Heart failure (HF) is a prominent chronic disease, despite efforts in improving its prevention, diagnosis and treatment, represents the leading cause of disability and premature death throughout the world, while being is a heavy burden on health systems due to the multiple, prolonged hospitalizations required for patients suffering from it and the related management costs. Nevertheless, studies have shown that routine patient-physician or patient-nurse communication following discharge can result in significant reduction of hospitalizations. The pertinent collected patient data may include simple yet important information (e.g. patient weight), as well as previously difficult to obtain information such as routine ECG, ICD/CRT-D interrogation and pulmonary arterial pressure monitoring, which are now within reach due to technological progress. Motivated by the above, RETENTION aims to develop and deliver an innovative platform supporting enhanced clinical monitoring and interventions aimed at improving the clinical management of patients with chronic HF, reducing their mortality and hospitalisation rates, and improving their quality of life, safety, and well-being. The RETENTION platform will support clinical decision making and evidenced based personalised interventions for HF patients by: (a) continually monitoring and collecting medical, clinical, physiological, behavioural, psychosocial, and real-world data for such patients, (b) analysing these data using innovative model-driven big data analytics, statistical, artificial intelligence and machine learning techniques, (c) detecting patterns in the HF disease progression and the quality of life of patients, (d) cross checking and validating them against the clinical literature, and (e) offering transparent, explainable and verifiable decision making capabilities that leverage the evidence produced by the underlying data analysis and augment clinical studies targeting HF and other CVDs.

Heart failure (HF) is a chronic clinical condition involving up to 6.5 million people in Europe, the most frequent cause of hospitalization in adults with a 5-year mortality rate up to 70%. Several drugs positively modify the course of disease in the patients with HF with reduced ejection fraction (HFrEF), with a high level of evidence. Besides, the use of diuretics, the basic cornerstone of symptoms relief in HFrEF by targeting congestion, is supported by poor and outdated evidence. Congestion drives symptoms worsening leading to hospital admission. Clinical evaluation of congestion is often inaccurate and insensitive to detect interstitial or intravascular fluid overload, and thus insufficient to guide use of diuretics. Indeed, their use is inefficient, with studies showing that up to 70% of patients with chronic HFrEF show congestion despite diuretic therapy, the use of diuretics does prevent clinical events in patients discharged after an acute heart failure episode, and diuretics may represent a barrier to adherence to disease modifier therapies. An appropriate management of diuretic therapy is therefore crucial to overcome the risk of re-hospitalisation, manage patients symptoms, and achieve target guideline-directed medical therapy. To fill these gaps, BIOTOOL-CHF will 1) validate a set of qualified biomarkers estimating congestion, 2) define a multiparametric artificial intelligence-based score predicting congestion and prognosis, 3) develop a decision-making tool to manage congestion by diuretics, 4) develop a Point of Care companion diagnostic (CD) to assess biomarkers concentrations 5) set up a Strategy plan for industrial development and market access of the CD. This approach will support the definition of a framework to regulatory agencies and scientific societies to disseminate recommendations for a more efficient use of existing pharmaceuticals and allow a personalised strategy for the management of HFrEF, by using new tools and digital solutions.