Project Details
Description
U-Heal is an EWUU (https://ewuu.nl/) funded project aiming at developing a human-centered and explainable AI framework for a smart healthcare application in psychiatry that promotes distant self-care. Inspired by a similar initiative for preventing cardiovascular diseases (https://u-prevent.com/), U-HEAL aims at finding explainable AI solutions to improve the personalized treatment response in patients with psychosis.
U-Heal is a follow-up study on top of the Psychosis Prognosis Predictor (PPP) project, a ZonMw-funded research project, which leverages state-of-the-art explainable AI solutions including multi-modal and multi-task dynamic data modeling using deep learning and counterfactual inference for i) multi-aspect (e.g., symptomatic, functional, and clinical) personalized treatment outcome prediction and ii) optimizing the clinical treatments (e.g., the type and dosage of antipsychotic medications). While sharing a similar ambition (in optimizing the treatment response), U-HEAL, in contrast, aims at shifting the focus from the clinicians to the patients as end-users.
U-Heal is a follow-up study on top of the Psychosis Prognosis Predictor (PPP) project, a ZonMw-funded research project, which leverages state-of-the-art explainable AI solutions including multi-modal and multi-task dynamic data modeling using deep learning and counterfactual inference for i) multi-aspect (e.g., symptomatic, functional, and clinical) personalized treatment outcome prediction and ii) optimizing the clinical treatments (e.g., the type and dosage of antipsychotic medications). While sharing a similar ambition (in optimizing the treatment response), U-HEAL, in contrast, aims at shifting the focus from the clinicians to the patients as end-users.
Short title | User-centric HEAlthy Lifestyle recommender |
---|---|
Acronym | U-Heal |
Status | Finished |
Effective start/end date | 1/09/22 → 31/08/23 |
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.