PhD Studentship: Causal AI: This fully funded PhD project focuses on developing AI-first causal models to improve continuous postoperative deterioration monitoring in global surgery. By utilizing continuous wearable sensing data from the EMUs multi-country datasets (linking Sibel ANNE® One waveforms to time-stamped events and 30-day outcomes), the research aims to flag early signs of deterioration better than intermittent ward observations. The project goes beyond simple prediction by quantifying the impact of alternative medical actions through counterfactual sequence prediction and off-policy evaluation of escalation strategies. The ultimate goal is to provide robust, equitable, and actionable decision support that highlights expected benefits, harms, and uncertainties across various global healthcare settings.
PhD Studentship: Causal AI for Continuous Postoperative Deterioration Monitoring in Global Surgery
Quick Facts Overview
| Feature | Details |
|---|---|
| Designation | PhD Studentship |
| Funding Status | Fully Funded (Fees and Stipend) |
| Host Institution | University of Edinburgh (School of Engineering) & CHAI Hub |
| Industry Partner | Sibel Health Inc. |
| Start Date | October 2026 |
| Application Deadline | 19th April 2026 at 1700 hrs GMT |
Designation
PhD Student / Early Career Researcher
Research Area
Artificial Intelligence in Healthcare, specifically focusing on Causal Machine Learning, Physiological Signal Processing, Wearable Sensing, and Global Surgical Care.
Location
Edinburgh, United Kingdom (The student must be based in Edinburgh for the duration of the program).
Job Description (Research Aims & Responsibilities)
As a PhD candidate, you will work at the intersection of causal AI and clinical data science. Your core responsibilities and research aims will include:
- Representation Learning: Learning high-fidelity, clinically grounded representations of postoperative physiology using continuous waveforms and contextual data.
- Causal Effect Estimation: Estimating the heterogeneous causal effects of time-varying clinical decisions (such as escalation of care, antibiotics, imaging, or ICU transfer) using AI-augmented counterfactual modeling.
- Policy Development: Developing transportable and fair causal decision policies that remain reliable under domain shift, missing data, and resource constraints.
- Clinical Co-design: Creating an interpretable prototype that compares “what if” trajectories under alternative care pathways to support shared clinical decision-making.
- Industry Placement: Participating in a placement with Sibel Health Inc. to gain hands-on experience with device data pipelines, edge deployment constraints, and software integration.
Eligibility and Qualifications
We are looking for candidates who demonstrate a strong motivation to learn and a thoughtful attitude toward responsible AI. A successful candidate will:
- Residency: Be a home student to the UK and willing to be based in Edinburgh.
- Educational Background: Possess a strong foundation in Computer Science, AI, Cognitive Science, Mathematics, Physics, Engineering, Biomedical Science, Biological Science, or Clinical & Public Health Sciences.
- Technical Skills: Demonstrate training in programming, data analysis, or computational thinking, ideally evidenced by the successful deployment of these skills in a practical project.
- Domain Interest: Have a genuine interest in biomedical or health applications and an awareness of the unique challenges within this sector.
- Ethical Awareness: Appreciate the ethical, societal, and patient-safety responsibilities of using AI in medicine, showing curiosity for fairness, transparency, and privacy.
- Mindset: Exhibit enthusiasm for engaging with public and patient communities, possess a collaborative and open mindset, and show a willingness to develop a broad, interdisciplinary skillset.
How to Apply
To apply for this PhD studentship, please prepare your supporting documents and submit them via email with the subject line: “Project funding by Prof. Tsaftaris and Sibel Health for CHAI”.
Required Documents:
- A Supporting Statement consisting of two parts:
- Part 1 (Max. 500 words): Detail your background, including education, relevant work experience, academic interests, career development goals, and what you hope to learn.
- Part 2 (Max. 750 words): Explain your suitability for the project. Highlight the skills, experiences, and attributes that make you a great fit, share your thoughts on the ethics of using AI in healthcare, and outline what you can bring to the project.
- An up-to-date CV.
- Degree certificates.
Contact Information for Inquiries:
- For general questions, contact CHAI Business Development Associate Rosanna Culver at
Rosanna.culver@ei.ed.ac.uk. - For scientific questions regarding the project, contact Prof. Ewen Harrison at
Ewen.Harrison@ed.ac.uk.
Note: Interviews will be held shortly after the application deadline. You can read more about the clinical trial data context here: NCT06565559 and BMJ Open Protocol.
Last Date for Apply
19th April 2026 at 1700 hrs GMT.
