FAITH is an EU-funded research project that aims to provide an Artificial Intelligence application that remotely identifies depression markers using Federated Machine Learning to support people who have undergone cancer as well as their care giver and consultant team. FAITH focuses primarily with patients who have undergone either lung and breast cancer and applies the latest Artificial Intelligence and Big Data analytics techniques to better model post-treatment cancer patients. Post-cancer patients are particularly vulnerable to depression insurgence. Depression is one of the most common comorbidities in cancer patients: overall, people with cancer are at an increased risk of mortality in comparison with non-depressed patients. In fact, too often the symptoms of depression go unnoticed, or clinicians can dismiss them as being symptoms of cancer. Until their depression is eventually diagnosed and treated, these people experience tremendous suffering. The project is led by the Walton Institute for Information and Communications Systems Science (formally, WIT-Telecommunication Software and Systems Group), Ireland.
The project aims to build an ‘AI Angel’ that will remotely analyse depression markers. The markers are assessed in accordance with the traditional, tried and trusted 3M strategy – Monitor, Measure and Manage. As a result of the AI Angel application, FAITH will predict negative trends in patients’ disease trajectory, enabling better treatment and care to be realised. In order to analyse depression markers, FAITH will monitor data sources such as a patient’s activity, outlook, sleep, appetite and voice tone. The patients’ mobile phone will record all the data via an ‘Angel App’. The solution will be interfacing with the patient from home and will eventually send warnings to the hospital whenever suspicious red flags appear. In addition to this, FAITH will require only one extra device to monitor sleep. By using Federated Machine Learning, FAITH will deliver personalised AI models directly to each patient’s device, therefore, eliminating the requirement for data to be sent to the Cloud for processing. Using Federated Machine Learning enables privacy concerns relating to the potentially sensitive data to be overcome. Federated Machine Learning is a machine learning technique that trains an algorithm across multiple decentralized devices holding data samples locally. Thus, Federated Machine Learning enables 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. FAITH trials are in Waterford, Lisbon and Madrid.
TFC Research and Innovation Limited (@TFCRIL) operates in FAITH to enhance the project findings by working closely with the Project Coordinator in both quality and risk management as well as working across each work package leader. The company also leads the project clustering activities and heads up the standardisation and best practice development activities.
According to the World Health Organisation website (8th March 2021), cancer is the second leading cause of death globally, accounting for an estimated 9.6 million deaths, or one in six deaths, in 2018. Lung, prostate, colorectal, stomach and liver cancer are the most common types of cancer in men, while breast, colorectal, lung, cervical and thyroid cancer are the most common among women. The cancer burden continues to grow globally, exerting tremendous physical, emotional and financial strain on individuals, families, communities and health systems.
FAITH supports patients and healthcare providers in their post-cancer battle stage of life.