AID-HF

Heart failure (HF) is the most common reason for hospitalisation of elderly patients in developed countries. Heart failure is characterised by periods of sudden worsening of symptoms, called decompensation. The majority of hospital admissions are of patients with decompensated chronic heart failure. To prevent decompensation, HF patients can be monitored via telemedicine to detect worsening heart failure early. However, therapeutic interventions for decompensation, usually adjustments of urinary agents, are performed by physicians or nurse specialists and self-care is limited.
We will develop a decision support system based on artificial intelligence to enable HF patients to self-adjust their urinary drugs. We will combine expertise and knowledge from clinical data using machine-learning algorithms. With this, we will develop a model that can make personalised predictions about a patient's risk of decompensation based on their clinical data, their symptoms and current therapy. By combining these predictions and the preferences of clinicians and patients, our decision support system will be able to provide timely personalised advice, such as changing the patient's therapy with urinary drugs or referring the patient to the clinic. This will increase the quality of self-care of patients with HF, avoid unnecessary consultations with healthcare providers and reduce the risk of hospital admissions due to cardiac decompensation. This will reduce healthcare costs and resource utilisation. We plan to implement this eHealth solution as a module that can be integrated into various telemonitoring applications.

This is a grant from the healthcare innovation and research funding organisation ZonMW.