ProfessorPayam Barnaghi
Chair in Machine Intelligence Applied to Medicine
Department of Brain Sciences - Faculty of Medicine
- Chair in Machine Intelligence Applied to MedicineDepartment of Brain Sciences - Faculty of Medicine
- Brain Sciences and UK DRI Care and Research Technology Centre, 9th Floor, Sir Michael Uren Hub, White City Campus, W12 0BZ, United Kingdom
BIO
Professor Payam Barnaghi is Chair in Machine Intelligence Applied to Medicine in the Department of Brain Sciences at Imperial College London. His research focuses on advancing artificial intelligence and machine learning for healthcare applications. His research group develops affordable, scalable digital solutions to improve outcomes across diverse health conditions, with a particular focus on neurodegenerative disorders and rare, complex diseases. Their work integrates statistical and probabilistic modelling, deep learning, natural language processing, and multimodal data fusion, leveraging large-scale electronic health records, neuroimaging, in-home monitoring, and wearable sensor data to enable early diagnosis, personalised care, and predictive modelling.
He holds the Great Ormond Street Hospital / Royal Academy of Engineering Research Chair in Machine Intelligence for Medicine, serves as Co-Director of the School of Convergence Science (Human and Artificial Intelligence), and is Deputy Head of the Division of Neurology at Imperial.
He contributes to several initiatives, including:
- Principal Investigator and Group Lead for Translational Machine Intelligence at the Care Research and Technology Centre, UK Dementia Research Institute (UK DRI)
- Co-Investigator and Steering Committee Member at the British Heart Foundation Centre for Research Excellence at Imperial
- Visiting Professor at the Great Ormond Street Institute of Child Health, University College London
- Member of boards and panels, including the UKRI Mental Health Platform Oversight Board, MRC Developmental Pathway Funding Scheme Panel, and MRC Gap Fund Panel for early-stage healthcare innovations
- Vice-Chair of the IEEE Special Interest Group on Big Data Intelligent Networking
He is an NVIDIA-certified instructor in Fundamentals of Deep Learning.
- Lab Homepage: https://tmi-lab.github.io
- UK DRI Profile: https://ukdri.ac.uk/team/payam-barnaghi
- GitHub: https://github.com/PBarnaghi/
- Teaching: https://ml4ns.github.io
Note: This page highlights a selection of my recent work. Like any researcher, I have had my share of rejected papers, grant applications, and fellowships. Adding the failures would have made the page very long.
Awards
- Mentorship (highly commended), Department of Brain Sciences, Imperial College London, June 2026.
- Mental Health Ideathon Award, Wellcome Trust (team award), July 2023.
- Mentorship Award, Department of Brain Sciences, Imperial College London, June 2023.
- Outstanding Service Award, The Web Intelligence Consortium (WIC), October 2019.
- IEEE Outstanding Leadership Award 2017.
- The Most Outstanding Innovation, Guildford's Innovation Awards (TIHM for Dementia project).
- HSJ 2018 Award for Improving Care with Technology (TIHM for Dementia project).
- Regional NHS Parliamentary Award, NHS 70th Anniversary, 2018 (TIHM for Dementia project).
- Best Mental Health Initiative Award, EHI 2017 Awards (TIHM for Dementia project)
A list of our public research software and datasets.
Full list: https://github.com/orgs/tmi-lab/repositories
🧠 Dementia & neurodegeneration related tools
AI tools to advance understanding, prediction, and monitoring in dementia.
- Theia - Decision‑support tool for dementia decline prediction.
https://github.com/tmi-lab/theia - AD‑VD Chronological Mapping - Mapping comorbidities in Alzheimer’s disease and vascular dementia.
https://github.com/tmi-lab/AD-VD-ChronologicalMapping - Sleep Biomarker for Dementia - Machine‑learning models linking sleep patterns to dementia risk.
https://github.com/tmi-lab/Sleep-Age-Dementia - 3BTRON - Blood-brain barrier recognition network.
https://github.com/tmi-lab/3BTRON - Analysing Activity Patterns (Markov‑Chain Model) - Markov‑chain model for detecting changes in eating and drinking patterns using in‑home activity monitoring data.
https://github.com/tmi-lab/Markov-Chain-Model
AI tools for EHR data analysis and clinical decision support in paediatric medicine.
- GOSH EHR Cardiology - Tools for predicting hospital stay and retrieving similar cases in paediatric cardiology.
https://github.com/tmi-lab/GOSH-EHR-cardiology
Platforms for real‑world, continuous health monitoring.
- Resilient - Platform integrating wearable device and in‑home monitoring data.
https://github.com/tmi-lab/resilient - Resilient Dataset - Backend and dataset supporting multimodal monitoring in ageing and dementia studies.
https://github.com/tmi-lab/Resilient-Platform-and-Dataset - TIHM Dataset - multimodal activity, sleep, physiology, and health‑event data from TIHM 1.5 dementia study
https://github.com/tmi-lab/TIHM-Dataset
Robust, explainable, and reliable ML methods for clinical AI.
- Loss Adapted Plasticity - Methods for learning from noisy or out‑of‑distribution multi‑source data.
https://github.com/tmi-lab/loss_adapted_plasticity - Entropy Analysis for Time‑Series Data - Entropy‑based analysis pipeline.
https://github.com/tmi-lab/EntropyPipeline - Time Series and Transformers Analysis - Analysis and benchmarking of transformer models for time‑series forecasting.
https://github.com/tmi-lab/TimeSeries-Transformers-Analysis
Extracting meaningful structure from complex biomedical and behavioural datasets.
- Text‑Encoders for Daily Movement Data - Representation learning for movement and activity patterns.
https://github.com/tmi-lab/Text-Encoders-For-Daily-Movement-Data
Leveraging large language models to enhance predictive modelling pipelines.
- AutoElicit - LLM‑elicited priors for predictive modelling.
https://github.com/tmi-lab/autoelicit
Utilities that improve usability, accessibility, and workflow support.
- UK Biobank–DNANexus Accessibility CSS - Accessibility‑enhancing stylesheet for DNAnexus UK Biobank interface.
https://github.com/tmi-lab/ukb-dnanexus-accessibility-css - Clinical Trials Retention Rate Prediction - Machine learning models for predicting retention and dropout in clinical trials.
https://github.com/tmi-lab/ClinicalTrialsRetentionRatePrediction
ACADEMIC POSITIONS
- Great Ormond Street Hospital / Royal Academy of Engineering Research Chair in Machine Intelligence for MedicineImperial College London, Brain Sciences, London, United Kingdom1 Apr 2024 - present
- Chair in Machine Intelligence Applied to MedicineImperial College London, Brain Sciences, London, United Kingdom1 Sep 2020 - present
- Co-Director, the School of Convergence Science in Human and Artificial IntelligenceImperial College London, London, United Kingdom1 Oct 2024 - present
- Deputy Head of Division of NeurologyImperial College London, Brain Sciences, London, United Kingdom1 May 2023 - present
- Visiting ProfessorUniversity College London, The Great Ormond Street Institute of Child Health, London, United Kingdom1 Dec 2021 - present
NON-ACADEMIC POSITIONS
- Visiting ResearcherGreat Ormond Street Hospital for Children NHS Foundation Trust, London, United Kingdom1 Feb 2023 - present
- Member of the Scientific Advisory BoardVesalic Ltd., United Kingdom3 Jun 2024 - present
- Member of the Medical Advisory CommitteeSir Jules Thorn Charitable Trust, United Kingdom2 Feb 2026 - present
CERTIFICATIONS
- NVIDIA Deep Learning Institute (DLI) University AmbassadorNvidia (United States)
- Mental Health First AiderMental Health First Aid England®
- Fellow of the Higher Education AcademyThe Higher Education Academy
FACULTY
- Faculty of Medicine
POSITION NAME
- Chair in Machine Intelligence Applied to Medicine