Causal AI for Proactive Self-healthcare

With the aid of novel digital technologies, self-healthcare has changed the current healthcare practice in several ways such as easy access, less communication burden to Health Centres and reduced workload of health carers [1]. For example, the elders and patients with multi-morbidity benefit significantly through efficient tracking and management on their health [2]. With the surge of multimodal data arising from multi-channels including wearable devices, smart phones and telemedicine, AI have been widely adopted to provide disease diagnosis and prediction and optimised treatment [3].

However, these AI approaches are focused on relating a health condition to any potential predictors regardless whether there is a causal effect. It is hard to explain the clinical outcome for an individual patient by tracing back risk factors (e.g., age, lifestyle, family history, nutrition and environmental exposure). This project aims to improve the causal inferencing ability and interpretability of AI models leveraging multi-modal learning, causal inference, transfer learning and federal learning.

The proposed project will focus on the following three objectives,

1. Create innovative AI use cases for self-healthcare focusing on health assessment with the use of multimodal data.
2. Develop univariate causal inference frameworks to identify a pool of causal factors (e.g., nutrition) among other predictors for health assessment (e.g., survival).
3. Develop multimodal deep learning models, combined with circumstance of individual patients, for self-care decision support such as behaviour change and dietary.

Newcastle University is committed to being a fully inclusive Global University which actively recruits, supports and retains colleagues from all sectors of society. We value diversity as well as celebrate, support and thrive on the contributions of all our employees and the communities they represent.  We are proud to be an equal opportunities employer and encourage applications from everybody, regardless of race, sex, ethnicity, religion, nationality, sexual orientation, age, disability, gender identity, marital status/civil partnership, pregnancy and maternity, as well as being open to flexible working practices.

Application enquires: 

Dr Jingjing Zhang

Jingjing.Zhang@newcastle.ac.uk

https://www.ncl.ac.uk/engineering/staff/profile/jingjingzhang.html