FAITH project

FAITH project is rated 3 out of 5 in the category mental health care. Read and write reviews about FAITH project. FAITH is an EU-funded research project that aims at providing an Artificial Intelligence application that remotely identifies and analyses depression markers, using Federated Learning, to predict negative trends in people that have undergone cancer treatment. This concept would present healthcare providers with advanced warnings to allow timely intervention, and allow cancer patients to be more aware of their mental health situation and improve their quality of life. Obviously, FAITH does not intend to replace clinicians in diagnosing depression; rather, it works in support of clinicians, providing them with an additional tool to support post-cancer patients at risk of depression. The concept will be validated through trial sites in Madrid, Waterford, and Lisbon, involving real end users (both clinicians and post-cancer patients) able to assess and validate the tool and ensure its usefulness. Why is the project needed? Post-cancer patients are more likely to experience depression, thus presenting a higher risk of mortality and a poorer quality of life compared with non-depressed people. FAITH aims at improving their quality of life by supporting their mental health. How does FAITH work? The FAITH framework envisages the collection and monitoring of a range of health indicators, such as activity, sleep quality, outlook, appetite and social activity, to analyse and infer information about the mental status of a person in a non-intrusive way. In order to tackle privacy concerns related to the potentially sensitive data that the project intends to collect, FAITH makes use of Federated Learning. Federated Learning is a machine learning technique that trains an algorithm across multiple decentralized devices holding data samples locally. Thus, Federated Learning allows FAITH to analyse patients’ data whilst fully respecting their privacy, since the approach does not require the sensitive data to leave the person’s devices to be analysed.