajectory of Heart Failure. Accordingly, early identification of Heart Failure worsening is mandatory to improve patient condition and reduce Heart Failure costs, which are mainly associated with hospitalizations.

Our main goal through this project is to create clinical tool for detection of early signs of chronic heart failure (CHF) worsening that will allow timely therapeutic intervention. This timely manner intervention can lead to a much better outcome for the patient, possibly reducing the need for hospitalization or lower the number of hospitalization days.

The aim of this project is to develop clinical decision tool based on artificial intelligence (AI) algorithms to early detect the signs of exacerbation of chronic heart failure and predict the risk of its progression, by integrating high quality medical data obtained through a wearable device (L.I.F.E. Italia Srl's "wearable clinic" - a vest with accessories, which is a TRL 9 medical grade sensorized garment, already available on the market). Specifically, the focus will be on the early detection of CHF worsening in patients who have already been diagnosed with CHF.

Inclusion Criteria:

• Presence of symptoms and/or signs of HF
• left ventricular ejection fraction (LVEF) ≤40%. LVEF values will be obtained by determining the reduced LV systolic function, by transthoracic echocardiographic assessment as recommended by European Association of Cardiovascular Imaging (EACVI) and American Society of Echocardiography position paper.
• NYHA functional classes II-III).

Exclusion Criteria:

• NYHA functional class IV,
• Candidates for left-ventricular assist device (LVAD) or heart transplant, as per latest definition of Heart Failure Association of the ESC.
• Recent acute coronary syndrome within 1-year prior to the date of potential enrollment,
• Indirect echocardiographic evidence of significantly elevated pulmonary pressures
• Clinically relevant pulmonary hypertension
• non-adherence to optimal medical treatment for CHF

Patients with CHF will be considered for inclusion in the study based on their verified medical record, indicating that they are diagnosed with CHF and are using guideline-directed medical therapy (GDMT). Diagnostic criteria, as laid out in the latest 2021 European Society of Cardiology (ESC) guidelines for the diagnosis and management of chronic and acute heart failure, will be followed.