The following is the summary of “A prospective observational study for a Federated Artificial Intelligence solution for moniToring mental Health status after cancer treatment (FAITH): study protocol” published in the December 2022 issue of Psychiatry by Lemos, et al.

Cancer patients frequently experience depression at different stages of their illness. Unfortunately, although having higher incidence rates than the general population, this is often not documented or goes unrecognized. It’s important to remember that cancer can manifest in various ways, and that somatic symptoms of sadness are not uncommon in the oncological context. Keeping tabs on emotional suffering after a treatment has ended is especially difficult because of the infrequent nature of most people’s interactions with the healthcare system during this time. Using a federated machine learning (ML) technique, the FAITH project aims to anticipate the onset of depression symptoms in cancer survivors from a distance while protecting their anonymity.

Depression biomarkers will be analyzed remotely by FAITH, and unfavorable patterns will be predicted. These indicators, which can be measured in part by means of wearable technology, will be handled separately, with special attention paid to the areas of diet, rest, exercise, and communication. Patients with a history of breast or lung cancer will be recruited for the trial between 1 and 5 years after their initial cancer has been treated. The research will follow cancer survivors for 12 months as part of a prospective observational cohort study, with monthly evaluations made to see how depressive symptoms and quality of life have changed over that time. Major depression, as judged by the Hamilton Depression Rating Scale (Ham-D) at 3, 6, 9, and 12 months is the primary outcome. Anxiety and depression symptoms (using the Hospital Anxiety and Depression Scale) and quality of life (using the European Organization for Research and Treatment of Cancer Questionnaires) are secondary outcomes. 

FAITH will also attempt to further develop a conceptual federated learning framework based on the obtained predictive models, allowing machine learning models for the prediction and monitoring of depression to be constructed without direct access to user-specific data. There is a pressing need for more objective psychiatric diagnosis and treatment methods. Smart jewelry has the potential to serve as biofeedback monitor and depression and anxiety early warning systems. To screen for depressed symptoms in oncological settings, healthcare systems may soon have access to a cutting-edge new tool if the FAITH app proves to be useful.